| <!DOCTYPE html> |
| |
| <html xmlns="http://www.w3.org/1999/xhtml"> |
| <head> |
| <meta charset="utf-8" /> |
| <meta charset="utf-8"> |
| <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"> |
| <meta http-equiv="x-ua-compatible" content="ie=edge"> |
| <style> |
| .dropdown { |
| position: relative; |
| display: inline-block; |
| } |
| |
| .dropdown-content { |
| display: none; |
| position: absolute; |
| background-color: #f9f9f9; |
| min-width: 160px; |
| box-shadow: 0px 8px 16px 0px rgba(0,0,0,0.2); |
| padding: 12px 16px; |
| z-index: 1; |
| text-align: left; |
| } |
| |
| .dropdown:hover .dropdown-content { |
| display: block; |
| } |
| |
| .dropdown-option:hover { |
| color: #FF4500; |
| } |
| |
| .dropdown-option-active { |
| color: #FF4500; |
| font-weight: lighter; |
| } |
| |
| .dropdown-option { |
| color: #000000; |
| font-weight: lighter; |
| } |
| |
| .dropdown-header { |
| color: #FFFFFF; |
| display: inline-flex; |
| } |
| |
| .dropdown-caret { |
| width: 18px; |
| height: 54px; |
| } |
| |
| .dropdown-caret-path { |
| fill: #FFFFFF; |
| } |
| </style> |
| |
| <title>gluon.loss — Apache MXNet documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/mxnet.css" /> |
| <link rel="stylesheet" href="../../../_static/material-design-lite-1.3.0/material.blue-deep_orange.min.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/sphinx_materialdesign_theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/fontawesome/all.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/fonts.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/feedback.css" type="text/css" /> |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/matomo_analytics.js"></script> |
| <script src="../../../_static/autodoc.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <script src="../../../_static/sphinx_materialdesign_theme.js"></script> |
| <link rel="shortcut icon" href="../../../_static/mxnet-icon.png"/> |
| <link rel="index" title="Index" href="../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <link rel="next" title="gluon.metric" href="../metric/index.html" /> |
| <link rel="prev" title="vision.transforms" href="../data/vision/transforms/index.html" /> |
| </head> |
| <body><header class="site-header" role="banner"> |
| <div class="wrapper"> |
| <a class="site-title" rel="author" href="/"><img |
| src="../../../_static/mxnet_logo.png" class="site-header-logo"></a> |
| <nav class="site-nav"> |
| <input type="checkbox" id="nav-trigger" class="nav-trigger"/> |
| <label for="nav-trigger"> |
| <span class="menu-icon"> |
| <svg viewBox="0 0 18 15" width="18px" height="15px"> |
| <path d="M18,1.484c0,0.82-0.665,1.484-1.484,1.484H1.484C0.665,2.969,0,2.304,0,1.484l0,0C0,0.665,0.665,0,1.484,0 h15.032C17.335,0,18,0.665,18,1.484L18,1.484z M18,7.516C18,8.335,17.335,9,16.516,9H1.484C0.665,9,0,8.335,0,7.516l0,0 c0-0.82,0.665-1.484,1.484-1.484h15.032C17.335,6.031,18,6.696,18,7.516L18,7.516z M18,13.516C18,14.335,17.335,15,16.516,15H1.484 C0.665,15,0,14.335,0,13.516l0,0c0-0.82,0.665-1.483,1.484-1.483h15.032C17.335,12.031,18,12.695,18,13.516L18,13.516z"/> |
| </svg> |
| </span> |
| </label> |
| |
| <div class="trigger"> |
| <a class="page-link" href="/get_started">Get Started</a> |
| <a class="page-link" href="/features">Features</a> |
| <a class="page-link" href="/ecosystem">Ecosystem</a> |
| <a class="page-link page-current" href="/api">Docs & Tutorials</a> |
| <a class="page-link" href="/trusted_by">Trusted By</a> |
| <a class="page-link" href="https://github.com/apache/mxnet">GitHub</a> |
| <div class="dropdown" style="min-width:100px"> |
| <span class="dropdown-header">Apache |
| <svg class="dropdown-caret" viewBox="0 0 32 32" class="icon icon-caret-bottom" aria-hidden="true"><path class="dropdown-caret-path" d="M24 11.305l-7.997 11.39L8 11.305z"></path></svg> |
| </span> |
| <div class="dropdown-content" style="min-width:250px"> |
| <a href="https://www.apache.org/foundation/">Apache Software Foundation</a> |
| <a href="https://incubator.apache.org/">Apache Incubator</a> |
| <a href="https://www.apache.org/licenses/">License</a> |
| <a href="/versions/1.9.1/api/faq/security.html">Security</a> |
| <a href="https://privacy.apache.org/policies/privacy-policy-public.html">Privacy</a> |
| <a href="https://www.apache.org/events/current-event">Events</a> |
| <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a> |
| <a href="https://www.apache.org/foundation/thanks.html">Thanks</a> |
| </div> |
| </div> |
| <div class="dropdown"> |
| <span class="dropdown-header">master |
| <svg class="dropdown-caret" viewBox="0 0 32 32" class="icon icon-caret-bottom" aria-hidden="true"><path class="dropdown-caret-path" d="M24 11.305l-7.997 11.39L8 11.305z"></path></svg> |
| </span> |
| <div class="dropdown-content"> |
| <a class="dropdown-option-active" href="/versions/master/">master</a><br> |
| <a class="dropdown-option" href="/versions/1.9.1/">1.9.1</a><br> |
| <a class="dropdown-option" href="/versions/1.8.0/">1.8.0</a><br> |
| <a class="dropdown-option" href="/versions/1.7.0/">1.7.0</a><br> |
| <a class="dropdown-option" href="/versions/1.6.0/">1.6.0</a><br> |
| <a class="dropdown-option" href="/versions/1.5.0/">1.5.0</a><br> |
| <a class="dropdown-option" href="/versions/1.4.1/">1.4.1</a><br> |
| <a class="dropdown-option" href="/versions/1.3.1/">1.3.1</a><br> |
| <a class="dropdown-option" href="/versions/1.2.1/">1.2.1</a><br> |
| <a class="dropdown-option" href="/versions/1.1.0/">1.1.0</a><br> |
| <a class="dropdown-option" href="/versions/1.0.0/">1.0.0</a><br> |
| <a class="dropdown-option" href="/versions/0.12.1/">0.12.1</a><br> |
| <a class="dropdown-option" href="/versions/0.11.0/">0.11.0</a> |
| </div> |
| </div> |
| </div> |
| </nav> |
| </div> |
| </header> |
| <div class="mdl-layout mdl-js-layout mdl-layout--fixed-header mdl-layout--fixed-drawer"><header class="mdl-layout__header mdl-layout__header--waterfall "> |
| <div class="mdl-layout__header-row"> |
| |
| <nav class="mdl-navigation breadcrumb"> |
| <a class="mdl-navigation__link" href="../../index.html">Python API</a><i class="material-icons">navigate_next</i> |
| <a class="mdl-navigation__link" href="../index.html">mxnet.gluon</a><i class="material-icons">navigate_next</i> |
| <a class="mdl-navigation__link is-active">gluon.loss</a> |
| </nav> |
| <div class="mdl-layout-spacer"></div> |
| <nav class="mdl-navigation"> |
| |
| <form class="form-inline pull-sm-right" action="../../../search.html" method="get"> |
| <div class="mdl-textfield mdl-js-textfield mdl-textfield--expandable mdl-textfield--floating-label mdl-textfield--align-right"> |
| <label id="quick-search-icon" class="mdl-button mdl-js-button mdl-button--icon" for="waterfall-exp"> |
| <i class="material-icons">search</i> |
| </label> |
| <div class="mdl-textfield__expandable-holder"> |
| <input class="mdl-textfield__input" type="text" name="q" id="waterfall-exp" placeholder="Search" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </div> |
| </div> |
| <div class="mdl-tooltip" data-mdl-for="quick-search-icon"> |
| Quick search |
| </div> |
| </form> |
| |
| <a id="button-show-github" |
| href="https://github.com/apache/mxnet/edit/master/docs/python_docs/python/api/gluon/loss/index.rst" class="mdl-button mdl-js-button mdl-button--icon"> |
| <i class="material-icons">edit</i> |
| </a> |
| <div class="mdl-tooltip" data-mdl-for="button-show-github"> |
| Edit on Github |
| </div> |
| </nav> |
| </div> |
| <div class="mdl-layout__header-row header-links"> |
| <div class="mdl-layout-spacer"></div> |
| <nav class="mdl-navigation"> |
| </nav> |
| </div> |
| </header><header class="mdl-layout__drawer"> |
| |
| <div class="globaltoc"> |
| <span class="mdl-layout-title toc">Table Of Contents</span> |
| |
| |
| |
| <nav class="mdl-navigation"> |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index.html">Python Tutorials</a><ul> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/getting-started/index.html">Getting Started</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/index.html">Crash Course</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/0-introduction.html">Introduction</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/1-nparray.html">Step 1: Manipulate data with NP on MXNet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/2-create-nn.html">Step 2: Create a neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/3-autograd.html">Step 3: Automatic differentiation with autograd</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/4-components.html">Step 4: Necessary components that are not in the network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html">Step 5: <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#Using-your-own-data-with-custom-Datasets">Using your own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#New-in-MXNet-2.0:-faster-C++-backend-dataloaders">New in MXNet 2.0: faster C++ backend dataloaders</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/6-train-nn.html">Step 6: Train a Neural Network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/7-use-gpus.html">Step 7: Load and Run a NN using GPU</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/index.html">Moving to MXNet from Other Frameworks</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/pytorch.html">PyTorch vs Apache MXNet</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_from_experiment_to_deployment.html">Gluon: from experiment to deployment</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_migration_guide.html">Gluon2.0: Migration Guide</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/logistic_regression_explained.html">Logistic regression explained</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/image/mnist.html">MNIST</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/packages/index.html">Packages</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/autograd/index.html">Automatic Differentiation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/gluon/index.html">Gluon</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/index.html">Blocks</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/custom-layer.html">Custom Layers</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/hybridize.html">Hybridize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/init.html">Initialization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/naming.html">Parameter and Block Naming</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/nn.html">Layers and Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/parameters.html">Parameter Management</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/activations/activations.html">Activation Blocks</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/data/index.html">Data Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html">Image Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html">Gluon <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-custom-Datasets">Using own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Appendix:-Upgrading-from-Module-DataIter-to-Gluon-DataLoader">Appendix: Upgrading from Module <code class="docutils literal notranslate"><span class="pre">DataIter</span></code> to Gluon <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/image/index.html">Image Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/info_gan.html">Image similarity search with InfoGAN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/mnist.html">Handwritten Digit Recognition</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/index.html">Losses</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/custom-loss.html">Custom Loss Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/kl_divergence.html">Kullback-Leibler (KL) Divergence</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/loss.html">Loss functions</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/text/index.html">Text Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/gnmt.html">Google Neural Machine Translation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/transformer.html">Machine Translation with Transformer</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/training/index.html">Training</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/fit_api_tutorial.html">MXNet Gluon Fit API</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/trainer.html">Trainer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/index.html">Learning Rates</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_finder.html">Learning Rate Finder</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules.html">Learning Rate Schedules</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules_advanced.html">Advanced Learning Rate Schedules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/normalization/index.html">Normalization Blocks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/kvstore/index.html">KVStore</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/kvstore/kvstore.html">Distributed Key-Value Store</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/legacy/index.html">Legacy</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/index.html">NDArray</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/01-ndarray-intro.html">An Intro: Manipulate Data the MXNet Way with NDArray</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/02-ndarray-operations.html">NDArray Operations</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/03-ndarray-contexts.html">NDArray Contexts</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/gotchas_numpy_in_mxnet.html">Gotchas using NumPy in Apache MXNet</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/index.html">Tutorials</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/csr.html">CSRNDArray - NDArray in Compressed Sparse Row Storage Format</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/row_sparse.html">RowSparseNDArray - NDArray for Sparse Gradient Updates</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/np/index.html">What is NP on MXNet</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/np/cheat-sheet.html">The NP on MXNet cheat sheet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/np/np-vs-numpy.html">Differences between NP on MXNet and NumPy</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/onnx/index.html">ONNX</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/fine_tuning_gluon.html">Fine-tuning an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/inference_on_onnx_model.html">Running inference on MXNet/Gluon from an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html">Export ONNX Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/optimizer/index.html">Optimizers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/viz/index.html">Visualization</a><ul> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/visualize_graph">Visualize networks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/performance/index.html">Performance</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/compression/index.html">Compression</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/compression/int8.html">Deploy with int-8</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/float16">Float16</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/gradient_compression">Gradient Compression</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html">GluonCV with Quantized Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/backend/index.html">Accelerated Backend Tools</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/index.html">oneDNN</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_readme.html">Install MXNet with oneDNN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_quantization.html">oneDNN Quantization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_quantization_inc.html">Improving accuracy with Intel® Neural Compressor</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tvm.html">Use TVM</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/profiler.html">Profiling MXNet Models</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/amp.html">Using AMP: Automatic Mixed Precision</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/deploy/index.html">Deployment</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/export/index.html">Export</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/export/onnx.html">Exporting to ONNX format</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/export_network.html">Export Gluon CV Models</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Save / Load Parameters</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/inference/index.html">Inference</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/cpp.html">Deploy into C++</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/image_classification_jetson.html">Image Classication using pretrained ResNet-50 model on Jetson module</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/index.html">Run on AWS</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_ec2.html">Run on an EC2 Instance</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_sagemaker.html">Run on Amazon SageMaker</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/cloud.html">MXNet on the Cloud</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/extend/index.html">Extend</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/extend/customop.html">Custom Numpy Operators</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/new_op">New Operator Creation</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/add_op_in_backend">New Operator in MXNet Backend</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/using_rtc">Using RTC for CUDA kernels</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1 current"><a class="reference internal" href="../../index.html">Python API</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="../../np/index.html">mxnet.np</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../np/arrays.html">Array objects</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/arrays.ndarray.html">The N-dimensional array (<code class="xref py py-class docutils literal notranslate"><span class="pre">ndarray</span></code>)</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/arrays.indexing.html">Indexing</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../np/routines.html">Routines</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.array-creation.html">Array creation routines</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.eye.html">mxnet.np.eye</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.empty.html">mxnet.np.empty</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.full.html">mxnet.np.full</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.identity.html">mxnet.np.identity</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ones.html">mxnet.np.ones</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ones_like.html">mxnet.np.ones_like</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.zeros.html">mxnet.np.zeros</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.zeros_like.html">mxnet.np.zeros_like</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.array.html">mxnet.np.array</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.copy.html">mxnet.np.copy</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arange.html">mxnet.np.arange</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linspace.html">mxnet.np.linspace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.logspace.html">mxnet.np.logspace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.meshgrid.html">mxnet.np.meshgrid</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tril.html">mxnet.np.tril</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.array-manipulation.html">Array manipulation routines</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.reshape.html">mxnet.np.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ravel.html">mxnet.np.ravel</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ndarray.flatten.html">mxnet.np.ndarray.flatten</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.swapaxes.html">mxnet.np.swapaxes</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ndarray.T.html">mxnet.np.ndarray.T</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.transpose.html">mxnet.np.transpose</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.moveaxis.html">mxnet.np.moveaxis</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.rollaxis.html">mxnet.np.rollaxis</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.expand_dims.html">mxnet.np.expand_dims</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.squeeze.html">mxnet.np.squeeze</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.broadcast_to.html">mxnet.np.broadcast_to</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.broadcast_arrays.html">mxnet.np.broadcast_arrays</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.atleast_1d.html">mxnet.np.atleast_1d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.atleast_2d.html">mxnet.np.atleast_2d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.atleast_3d.html">mxnet.np.atleast_3d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.concatenate.html">mxnet.np.concatenate</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.stack.html">mxnet.np.stack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.dstack.html">mxnet.np.dstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.vstack.html">mxnet.np.vstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.column_stack.html">mxnet.np.column_stack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.hstack.html">mxnet.np.hstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.split.html">mxnet.np.split</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.hsplit.html">mxnet.np.hsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.vsplit.html">mxnet.np.vsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.array_split.html">mxnet.np.array_split</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.dsplit.html">mxnet.np.dsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tile.html">mxnet.np.tile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.repeat.html">mxnet.np.repeat</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.unique.html">mxnet.np.unique</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.delete.html">mxnet.np.delete</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.insert.html">mxnet.np.insert</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.append.html">mxnet.np.append</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.resize.html">mxnet.np.resize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.trim_zeros.html">mxnet.np.trim_zeros</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.reshape.html">mxnet.np.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.flip.html">mxnet.np.flip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.roll.html">mxnet.np.roll</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.rot90.html">mxnet.np.rot90</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fliplr.html">mxnet.np.fliplr</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.flipud.html">mxnet.np.flipud</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.io.html">Input and output</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.genfromtxt.html">mxnet.np.genfromtxt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ndarray.tolist.html">mxnet.np.ndarray.tolist</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.set_printoptions.html">mxnet.np.set_printoptions</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.linalg.html">Linear algebra (<code class="xref py py-mod docutils literal notranslate"><span class="pre">numpy.linalg</span></code>)</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.dot.html">mxnet.np.dot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.vdot.html">mxnet.np.vdot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.inner.html">mxnet.np.inner</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.outer.html">mxnet.np.outer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tensordot.html">mxnet.np.tensordot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.einsum.html">mxnet.np.einsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.multi_dot.html">mxnet.np.linalg.multi_dot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.matmul.html">mxnet.np.matmul</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.matrix_power.html">mxnet.np.linalg.matrix_power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.kron.html">mxnet.np.kron</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.svd.html">mxnet.np.linalg.svd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.cholesky.html">mxnet.np.linalg.cholesky</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.qr.html">mxnet.np.linalg.qr</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.eig.html">mxnet.np.linalg.eig</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.eigh.html">mxnet.np.linalg.eigh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.eigvals.html">mxnet.np.linalg.eigvals</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.eigvalsh.html">mxnet.np.linalg.eigvalsh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.norm.html">mxnet.np.linalg.norm</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.trace.html">mxnet.np.trace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.cond.html">mxnet.np.linalg.cond</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.det.html">mxnet.np.linalg.det</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.matrix_rank.html">mxnet.np.linalg.matrix_rank</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.slogdet.html">mxnet.np.linalg.slogdet</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.solve.html">mxnet.np.linalg.solve</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.tensorsolve.html">mxnet.np.linalg.tensorsolve</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.lstsq.html">mxnet.np.linalg.lstsq</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.inv.html">mxnet.np.linalg.inv</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.pinv.html">mxnet.np.linalg.pinv</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.tensorinv.html">mxnet.np.linalg.tensorinv</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.math.html">Mathematical functions</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sin.html">mxnet.np.sin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cos.html">mxnet.np.cos</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tan.html">mxnet.np.tan</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arcsin.html">mxnet.np.arcsin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arccos.html">mxnet.np.arccos</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arctan.html">mxnet.np.arctan</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.degrees.html">mxnet.np.degrees</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.radians.html">mxnet.np.radians</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.hypot.html">mxnet.np.hypot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arctan2.html">mxnet.np.arctan2</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.deg2rad.html">mxnet.np.deg2rad</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.rad2deg.html">mxnet.np.rad2deg</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.unwrap.html">mxnet.np.unwrap</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sinh.html">mxnet.np.sinh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cosh.html">mxnet.np.cosh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tanh.html">mxnet.np.tanh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arcsinh.html">mxnet.np.arcsinh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arccosh.html">mxnet.np.arccosh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arctanh.html">mxnet.np.arctanh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.rint.html">mxnet.np.rint</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fix.html">mxnet.np.fix</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.floor.html">mxnet.np.floor</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ceil.html">mxnet.np.ceil</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.trunc.html">mxnet.np.trunc</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.around.html">mxnet.np.around</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.round_.html">mxnet.np.round_</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sum.html">mxnet.np.sum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.prod.html">mxnet.np.prod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cumsum.html">mxnet.np.cumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanprod.html">mxnet.np.nanprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nansum.html">mxnet.np.nansum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cumprod.html">mxnet.np.cumprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nancumprod.html">mxnet.np.nancumprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nancumsum.html">mxnet.np.nancumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.diff.html">mxnet.np.diff</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ediff1d.html">mxnet.np.ediff1d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cross.html">mxnet.np.cross</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.trapz.html">mxnet.np.trapz</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.exp.html">mxnet.np.exp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.expm1.html">mxnet.np.expm1</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.log.html">mxnet.np.log</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.log10.html">mxnet.np.log10</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.log2.html">mxnet.np.log2</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.log1p.html">mxnet.np.log1p</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.logaddexp.html">mxnet.np.logaddexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.i0.html">mxnet.np.i0</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ldexp.html">mxnet.np.ldexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.signbit.html">mxnet.np.signbit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.copysign.html">mxnet.np.copysign</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.frexp.html">mxnet.np.frexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.spacing.html">mxnet.np.spacing</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.lcm.html">mxnet.np.lcm</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.gcd.html">mxnet.np.gcd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.add.html">mxnet.np.add</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.reciprocal.html">mxnet.np.reciprocal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.negative.html">mxnet.np.negative</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.divide.html">mxnet.np.divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.power.html">mxnet.np.power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.subtract.html">mxnet.np.subtract</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.mod.html">mxnet.np.mod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.multiply.html">mxnet.np.multiply</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.true_divide.html">mxnet.np.true_divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.remainder.html">mxnet.np.remainder</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.positive.html">mxnet.np.positive</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.float_power.html">mxnet.np.float_power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fmod.html">mxnet.np.fmod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.modf.html">mxnet.np.modf</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.divmod.html">mxnet.np.divmod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.floor_divide.html">mxnet.np.floor_divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.clip.html">mxnet.np.clip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sqrt.html">mxnet.np.sqrt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cbrt.html">mxnet.np.cbrt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.square.html">mxnet.np.square</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.absolute.html">mxnet.np.absolute</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sign.html">mxnet.np.sign</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.maximum.html">mxnet.np.maximum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.minimum.html">mxnet.np.minimum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fabs.html">mxnet.np.fabs</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.heaviside.html">mxnet.np.heaviside</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fmax.html">mxnet.np.fmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fmin.html">mxnet.np.fmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nan_to_num.html">mxnet.np.nan_to_num</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.interp.html">mxnet.np.interp</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/random/index.html">np.random</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.choice.html">mxnet.np.random.choice</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.shuffle.html">mxnet.np.random.shuffle</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.normal.html">mxnet.np.random.normal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.uniform.html">mxnet.np.random.uniform</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.rand.html">mxnet.np.random.rand</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.randint.html">mxnet.np.random.randint</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.beta.html">mxnet.np.random.beta</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.chisquare.html">mxnet.np.random.chisquare</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.exponential.html">mxnet.np.random.exponential</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.f.html">mxnet.np.random.f</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.gamma.html">mxnet.np.random.gamma</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.gumbel.html">mxnet.np.random.gumbel</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.laplace.html">mxnet.np.random.laplace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.logistic.html">mxnet.np.random.logistic</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.lognormal.html">mxnet.np.random.lognormal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.multinomial.html">mxnet.np.random.multinomial</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.multivariate_normal.html">mxnet.np.random.multivariate_normal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.pareto.html">mxnet.np.random.pareto</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.power.html">mxnet.np.random.power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.rayleigh.html">mxnet.np.random.rayleigh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.weibull.html">mxnet.np.random.weibull</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.sort.html">Sorting, searching, and counting</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ndarray.sort.html">mxnet.np.ndarray.sort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sort.html">mxnet.np.sort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.lexsort.html">mxnet.np.lexsort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argsort.html">mxnet.np.argsort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.msort.html">mxnet.np.msort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.partition.html">mxnet.np.partition</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argpartition.html">mxnet.np.argpartition</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argmax.html">mxnet.np.argmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argmin.html">mxnet.np.argmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanargmax.html">mxnet.np.nanargmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanargmin.html">mxnet.np.nanargmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argwhere.html">mxnet.np.argwhere</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nonzero.html">mxnet.np.nonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.flatnonzero.html">mxnet.np.flatnonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.where.html">mxnet.np.where</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.searchsorted.html">mxnet.np.searchsorted</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.extract.html">mxnet.np.extract</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.count_nonzero.html">mxnet.np.count_nonzero</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.statistics.html">Statistics</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.min.html">mxnet.np.min</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.max.html">mxnet.np.max</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.amin.html">mxnet.np.amin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.amax.html">mxnet.np.amax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanmin.html">mxnet.np.nanmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanmax.html">mxnet.np.nanmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ptp.html">mxnet.np.ptp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.percentile.html">mxnet.np.percentile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanpercentile.html">mxnet.np.nanpercentile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.quantile.html">mxnet.np.quantile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanquantile.html">mxnet.np.nanquantile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.mean.html">mxnet.np.mean</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.std.html">mxnet.np.std</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.var.html">mxnet.np.var</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.median.html">mxnet.np.median</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.average.html">mxnet.np.average</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanmedian.html">mxnet.np.nanmedian</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanstd.html">mxnet.np.nanstd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanvar.html">mxnet.np.nanvar</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.corrcoef.html">mxnet.np.corrcoef</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.correlate.html">mxnet.np.correlate</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cov.html">mxnet.np.cov</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.histogram.html">mxnet.np.histogram</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.histogram2d.html">mxnet.np.histogram2d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.histogramdd.html">mxnet.np.histogramdd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.bincount.html">mxnet.np.bincount</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.histogram_bin_edges.html">mxnet.np.histogram_bin_edges</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.digitize.html">mxnet.np.digitize</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../npx/index.html">NPX: NumPy Neural Network Extension</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.set_np.html">mxnet.npx.set_np</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.reset_np.html">mxnet.npx.reset_np</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.cpu.html">mxnet.npx.cpu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.cpu_pinned.html">mxnet.npx.cpu_pinned</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.gpu.html">mxnet.npx.gpu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.gpu_memory_info.html">mxnet.npx.gpu_memory_info</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.current_device.html">mxnet.npx.current_device</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.num_gpus.html">mxnet.npx.num_gpus</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.activation.html">mxnet.npx.activation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.batch_norm.html">mxnet.npx.batch_norm</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.convolution.html">mxnet.npx.convolution</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.dropout.html">mxnet.npx.dropout</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.embedding.html">mxnet.npx.embedding</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.fully_connected.html">mxnet.npx.fully_connected</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.layer_norm.html">mxnet.npx.layer_norm</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.pooling.html">mxnet.npx.pooling</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.rnn.html">mxnet.npx.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.leaky_relu.html">mxnet.npx.leaky_relu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.multibox_detection.html">mxnet.npx.multibox_detection</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.multibox_prior.html">mxnet.npx.multibox_prior</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.multibox_target.html">mxnet.npx.multibox_target</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.roi_pooling.html">mxnet.npx.roi_pooling</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.sigmoid.html">mxnet.npx.sigmoid</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.relu.html">mxnet.npx.relu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.smooth_l1.html">mxnet.npx.smooth_l1</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.softmax.html">mxnet.npx.softmax</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.log_softmax.html">mxnet.npx.log_softmax</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.topk.html">mxnet.npx.topk</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.waitall.html">mxnet.npx.waitall</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.load.html">mxnet.npx.load</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.save.html">mxnet.npx.save</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.one_hot.html">mxnet.npx.one_hot</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.pick.html">mxnet.npx.pick</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.reshape_like.html">mxnet.npx.reshape_like</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.batch_flatten.html">mxnet.npx.batch_flatten</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.batch_dot.html">mxnet.npx.batch_dot</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.gamma.html">mxnet.npx.gamma</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.sequence_mask.html">mxnet.npx.sequence_mask</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2 current"><a class="reference internal" href="../index.html">mxnet.gluon</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="../block.html">gluon.Block</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../hybrid_block.html">gluon.HybridBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../symbol_block.html">gluon.SymbolBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../constant.html">gluon.Constant</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../parameter.html">gluon.Parameter</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../trainer.html">gluon.Trainer</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../contrib/index.html">gluon.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../data/index.html">gluon.data</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../data/vision/index.html">data.vision</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../data/vision/datasets/index.html">vision.datasets</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../data/vision/transforms/index.html">vision.transforms</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="#">gluon.loss</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../metric/index.html">gluon.metric</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../model_zoo/index.html">gluon.model_zoo.vision</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../nn/index.html">gluon.nn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../rnn/index.html">gluon.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../utils/index.html">gluon.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../autograd/index.html">mxnet.autograd</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../initializer/index.html">mxnet.initializer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../optimizer/index.html">mxnet.optimizer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../lr_scheduler/index.html">mxnet.lr_scheduler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html">KVStore: Communication for Distributed Training</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html#horovod">Horovod</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.Horovod.html">mxnet.kvstore.Horovod</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html#byteps">BytePS</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.BytePS.html">mxnet.kvstore.BytePS</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html#kvstore-interface">KVStore Interface</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.KVStore.html">mxnet.kvstore.KVStore</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.KVStoreBase.html">mxnet.kvstore.KVStoreBase</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.KVStoreServer.html">mxnet.kvstore.KVStoreServer</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../contrib/index.html">mxnet.contrib</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/io/index.html">contrib.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/ndarray/index.html">contrib.ndarray</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/onnx/index.html">contrib.onnx</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/quantization/index.html">contrib.quantization</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/symbol/index.html">contrib.symbol</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/tensorboard/index.html">contrib.tensorboard</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/tensorrt/index.html">contrib.tensorrt</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/text/index.html">contrib.text</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../legacy/index.html">Legacy</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/callback/index.html">mxnet.callback</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/image/index.html">mxnet.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/io/index.html">mxnet.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/ndarray/index.html">mxnet.ndarray</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/ndarray.html">ndarray</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/contrib/index.html">ndarray.contrib</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/image/index.html">ndarray.image</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/linalg/index.html">ndarray.linalg</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/op/index.html">ndarray.op</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/random/index.html">ndarray.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/register/index.html">ndarray.register</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/sparse/index.html">ndarray.sparse</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/utils/index.html">ndarray.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/recordio/index.html">mxnet.recordio</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/symbol/index.html">mxnet.symbol</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/symbol.html">symbol</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/contrib/index.html">symbol.contrib</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/image/index.html">symbol.image</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/linalg/index.html">symbol.linalg</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/op/index.html">symbol.op</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/random/index.html">symbol.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/register/index.html">symbol.register</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/sparse/index.html">symbol.sparse</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/visualization/index.html">mxnet.visualization</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../device/index.html">mxnet.device</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../engine/index.html">mxnet.engine</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../executor/index.html">mxnet.executor</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore_server/index.html">mxnet.kvstore_server</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../profiler/index.html">mxnet.profiler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../rtc/index.html">mxnet.rtc</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../runtime/index.html">mxnet.runtime</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../runtime/generated/mxnet.runtime.Feature.html">mxnet.runtime.Feature</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../runtime/generated/mxnet.runtime.Features.html">mxnet.runtime.Features</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../runtime/generated/mxnet.runtime.feature_list.html">mxnet.runtime.feature_list</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../test_utils/index.html">mxnet.test_utils</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../util/index.html">mxnet.util</a></li> |
| </ul> |
| </li> |
| </ul> |
| |
| </nav> |
| |
| </div> |
| |
| </header> |
| <main class="mdl-layout__content" tabIndex="0"> |
| <header class="mdl-layout__drawer"> |
| |
| <div class="globaltoc"> |
| <span class="mdl-layout-title toc">Table Of Contents</span> |
| |
| |
| |
| <nav class="mdl-navigation"> |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index.html">Python Tutorials</a><ul> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/getting-started/index.html">Getting Started</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/index.html">Crash Course</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/0-introduction.html">Introduction</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/1-nparray.html">Step 1: Manipulate data with NP on MXNet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/2-create-nn.html">Step 2: Create a neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/3-autograd.html">Step 3: Automatic differentiation with autograd</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/4-components.html">Step 4: Necessary components that are not in the network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html">Step 5: <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#Using-your-own-data-with-custom-Datasets">Using your own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#New-in-MXNet-2.0:-faster-C++-backend-dataloaders">New in MXNet 2.0: faster C++ backend dataloaders</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/6-train-nn.html">Step 6: Train a Neural Network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/7-use-gpus.html">Step 7: Load and Run a NN using GPU</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/index.html">Moving to MXNet from Other Frameworks</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/pytorch.html">PyTorch vs Apache MXNet</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_from_experiment_to_deployment.html">Gluon: from experiment to deployment</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_migration_guide.html">Gluon2.0: Migration Guide</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/logistic_regression_explained.html">Logistic regression explained</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/image/mnist.html">MNIST</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/packages/index.html">Packages</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/autograd/index.html">Automatic Differentiation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/gluon/index.html">Gluon</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/index.html">Blocks</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/custom-layer.html">Custom Layers</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/hybridize.html">Hybridize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/init.html">Initialization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/naming.html">Parameter and Block Naming</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/nn.html">Layers and Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/parameters.html">Parameter Management</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/activations/activations.html">Activation Blocks</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/data/index.html">Data Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html">Image Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html">Gluon <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-custom-Datasets">Using own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Appendix:-Upgrading-from-Module-DataIter-to-Gluon-DataLoader">Appendix: Upgrading from Module <code class="docutils literal notranslate"><span class="pre">DataIter</span></code> to Gluon <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/image/index.html">Image Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/info_gan.html">Image similarity search with InfoGAN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/mnist.html">Handwritten Digit Recognition</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/index.html">Losses</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/custom-loss.html">Custom Loss Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/kl_divergence.html">Kullback-Leibler (KL) Divergence</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/loss.html">Loss functions</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/text/index.html">Text Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/gnmt.html">Google Neural Machine Translation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/transformer.html">Machine Translation with Transformer</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/training/index.html">Training</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/fit_api_tutorial.html">MXNet Gluon Fit API</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/trainer.html">Trainer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/index.html">Learning Rates</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_finder.html">Learning Rate Finder</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules.html">Learning Rate Schedules</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules_advanced.html">Advanced Learning Rate Schedules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/normalization/index.html">Normalization Blocks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/kvstore/index.html">KVStore</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/kvstore/kvstore.html">Distributed Key-Value Store</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/legacy/index.html">Legacy</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/index.html">NDArray</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/01-ndarray-intro.html">An Intro: Manipulate Data the MXNet Way with NDArray</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/02-ndarray-operations.html">NDArray Operations</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/03-ndarray-contexts.html">NDArray Contexts</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/gotchas_numpy_in_mxnet.html">Gotchas using NumPy in Apache MXNet</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/index.html">Tutorials</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/csr.html">CSRNDArray - NDArray in Compressed Sparse Row Storage Format</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/row_sparse.html">RowSparseNDArray - NDArray for Sparse Gradient Updates</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/np/index.html">What is NP on MXNet</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/np/cheat-sheet.html">The NP on MXNet cheat sheet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/np/np-vs-numpy.html">Differences between NP on MXNet and NumPy</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/onnx/index.html">ONNX</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/fine_tuning_gluon.html">Fine-tuning an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/inference_on_onnx_model.html">Running inference on MXNet/Gluon from an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html">Export ONNX Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/optimizer/index.html">Optimizers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/viz/index.html">Visualization</a><ul> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/visualize_graph">Visualize networks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/performance/index.html">Performance</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/compression/index.html">Compression</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/compression/int8.html">Deploy with int-8</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/float16">Float16</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/gradient_compression">Gradient Compression</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html">GluonCV with Quantized Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/backend/index.html">Accelerated Backend Tools</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/index.html">oneDNN</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_readme.html">Install MXNet with oneDNN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_quantization.html">oneDNN Quantization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_quantization_inc.html">Improving accuracy with Intel® Neural Compressor</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tvm.html">Use TVM</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/profiler.html">Profiling MXNet Models</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/amp.html">Using AMP: Automatic Mixed Precision</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/deploy/index.html">Deployment</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/export/index.html">Export</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/export/onnx.html">Exporting to ONNX format</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/export_network.html">Export Gluon CV Models</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Save / Load Parameters</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/inference/index.html">Inference</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/cpp.html">Deploy into C++</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/image_classification_jetson.html">Image Classication using pretrained ResNet-50 model on Jetson module</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/index.html">Run on AWS</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_ec2.html">Run on an EC2 Instance</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_sagemaker.html">Run on Amazon SageMaker</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/cloud.html">MXNet on the Cloud</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/extend/index.html">Extend</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/extend/customop.html">Custom Numpy Operators</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/new_op">New Operator Creation</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/add_op_in_backend">New Operator in MXNet Backend</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/using_rtc">Using RTC for CUDA kernels</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1 current"><a class="reference internal" href="../../index.html">Python API</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="../../np/index.html">mxnet.np</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../np/arrays.html">Array objects</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/arrays.ndarray.html">The N-dimensional array (<code class="xref py py-class docutils literal notranslate"><span class="pre">ndarray</span></code>)</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/arrays.indexing.html">Indexing</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../np/routines.html">Routines</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.array-creation.html">Array creation routines</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.eye.html">mxnet.np.eye</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.empty.html">mxnet.np.empty</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.full.html">mxnet.np.full</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.identity.html">mxnet.np.identity</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ones.html">mxnet.np.ones</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ones_like.html">mxnet.np.ones_like</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.zeros.html">mxnet.np.zeros</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.zeros_like.html">mxnet.np.zeros_like</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.array.html">mxnet.np.array</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.copy.html">mxnet.np.copy</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arange.html">mxnet.np.arange</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linspace.html">mxnet.np.linspace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.logspace.html">mxnet.np.logspace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.meshgrid.html">mxnet.np.meshgrid</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tril.html">mxnet.np.tril</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.array-manipulation.html">Array manipulation routines</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.reshape.html">mxnet.np.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ravel.html">mxnet.np.ravel</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ndarray.flatten.html">mxnet.np.ndarray.flatten</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.swapaxes.html">mxnet.np.swapaxes</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ndarray.T.html">mxnet.np.ndarray.T</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.transpose.html">mxnet.np.transpose</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.moveaxis.html">mxnet.np.moveaxis</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.rollaxis.html">mxnet.np.rollaxis</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.expand_dims.html">mxnet.np.expand_dims</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.squeeze.html">mxnet.np.squeeze</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.broadcast_to.html">mxnet.np.broadcast_to</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.broadcast_arrays.html">mxnet.np.broadcast_arrays</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.atleast_1d.html">mxnet.np.atleast_1d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.atleast_2d.html">mxnet.np.atleast_2d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.atleast_3d.html">mxnet.np.atleast_3d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.concatenate.html">mxnet.np.concatenate</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.stack.html">mxnet.np.stack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.dstack.html">mxnet.np.dstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.vstack.html">mxnet.np.vstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.column_stack.html">mxnet.np.column_stack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.hstack.html">mxnet.np.hstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.split.html">mxnet.np.split</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.hsplit.html">mxnet.np.hsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.vsplit.html">mxnet.np.vsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.array_split.html">mxnet.np.array_split</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.dsplit.html">mxnet.np.dsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tile.html">mxnet.np.tile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.repeat.html">mxnet.np.repeat</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.unique.html">mxnet.np.unique</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.delete.html">mxnet.np.delete</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.insert.html">mxnet.np.insert</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.append.html">mxnet.np.append</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.resize.html">mxnet.np.resize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.trim_zeros.html">mxnet.np.trim_zeros</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.reshape.html">mxnet.np.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.flip.html">mxnet.np.flip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.roll.html">mxnet.np.roll</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.rot90.html">mxnet.np.rot90</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fliplr.html">mxnet.np.fliplr</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.flipud.html">mxnet.np.flipud</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.io.html">Input and output</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.genfromtxt.html">mxnet.np.genfromtxt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ndarray.tolist.html">mxnet.np.ndarray.tolist</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.set_printoptions.html">mxnet.np.set_printoptions</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.linalg.html">Linear algebra (<code class="xref py py-mod docutils literal notranslate"><span class="pre">numpy.linalg</span></code>)</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.dot.html">mxnet.np.dot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.vdot.html">mxnet.np.vdot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.inner.html">mxnet.np.inner</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.outer.html">mxnet.np.outer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tensordot.html">mxnet.np.tensordot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.einsum.html">mxnet.np.einsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.multi_dot.html">mxnet.np.linalg.multi_dot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.matmul.html">mxnet.np.matmul</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.matrix_power.html">mxnet.np.linalg.matrix_power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.kron.html">mxnet.np.kron</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.svd.html">mxnet.np.linalg.svd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.cholesky.html">mxnet.np.linalg.cholesky</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.qr.html">mxnet.np.linalg.qr</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.eig.html">mxnet.np.linalg.eig</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.eigh.html">mxnet.np.linalg.eigh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.eigvals.html">mxnet.np.linalg.eigvals</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.eigvalsh.html">mxnet.np.linalg.eigvalsh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.norm.html">mxnet.np.linalg.norm</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.trace.html">mxnet.np.trace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.cond.html">mxnet.np.linalg.cond</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.det.html">mxnet.np.linalg.det</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.matrix_rank.html">mxnet.np.linalg.matrix_rank</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.slogdet.html">mxnet.np.linalg.slogdet</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.solve.html">mxnet.np.linalg.solve</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.tensorsolve.html">mxnet.np.linalg.tensorsolve</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.lstsq.html">mxnet.np.linalg.lstsq</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.inv.html">mxnet.np.linalg.inv</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.pinv.html">mxnet.np.linalg.pinv</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.linalg.tensorinv.html">mxnet.np.linalg.tensorinv</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.math.html">Mathematical functions</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sin.html">mxnet.np.sin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cos.html">mxnet.np.cos</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tan.html">mxnet.np.tan</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arcsin.html">mxnet.np.arcsin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arccos.html">mxnet.np.arccos</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arctan.html">mxnet.np.arctan</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.degrees.html">mxnet.np.degrees</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.radians.html">mxnet.np.radians</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.hypot.html">mxnet.np.hypot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arctan2.html">mxnet.np.arctan2</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.deg2rad.html">mxnet.np.deg2rad</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.rad2deg.html">mxnet.np.rad2deg</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.unwrap.html">mxnet.np.unwrap</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sinh.html">mxnet.np.sinh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cosh.html">mxnet.np.cosh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.tanh.html">mxnet.np.tanh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arcsinh.html">mxnet.np.arcsinh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arccosh.html">mxnet.np.arccosh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.arctanh.html">mxnet.np.arctanh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.rint.html">mxnet.np.rint</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fix.html">mxnet.np.fix</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.floor.html">mxnet.np.floor</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ceil.html">mxnet.np.ceil</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.trunc.html">mxnet.np.trunc</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.around.html">mxnet.np.around</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.round_.html">mxnet.np.round_</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sum.html">mxnet.np.sum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.prod.html">mxnet.np.prod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cumsum.html">mxnet.np.cumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanprod.html">mxnet.np.nanprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nansum.html">mxnet.np.nansum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cumprod.html">mxnet.np.cumprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nancumprod.html">mxnet.np.nancumprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nancumsum.html">mxnet.np.nancumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.diff.html">mxnet.np.diff</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ediff1d.html">mxnet.np.ediff1d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cross.html">mxnet.np.cross</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.trapz.html">mxnet.np.trapz</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.exp.html">mxnet.np.exp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.expm1.html">mxnet.np.expm1</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.log.html">mxnet.np.log</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.log10.html">mxnet.np.log10</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.log2.html">mxnet.np.log2</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.log1p.html">mxnet.np.log1p</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.logaddexp.html">mxnet.np.logaddexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.i0.html">mxnet.np.i0</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ldexp.html">mxnet.np.ldexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.signbit.html">mxnet.np.signbit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.copysign.html">mxnet.np.copysign</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.frexp.html">mxnet.np.frexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.spacing.html">mxnet.np.spacing</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.lcm.html">mxnet.np.lcm</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.gcd.html">mxnet.np.gcd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.add.html">mxnet.np.add</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.reciprocal.html">mxnet.np.reciprocal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.negative.html">mxnet.np.negative</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.divide.html">mxnet.np.divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.power.html">mxnet.np.power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.subtract.html">mxnet.np.subtract</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.mod.html">mxnet.np.mod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.multiply.html">mxnet.np.multiply</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.true_divide.html">mxnet.np.true_divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.remainder.html">mxnet.np.remainder</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.positive.html">mxnet.np.positive</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.float_power.html">mxnet.np.float_power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fmod.html">mxnet.np.fmod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.modf.html">mxnet.np.modf</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.divmod.html">mxnet.np.divmod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.floor_divide.html">mxnet.np.floor_divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.clip.html">mxnet.np.clip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sqrt.html">mxnet.np.sqrt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cbrt.html">mxnet.np.cbrt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.square.html">mxnet.np.square</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.absolute.html">mxnet.np.absolute</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sign.html">mxnet.np.sign</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.maximum.html">mxnet.np.maximum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.minimum.html">mxnet.np.minimum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fabs.html">mxnet.np.fabs</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.heaviside.html">mxnet.np.heaviside</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fmax.html">mxnet.np.fmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.fmin.html">mxnet.np.fmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nan_to_num.html">mxnet.np.nan_to_num</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.interp.html">mxnet.np.interp</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/random/index.html">np.random</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.choice.html">mxnet.np.random.choice</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.shuffle.html">mxnet.np.random.shuffle</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.normal.html">mxnet.np.random.normal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.uniform.html">mxnet.np.random.uniform</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.rand.html">mxnet.np.random.rand</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.randint.html">mxnet.np.random.randint</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.beta.html">mxnet.np.random.beta</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.chisquare.html">mxnet.np.random.chisquare</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.exponential.html">mxnet.np.random.exponential</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.f.html">mxnet.np.random.f</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.gamma.html">mxnet.np.random.gamma</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.gumbel.html">mxnet.np.random.gumbel</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.laplace.html">mxnet.np.random.laplace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.logistic.html">mxnet.np.random.logistic</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.lognormal.html">mxnet.np.random.lognormal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.multinomial.html">mxnet.np.random.multinomial</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.multivariate_normal.html">mxnet.np.random.multivariate_normal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.pareto.html">mxnet.np.random.pareto</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.power.html">mxnet.np.random.power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.rayleigh.html">mxnet.np.random.rayleigh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/random/generated/mxnet.np.random.weibull.html">mxnet.np.random.weibull</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.sort.html">Sorting, searching, and counting</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ndarray.sort.html">mxnet.np.ndarray.sort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.sort.html">mxnet.np.sort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.lexsort.html">mxnet.np.lexsort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argsort.html">mxnet.np.argsort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.msort.html">mxnet.np.msort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.partition.html">mxnet.np.partition</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argpartition.html">mxnet.np.argpartition</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argmax.html">mxnet.np.argmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argmin.html">mxnet.np.argmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanargmax.html">mxnet.np.nanargmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanargmin.html">mxnet.np.nanargmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.argwhere.html">mxnet.np.argwhere</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nonzero.html">mxnet.np.nonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.flatnonzero.html">mxnet.np.flatnonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.where.html">mxnet.np.where</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.searchsorted.html">mxnet.np.searchsorted</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.extract.html">mxnet.np.extract</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.count_nonzero.html">mxnet.np.count_nonzero</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../np/routines.statistics.html">Statistics</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.min.html">mxnet.np.min</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.max.html">mxnet.np.max</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.amin.html">mxnet.np.amin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.amax.html">mxnet.np.amax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanmin.html">mxnet.np.nanmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanmax.html">mxnet.np.nanmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.ptp.html">mxnet.np.ptp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.percentile.html">mxnet.np.percentile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanpercentile.html">mxnet.np.nanpercentile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.quantile.html">mxnet.np.quantile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanquantile.html">mxnet.np.nanquantile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.mean.html">mxnet.np.mean</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.std.html">mxnet.np.std</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.var.html">mxnet.np.var</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.median.html">mxnet.np.median</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.average.html">mxnet.np.average</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanmedian.html">mxnet.np.nanmedian</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanstd.html">mxnet.np.nanstd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.nanvar.html">mxnet.np.nanvar</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.corrcoef.html">mxnet.np.corrcoef</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.correlate.html">mxnet.np.correlate</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.cov.html">mxnet.np.cov</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.histogram.html">mxnet.np.histogram</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.histogram2d.html">mxnet.np.histogram2d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.histogramdd.html">mxnet.np.histogramdd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.bincount.html">mxnet.np.bincount</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.histogram_bin_edges.html">mxnet.np.histogram_bin_edges</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../np/generated/mxnet.np.digitize.html">mxnet.np.digitize</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../npx/index.html">NPX: NumPy Neural Network Extension</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.set_np.html">mxnet.npx.set_np</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.reset_np.html">mxnet.npx.reset_np</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.cpu.html">mxnet.npx.cpu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.cpu_pinned.html">mxnet.npx.cpu_pinned</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.gpu.html">mxnet.npx.gpu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.gpu_memory_info.html">mxnet.npx.gpu_memory_info</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.current_device.html">mxnet.npx.current_device</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.num_gpus.html">mxnet.npx.num_gpus</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.activation.html">mxnet.npx.activation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.batch_norm.html">mxnet.npx.batch_norm</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.convolution.html">mxnet.npx.convolution</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.dropout.html">mxnet.npx.dropout</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.embedding.html">mxnet.npx.embedding</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.fully_connected.html">mxnet.npx.fully_connected</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.layer_norm.html">mxnet.npx.layer_norm</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.pooling.html">mxnet.npx.pooling</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.rnn.html">mxnet.npx.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.leaky_relu.html">mxnet.npx.leaky_relu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.multibox_detection.html">mxnet.npx.multibox_detection</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.multibox_prior.html">mxnet.npx.multibox_prior</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.multibox_target.html">mxnet.npx.multibox_target</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.roi_pooling.html">mxnet.npx.roi_pooling</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.sigmoid.html">mxnet.npx.sigmoid</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.relu.html">mxnet.npx.relu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.smooth_l1.html">mxnet.npx.smooth_l1</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.softmax.html">mxnet.npx.softmax</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.log_softmax.html">mxnet.npx.log_softmax</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.topk.html">mxnet.npx.topk</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.waitall.html">mxnet.npx.waitall</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.load.html">mxnet.npx.load</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.save.html">mxnet.npx.save</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.one_hot.html">mxnet.npx.one_hot</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.pick.html">mxnet.npx.pick</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.reshape_like.html">mxnet.npx.reshape_like</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.batch_flatten.html">mxnet.npx.batch_flatten</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.batch_dot.html">mxnet.npx.batch_dot</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.gamma.html">mxnet.npx.gamma</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../npx/generated/mxnet.npx.sequence_mask.html">mxnet.npx.sequence_mask</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2 current"><a class="reference internal" href="../index.html">mxnet.gluon</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="../block.html">gluon.Block</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../hybrid_block.html">gluon.HybridBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../symbol_block.html">gluon.SymbolBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../constant.html">gluon.Constant</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../parameter.html">gluon.Parameter</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../trainer.html">gluon.Trainer</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../contrib/index.html">gluon.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../data/index.html">gluon.data</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../data/vision/index.html">data.vision</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../data/vision/datasets/index.html">vision.datasets</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../data/vision/transforms/index.html">vision.transforms</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="#">gluon.loss</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../metric/index.html">gluon.metric</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../model_zoo/index.html">gluon.model_zoo.vision</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../nn/index.html">gluon.nn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../rnn/index.html">gluon.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../utils/index.html">gluon.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../autograd/index.html">mxnet.autograd</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../initializer/index.html">mxnet.initializer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../optimizer/index.html">mxnet.optimizer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../lr_scheduler/index.html">mxnet.lr_scheduler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html">KVStore: Communication for Distributed Training</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html#horovod">Horovod</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.Horovod.html">mxnet.kvstore.Horovod</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html#byteps">BytePS</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.BytePS.html">mxnet.kvstore.BytePS</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore/index.html#kvstore-interface">KVStore Interface</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.KVStore.html">mxnet.kvstore.KVStore</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.KVStoreBase.html">mxnet.kvstore.KVStoreBase</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../kvstore/generated/mxnet.kvstore.KVStoreServer.html">mxnet.kvstore.KVStoreServer</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../contrib/index.html">mxnet.contrib</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/io/index.html">contrib.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/ndarray/index.html">contrib.ndarray</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/onnx/index.html">contrib.onnx</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/quantization/index.html">contrib.quantization</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/symbol/index.html">contrib.symbol</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/tensorboard/index.html">contrib.tensorboard</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/tensorrt/index.html">contrib.tensorrt</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../contrib/text/index.html">contrib.text</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../legacy/index.html">Legacy</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/callback/index.html">mxnet.callback</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/image/index.html">mxnet.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/io/index.html">mxnet.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/ndarray/index.html">mxnet.ndarray</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/ndarray.html">ndarray</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/contrib/index.html">ndarray.contrib</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/image/index.html">ndarray.image</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/linalg/index.html">ndarray.linalg</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/op/index.html">ndarray.op</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/random/index.html">ndarray.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/register/index.html">ndarray.register</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/sparse/index.html">ndarray.sparse</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/ndarray/utils/index.html">ndarray.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/recordio/index.html">mxnet.recordio</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/symbol/index.html">mxnet.symbol</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/symbol.html">symbol</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/contrib/index.html">symbol.contrib</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/image/index.html">symbol.image</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/linalg/index.html">symbol.linalg</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/op/index.html">symbol.op</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/random/index.html">symbol.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/register/index.html">symbol.register</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../legacy/symbol/sparse/index.html">symbol.sparse</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../legacy/visualization/index.html">mxnet.visualization</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../device/index.html">mxnet.device</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../engine/index.html">mxnet.engine</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../executor/index.html">mxnet.executor</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../kvstore_server/index.html">mxnet.kvstore_server</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../profiler/index.html">mxnet.profiler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../rtc/index.html">mxnet.rtc</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../runtime/index.html">mxnet.runtime</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../runtime/generated/mxnet.runtime.Feature.html">mxnet.runtime.Feature</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../runtime/generated/mxnet.runtime.Features.html">mxnet.runtime.Features</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../runtime/generated/mxnet.runtime.feature_list.html">mxnet.runtime.feature_list</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../test_utils/index.html">mxnet.test_utils</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../util/index.html">mxnet.util</a></li> |
| </ul> |
| </li> |
| </ul> |
| |
| </nav> |
| |
| </div> |
| |
| </header> |
| |
| <div class="document"> |
| <div class="page-content" role="main"> |
| |
| <div class="section" id="gluon-loss"> |
| <h1>gluon.loss<a class="headerlink" href="#gluon-loss" title="Permalink to this headline">¶</a></h1> |
| <p>Gluon provides pre-defined loss functions in the <a class="reference internal" href="#module-mxnet.gluon.loss" title="mxnet.gluon.loss"><code class="xref py py-mod docutils literal notranslate"><span class="pre">mxnet.gluon.loss</span></code></a> |
| module.</p> |
| <span class="target" id="module-mxnet.gluon.loss"></span><p>losses for training neural networks</p> |
| <p><strong>Classes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">Loss</span></code></a>(weight, batch_axis, **kwargs)</p></td> |
| <td><p>Base class for loss.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss" title="mxnet.gluon.loss.L2Loss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">L2Loss</span></code></a>([weight, batch_axis])</p></td> |
| <td><p>Calculates the mean squared error between <cite>label</cite> and <cite>pred</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss" title="mxnet.gluon.loss.L1Loss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">L1Loss</span></code></a>([weight, batch_axis])</p></td> |
| <td><p>Calculates the mean absolute error between <cite>label</cite> and <cite>pred</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SigmoidBinaryCrossEntropyLoss</span></code></a>([…])</p></td> |
| <td><p>The cross-entropy loss for binary classification.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBCELoss" title="mxnet.gluon.loss.SigmoidBCELoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SigmoidBCELoss</span></code></a></p></td> |
| <td><p>The cross-entropy loss for binary classification.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SoftmaxCrossEntropyLoss</span></code></a>([axis, …])</p></td> |
| <td><p>Computes the softmax cross entropy loss.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCELoss" title="mxnet.gluon.loss.SoftmaxCELoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SoftmaxCELoss</span></code></a></p></td> |
| <td><p>Computes the softmax cross entropy loss.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss" title="mxnet.gluon.loss.KLDivLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">KLDivLoss</span></code></a>([from_logits, axis, weight, …])</p></td> |
| <td><p>The Kullback-Leibler divergence loss.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss" title="mxnet.gluon.loss.CTCLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">CTCLoss</span></code></a>([layout, label_layout, weight])</p></td> |
| <td><p>Connectionist Temporal Classification Loss.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss" title="mxnet.gluon.loss.HuberLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">HuberLoss</span></code></a>([rho, weight, batch_axis])</p></td> |
| <td><p>Calculates smoothed L1 loss that is equal to L1 loss if absolute error exceeds rho but is equal to L2 loss otherwise.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss" title="mxnet.gluon.loss.HingeLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">HingeLoss</span></code></a>([margin, weight, batch_axis])</p></td> |
| <td><p>Calculates the hinge loss function often used in SVMs:</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss" title="mxnet.gluon.loss.SquaredHingeLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SquaredHingeLoss</span></code></a>([margin, weight, batch_axis])</p></td> |
| <td><p>Calculates the soft-margin loss function used in SVMs:</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss" title="mxnet.gluon.loss.LogisticLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">LogisticLoss</span></code></a>([weight, batch_axis, label_format])</p></td> |
| <td><p>Calculates the logistic loss (for binary losses only):</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss" title="mxnet.gluon.loss.TripletLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">TripletLoss</span></code></a>([margin, weight, batch_axis])</p></td> |
| <td><p>Calculates triplet loss given three input tensors and a positive margin.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss" title="mxnet.gluon.loss.PoissonNLLLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">PoissonNLLLoss</span></code></a>([weight, from_logits, …])</p></td> |
| <td><p>For a target (Random Variable) in a Poisson distribution, the function calculates the Negative Log likelihood loss.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss" title="mxnet.gluon.loss.CosineEmbeddingLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">CosineEmbeddingLoss</span></code></a>([weight, batch_axis, margin])</p></td> |
| <td><p>For a target label 1 or -1, vectors input1 and input2, the function computes the cosine distance between the vectors.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss" title="mxnet.gluon.loss.SDMLLoss"><code class="xref py py-obj docutils literal notranslate"><span class="pre">SDMLLoss</span></code></a>([smoothing_parameter, weight, …])</p></td> |
| <td><p>Calculates Batchwise Smoothed Deep Metric Learning (SDML) Loss given two input tensors and a smoothing weight SDM Loss learns similarity between paired samples by using unpaired samples in the minibatch as potential negative examples.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.Loss"> |
| <em class="property">class </em><code class="sig-name descname">Loss</code><span class="sig-paren">(</span><em class="sig-param">weight</em>, <em class="sig-param">batch_axis</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#Loss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.Loss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.block.HybridBlock</span></code></p> |
| <p>Base class for loss.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.apply" title="mxnet.gluon.loss.Loss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.collect_params" title="mxnet.gluon.loss.Loss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.export" title="mxnet.gluon.loss.Loss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.forward" title="mxnet.gluon.loss.Loss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(x, *args)</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.hybridize" title="mxnet.gluon.loss.Loss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.infer_shape" title="mxnet.gluon.loss.Loss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.infer_type" title="mxnet.gluon.loss.Loss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.initialize" title="mxnet.gluon.loss.Loss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.load" title="mxnet.gluon.loss.Loss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.load_dict" title="mxnet.gluon.loss.Loss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.load_parameters" title="mxnet.gluon.loss.Loss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.optimize_for" title="mxnet.gluon.loss.Loss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.register_forward_hook" title="mxnet.gluon.loss.Loss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.register_forward_pre_hook" title="mxnet.gluon.loss.Loss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.register_op_hook" title="mxnet.gluon.loss.Loss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.reset_ctx" title="mxnet.gluon.loss.Loss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.reset_device" title="mxnet.gluon.loss.Loss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.save" title="mxnet.gluon.loss.Loss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.save_parameters" title="mxnet.gluon.loss.Loss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.setattr" title="mxnet.gluon.loss.Loss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.share_parameters" title="mxnet.gluon.loss.Loss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.summary" title="mxnet.gluon.loss.Loss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.zero_grad" title="mxnet.gluon.loss.Loss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.Loss.params" title="mxnet.gluon.loss.Loss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#Loss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.Loss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.Loss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.Loss.forward" title="mxnet.gluon.loss.Loss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.Loss.forward" title="mxnet.gluon.loss.Loss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.Loss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.Loss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.L2Loss"> |
| <em class="property">class </em><code class="sig-name descname">L2Loss</code><span class="sig-paren">(</span><em class="sig-param">weight=1.0</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#L2Loss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.L2Loss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Calculates the mean squared error between <cite>label</cite> and <cite>pred</cite>.</p> |
| <div class="math notranslate nohighlight"> |
| \[L = \frac{1}{2} \sum_i \vert {label}_i - {pred}_i \vert^2.\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.apply" title="mxnet.gluon.loss.L2Loss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.collect_params" title="mxnet.gluon.loss.L2Loss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.export" title="mxnet.gluon.loss.L2Loss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.forward" title="mxnet.gluon.loss.L2Loss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.hybridize" title="mxnet.gluon.loss.L2Loss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.infer_shape" title="mxnet.gluon.loss.L2Loss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.infer_type" title="mxnet.gluon.loss.L2Loss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.initialize" title="mxnet.gluon.loss.L2Loss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.load" title="mxnet.gluon.loss.L2Loss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.load_dict" title="mxnet.gluon.loss.L2Loss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.load_parameters" title="mxnet.gluon.loss.L2Loss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.optimize_for" title="mxnet.gluon.loss.L2Loss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.register_forward_hook" title="mxnet.gluon.loss.L2Loss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.register_forward_pre_hook" title="mxnet.gluon.loss.L2Loss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.register_op_hook" title="mxnet.gluon.loss.L2Loss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.reset_ctx" title="mxnet.gluon.loss.L2Loss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.reset_device" title="mxnet.gluon.loss.L2Loss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.save" title="mxnet.gluon.loss.L2Loss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.save_parameters" title="mxnet.gluon.loss.L2Loss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.setattr" title="mxnet.gluon.loss.L2Loss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.share_parameters" title="mxnet.gluon.loss.L2Loss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.summary" title="mxnet.gluon.loss.L2Loss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.zero_grad" title="mxnet.gluon.loss.L2Loss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L2Loss.params" title="mxnet.gluon.loss.L2Loss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><cite>label</cite> and <cite>pred</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape</p></li> |
| <li><p><strong>label</strong>: target tensor with the same size as pred.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#L2Loss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.L2Loss.forward" title="mxnet.gluon.loss.L2Loss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.L2Loss.forward" title="mxnet.gluon.loss.L2Loss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L2Loss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L2Loss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.L1Loss"> |
| <em class="property">class </em><code class="sig-name descname">L1Loss</code><span class="sig-paren">(</span><em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#L1Loss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.L1Loss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Calculates the mean absolute error between <cite>label</cite> and <cite>pred</cite>.</p> |
| <div class="math notranslate nohighlight"> |
| \[L = \sum_i \vert {label}_i - {pred}_i \vert.\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.apply" title="mxnet.gluon.loss.L1Loss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.collect_params" title="mxnet.gluon.loss.L1Loss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.export" title="mxnet.gluon.loss.L1Loss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.forward" title="mxnet.gluon.loss.L1Loss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.hybridize" title="mxnet.gluon.loss.L1Loss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.infer_shape" title="mxnet.gluon.loss.L1Loss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.infer_type" title="mxnet.gluon.loss.L1Loss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.initialize" title="mxnet.gluon.loss.L1Loss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.load" title="mxnet.gluon.loss.L1Loss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.load_dict" title="mxnet.gluon.loss.L1Loss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.load_parameters" title="mxnet.gluon.loss.L1Loss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.optimize_for" title="mxnet.gluon.loss.L1Loss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.register_forward_hook" title="mxnet.gluon.loss.L1Loss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.register_forward_pre_hook" title="mxnet.gluon.loss.L1Loss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.register_op_hook" title="mxnet.gluon.loss.L1Loss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.reset_ctx" title="mxnet.gluon.loss.L1Loss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.reset_device" title="mxnet.gluon.loss.L1Loss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.save" title="mxnet.gluon.loss.L1Loss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.save_parameters" title="mxnet.gluon.loss.L1Loss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.setattr" title="mxnet.gluon.loss.L1Loss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.share_parameters" title="mxnet.gluon.loss.L1Loss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.summary" title="mxnet.gluon.loss.L1Loss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.zero_grad" title="mxnet.gluon.loss.L1Loss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.L1Loss.params" title="mxnet.gluon.loss.L1Loss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><cite>label</cite> and <cite>pred</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape</p></li> |
| <li><p><strong>label</strong>: target tensor with the same size as pred.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#L1Loss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.L1Loss.forward" title="mxnet.gluon.loss.L1Loss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.L1Loss.forward" title="mxnet.gluon.loss.L1Loss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.L1Loss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.L1Loss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss"> |
| <em class="property">class </em><code class="sig-name descname">SigmoidBinaryCrossEntropyLoss</code><span class="sig-paren">(</span><em class="sig-param">from_sigmoid=False</em>, <em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SigmoidBinaryCrossEntropyLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>The cross-entropy loss for binary classification. (alias: SigmoidBCELoss)</p> |
| <p>BCE loss is useful when training logistic regression. If <cite>from_sigmoid</cite> |
| is False (default), this loss computes:</p> |
| <div class="math notranslate nohighlight"> |
| \[ \begin{align}\begin{aligned}prob = \frac{1}{1 + \exp(-{pred})}\\L = - \sum_i {label}_i * \log({prob}_i) * pos\_weight + |
| (1 - {label}_i) * \log(1 - {prob}_i)\end{aligned}\end{align} \]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.apply" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.collect_params" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.export" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.forward" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight, pos_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.hybridize" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.infer_shape" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.infer_type" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.initialize" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load_dict" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load_parameters" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.optimize_for" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_forward_hook" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_forward_pre_hook" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_op_hook" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.reset_ctx" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.reset_device" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.save" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.save_parameters" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.setattr" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.share_parameters" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.summary" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.zero_grad" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.params" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p>If <cite>from_sigmoid</cite> is True, this loss computes:</p> |
| <div class="math notranslate nohighlight"> |
| \[L = - \sum_i {label}_i * \log({pred}_i) * pos\_weight + |
| (1 - {label}_i) * \log(1 - {pred}_i)\]</div> |
| <p>A tensor <cite>pos_weight > 1</cite> decreases the false negative count, hence increasing |
| the recall. |
| Conversely setting <cite>pos_weight < 1</cite> decreases the false positive count and |
| increases the precision.</p> |
| <p><cite>pred</cite> and <cite>label</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>from_sigmoid</strong> (bool, default is <cite>False</cite>) – Whether the input is from the output of sigmoid. Set this to false will make |
| the loss calculate sigmoid and BCE together, which is more numerically |
| stable through log-sum-exp trick.</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape</p></li> |
| <li><p><strong>label</strong>: target tensor with values in range <cite>[0, 1]</cite>. Must have the |
| same size as <cite>pred</cite>.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| <li><p><strong>pos_weight</strong>: a weighting tensor of positive examples. Must be a vector with length |
| equal to the number of classes.For example, if pred has shape (64, 10), |
| pos_weight should have shape (1, 10).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em>, <em class="sig-param">pos_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SigmoidBinaryCrossEntropyLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.forward" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.forward" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="mxnet.gluon.loss.SigmoidBCELoss"> |
| <code class="sig-name descname">SigmoidBCELoss</code><a class="headerlink" href="#mxnet.gluon.loss.SigmoidBCELoss" title="Permalink to this definition">¶</a></dt> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code>(pred, label[, sample_weight, pos_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <dd><p>alias of <a class="reference internal" href="#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss" title="mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss</span></code></a></p> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss"> |
| <em class="property">class </em><code class="sig-name descname">SoftmaxCrossEntropyLoss</code><span class="sig-paren">(</span><em class="sig-param">axis=-1</em>, <em class="sig-param">sparse_label=True</em>, <em class="sig-param">from_logits=False</em>, <em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SoftmaxCrossEntropyLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Computes the softmax cross entropy loss. (alias: SoftmaxCELoss)</p> |
| <p>If <cite>sparse_label</cite> is <cite>True</cite> (default), label should contain integer |
| category indicators:</p> |
| <div class="math notranslate nohighlight"> |
| \[ \begin{align}\begin{aligned}\DeclareMathOperator{softmax}{softmax}\\p = \softmax({pred})\\L = -\sum_i \log p_{i,{label}_i}\end{aligned}\end{align} \]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.apply" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.collect_params" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.export" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.forward" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.hybridize" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.infer_shape" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.infer_type" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.initialize" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load_dict" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load_parameters" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.optimize_for" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_forward_hook" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_forward_pre_hook" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_op_hook" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.reset_ctx" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.reset_device" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.save" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.save_parameters" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.setattr" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.share_parameters" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.summary" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.zero_grad" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.params" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><cite>label</cite>’s shape should be <cite>pred</cite>’s shape with the <cite>axis</cite> dimension removed. |
| i.e. for <cite>pred</cite> with shape (1,2,3,4) and <cite>axis = 2</cite>, <cite>label</cite>’s shape should |
| be (1,2,4).</p> |
| <p>If <cite>sparse_label</cite> is <cite>False</cite>, <cite>label</cite> should contain probability distribution |
| and <cite>label</cite>’s shape should be the same with <cite>pred</cite>:</p> |
| <div class="math notranslate nohighlight"> |
| \[ \begin{align}\begin{aligned}p = \softmax({pred})\\L = -\sum_i \sum_j {label}_j \log p_{ij}\end{aligned}\end{align} \]</div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>axis</strong> (<em>int</em><em>, </em><em>default -1</em>) – The axis to sum over when computing softmax and entropy.</p></li> |
| <li><p><strong>sparse_label</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether label is an integer array instead of probability distribution.</p></li> |
| <li><p><strong>from_logits</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether input is a log probability (usually from log_softmax) instead |
| of unnormalized numbers.</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: the prediction tensor, where the <cite>batch_axis</cite> dimension |
| ranges over batch size and <cite>axis</cite> dimension ranges over the number |
| of classes.</p></li> |
| <li><p><strong>label</strong>: the truth tensor. When <cite>sparse_label</cite> is True, <cite>label</cite>’s |
| shape should be <cite>pred</cite>’s shape with the <cite>axis</cite> dimension removed. |
| i.e. for <cite>pred</cite> with shape (1,2,3,4) and <cite>axis = 2</cite>, <cite>label</cite>’s shape |
| should be (1,2,4) and values should be integers between 0 and 2. If |
| <cite>sparse_label</cite> is False, <cite>label</cite>’s shape must be the same as <cite>pred</cite> |
| and values should be floats in the range <cite>[0, 1]</cite>.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SoftmaxCrossEntropyLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.forward" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.forward" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SoftmaxCrossEntropyLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="attribute"> |
| <dt id="mxnet.gluon.loss.SoftmaxCELoss"> |
| <code class="sig-name descname">SoftmaxCELoss</code><a class="headerlink" href="#mxnet.gluon.loss.SoftmaxCELoss" title="Permalink to this definition">¶</a></dt> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <dd><p>alias of <a class="reference internal" href="#mxnet.gluon.loss.SoftmaxCrossEntropyLoss" title="mxnet.gluon.loss.SoftmaxCrossEntropyLoss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.SoftmaxCrossEntropyLoss</span></code></a></p> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.KLDivLoss"> |
| <em class="property">class </em><code class="sig-name descname">KLDivLoss</code><span class="sig-paren">(</span><em class="sig-param">from_logits=True</em>, <em class="sig-param">axis=-1</em>, <em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#KLDivLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>The Kullback-Leibler divergence loss.</p> |
| <p>KL divergence measures the distance between contiguous distributions. It |
| can be used to minimize information loss when approximating a distribution. |
| If <cite>from_logits</cite> is True (default), loss is defined as:</p> |
| <div class="math notranslate nohighlight"> |
| \[L = \sum_i {label}_i * \big[\log({label}_i) - {pred}_i\big]\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.apply" title="mxnet.gluon.loss.KLDivLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.collect_params" title="mxnet.gluon.loss.KLDivLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.export" title="mxnet.gluon.loss.KLDivLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.forward" title="mxnet.gluon.loss.KLDivLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.hybridize" title="mxnet.gluon.loss.KLDivLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.infer_shape" title="mxnet.gluon.loss.KLDivLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.infer_type" title="mxnet.gluon.loss.KLDivLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.initialize" title="mxnet.gluon.loss.KLDivLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.load" title="mxnet.gluon.loss.KLDivLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.load_dict" title="mxnet.gluon.loss.KLDivLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.load_parameters" title="mxnet.gluon.loss.KLDivLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.optimize_for" title="mxnet.gluon.loss.KLDivLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.register_forward_hook" title="mxnet.gluon.loss.KLDivLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.register_forward_pre_hook" title="mxnet.gluon.loss.KLDivLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.register_op_hook" title="mxnet.gluon.loss.KLDivLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.reset_ctx" title="mxnet.gluon.loss.KLDivLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.reset_device" title="mxnet.gluon.loss.KLDivLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.save" title="mxnet.gluon.loss.KLDivLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.save_parameters" title="mxnet.gluon.loss.KLDivLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.setattr" title="mxnet.gluon.loss.KLDivLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.share_parameters" title="mxnet.gluon.loss.KLDivLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.summary" title="mxnet.gluon.loss.KLDivLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.zero_grad" title="mxnet.gluon.loss.KLDivLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.params" title="mxnet.gluon.loss.KLDivLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p>If <cite>from_logits</cite> is False, loss is defined as:</p> |
| <div class="math notranslate nohighlight"> |
| \[ \begin{align}\begin{aligned}\DeclareMathOperator{softmax}{softmax}\\prob = \softmax({pred})\\L = \sum_i {label}_i * \big[\log({label}_i) - \log({prob}_i)\big]\end{aligned}\end{align} \]</div> |
| <p><cite>label</cite> and <cite>pred</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>from_logits</strong> (bool, default is <cite>True</cite>) – Whether the input is log probability (usually from log_softmax) instead |
| of unnormalized numbers.</p></li> |
| <li><p><strong>axis</strong> (<em>int</em><em>, </em><em>default -1</em>) – The dimension along with to compute softmax. Only used when <cite>from_logits</cite> |
| is False.</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape. If <cite>from_logits</cite> is |
| True, <cite>pred</cite> should be log probabilities. Otherwise, it should be |
| unnormalized predictions, i.e. from a dense layer.</p></li> |
| <li><p><strong>label</strong>: truth tensor with values in range <cite>(0, 1)</cite>. Must have |
| the same size as <cite>pred</cite>.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://en.wikipedia.org/wiki/Kullback-Leibler_divergence">Kullback-Leibler divergence</a></p> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#KLDivLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.forward" title="mxnet.gluon.loss.KLDivLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.KLDivLoss.forward" title="mxnet.gluon.loss.KLDivLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.KLDivLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.KLDivLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.CTCLoss"> |
| <em class="property">class </em><code class="sig-name descname">CTCLoss</code><span class="sig-paren">(</span><em class="sig-param">layout='NTC'</em>, <em class="sig-param">label_layout='NT'</em>, <em class="sig-param">weight=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#CTCLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Connectionist Temporal Classification Loss.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>layout</strong> (<em>str</em><em>, </em><em>default 'NTC'</em>) – Layout of prediction tensor. ‘N’, ‘T’, ‘C’ stands for batch size, |
| sequence length, and alphabet_size respectively.</p></li> |
| <li><p><strong>label_layout</strong> (<em>str</em><em>, </em><em>default 'NT'</em>) – Layout of the labels. ‘N’, ‘T’ stands for batch size, and sequence |
| length respectively.</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.apply" title="mxnet.gluon.loss.CTCLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.collect_params" title="mxnet.gluon.loss.CTCLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.export" title="mxnet.gluon.loss.CTCLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.forward" title="mxnet.gluon.loss.CTCLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, pred_lengths, …])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.hybridize" title="mxnet.gluon.loss.CTCLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.infer_shape" title="mxnet.gluon.loss.CTCLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.infer_type" title="mxnet.gluon.loss.CTCLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.initialize" title="mxnet.gluon.loss.CTCLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.load" title="mxnet.gluon.loss.CTCLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.load_dict" title="mxnet.gluon.loss.CTCLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.load_parameters" title="mxnet.gluon.loss.CTCLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.optimize_for" title="mxnet.gluon.loss.CTCLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.register_forward_hook" title="mxnet.gluon.loss.CTCLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.register_forward_pre_hook" title="mxnet.gluon.loss.CTCLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.register_op_hook" title="mxnet.gluon.loss.CTCLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.reset_ctx" title="mxnet.gluon.loss.CTCLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.reset_device" title="mxnet.gluon.loss.CTCLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.save" title="mxnet.gluon.loss.CTCLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.save_parameters" title="mxnet.gluon.loss.CTCLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.setattr" title="mxnet.gluon.loss.CTCLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.share_parameters" title="mxnet.gluon.loss.CTCLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.summary" title="mxnet.gluon.loss.CTCLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.zero_grad" title="mxnet.gluon.loss.CTCLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.params" title="mxnet.gluon.loss.CTCLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: unnormalized prediction tensor (before softmax). |
| Its shape depends on <cite>layout</cite>. If <cite>layout</cite> is ‘TNC’, pred |
| should have shape <cite>(sequence_length, batch_size, alphabet_size)</cite>. |
| Note that in the last dimension, index <cite>alphabet_size-1</cite> is reserved |
| for internal use as blank label. So <cite>alphabet_size</cite> is one plus the |
| actual alphabet size.</p></li> |
| <li><p><strong>label</strong>: zero-based label tensor. Its shape depends on <cite>label_layout</cite>. |
| If <cite>label_layout</cite> is ‘TN’, <cite>label</cite> should have shape |
| <cite>(label_sequence_length, batch_size)</cite>.</p></li> |
| <li><p><strong>pred_lengths</strong>: optional (default None), used for specifying the |
| length of each entry when different <cite>pred</cite> entries in the same batch |
| have different lengths. <cite>pred_lengths</cite> should have shape <cite>(batch_size,)</cite>.</p></li> |
| <li><p><strong>label_lengths</strong>: optional (default None), used for specifying the |
| length of each entry when different <cite>label</cite> entries in the same batch |
| have different lengths. <cite>label_lengths</cite> should have shape <cite>(batch_size,)</cite>.</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: output loss has shape <cite>(batch_size,)</cite>.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p><strong>Example</strong>: suppose the vocabulary is <cite>[a, b, c]</cite>, and in one batch we |
| have three sequences ‘ba’, ‘cbb’, and ‘abac’. We can index the labels as |
| <cite>{‘a’: 0, ‘b’: 1, ‘c’: 2, blank: 3}</cite>. Then <cite>alphabet_size</cite> should be 4, |
| where label 3 is reserved for internal use by <cite>CTCLoss</cite>. We then need to |
| pad each sequence with <cite>-1</cite> to make a rectangular <cite>label</cite> tensor:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="p">[[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">],</span> |
| <span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">],</span> |
| <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">]]</span> |
| </pre></div> |
| </div> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="http://www.cs.toronto.edu/~graves/icml_2006.pdf">Connectionist Temporal Classification: Labelling Unsegmented |
| Sequence Data with Recurrent Neural Networks</a></p> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">pred_lengths=None</em>, <em class="sig-param">label_lengths=None</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#CTCLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.forward" title="mxnet.gluon.loss.CTCLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.CTCLoss.forward" title="mxnet.gluon.loss.CTCLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CTCLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CTCLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.HuberLoss"> |
| <em class="property">class </em><code class="sig-name descname">HuberLoss</code><span class="sig-paren">(</span><em class="sig-param">rho=1</em>, <em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#HuberLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Calculates smoothed L1 loss that is equal to L1 loss if absolute error |
| exceeds rho but is equal to L2 loss otherwise. Also called SmoothedL1 loss.</p> |
| <div class="math notranslate nohighlight"> |
| \[\begin{split}L = \sum_i \begin{cases} \frac{1}{2 {rho}} ({label}_i - {pred}_i)^2 & |
| \text{ if } |{label}_i - {pred}_i| < {rho} \\ |
| |{label}_i - {pred}_i| - \frac{{rho}}{2} & |
| \text{ otherwise } |
| \end{cases}\end{split}\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.apply" title="mxnet.gluon.loss.HuberLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.collect_params" title="mxnet.gluon.loss.HuberLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.export" title="mxnet.gluon.loss.HuberLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.forward" title="mxnet.gluon.loss.HuberLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.hybridize" title="mxnet.gluon.loss.HuberLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.infer_shape" title="mxnet.gluon.loss.HuberLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.infer_type" title="mxnet.gluon.loss.HuberLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.initialize" title="mxnet.gluon.loss.HuberLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.load" title="mxnet.gluon.loss.HuberLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.load_dict" title="mxnet.gluon.loss.HuberLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.load_parameters" title="mxnet.gluon.loss.HuberLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.optimize_for" title="mxnet.gluon.loss.HuberLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.register_forward_hook" title="mxnet.gluon.loss.HuberLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.register_forward_pre_hook" title="mxnet.gluon.loss.HuberLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.register_op_hook" title="mxnet.gluon.loss.HuberLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.reset_ctx" title="mxnet.gluon.loss.HuberLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.reset_device" title="mxnet.gluon.loss.HuberLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.save" title="mxnet.gluon.loss.HuberLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.save_parameters" title="mxnet.gluon.loss.HuberLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.setattr" title="mxnet.gluon.loss.HuberLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.share_parameters" title="mxnet.gluon.loss.HuberLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.summary" title="mxnet.gluon.loss.HuberLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.zero_grad" title="mxnet.gluon.loss.HuberLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.params" title="mxnet.gluon.loss.HuberLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><cite>label</cite> and <cite>pred</cite> can have arbitrary shape as long as they have the same |
| number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>rho</strong> (<em>float</em><em>, </em><em>default 1</em>) – Threshold for trimmed mean estimator.</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape</p></li> |
| <li><p><strong>label</strong>: target tensor with the same size as pred.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#HuberLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.forward" title="mxnet.gluon.loss.HuberLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.HuberLoss.forward" title="mxnet.gluon.loss.HuberLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HuberLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HuberLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.HingeLoss"> |
| <em class="property">class </em><code class="sig-name descname">HingeLoss</code><span class="sig-paren">(</span><em class="sig-param">margin=1</em>, <em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#HingeLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Calculates the hinge loss function often used in SVMs:</p> |
| <div class="math notranslate nohighlight"> |
| \[L = \sum_i max(0, {margin} - {pred}_i \cdot {label}_i)\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.apply" title="mxnet.gluon.loss.HingeLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.collect_params" title="mxnet.gluon.loss.HingeLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.export" title="mxnet.gluon.loss.HingeLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.forward" title="mxnet.gluon.loss.HingeLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.hybridize" title="mxnet.gluon.loss.HingeLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.infer_shape" title="mxnet.gluon.loss.HingeLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.infer_type" title="mxnet.gluon.loss.HingeLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.initialize" title="mxnet.gluon.loss.HingeLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.load" title="mxnet.gluon.loss.HingeLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.load_dict" title="mxnet.gluon.loss.HingeLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.load_parameters" title="mxnet.gluon.loss.HingeLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.optimize_for" title="mxnet.gluon.loss.HingeLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.register_forward_hook" title="mxnet.gluon.loss.HingeLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.register_forward_pre_hook" title="mxnet.gluon.loss.HingeLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.register_op_hook" title="mxnet.gluon.loss.HingeLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.reset_ctx" title="mxnet.gluon.loss.HingeLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.reset_device" title="mxnet.gluon.loss.HingeLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.save" title="mxnet.gluon.loss.HingeLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.save_parameters" title="mxnet.gluon.loss.HingeLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.setattr" title="mxnet.gluon.loss.HingeLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.share_parameters" title="mxnet.gluon.loss.HingeLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.summary" title="mxnet.gluon.loss.HingeLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.zero_grad" title="mxnet.gluon.loss.HingeLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.params" title="mxnet.gluon.loss.HingeLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p>where <cite>pred</cite> is the classifier prediction and <cite>label</cite> is the target tensor |
| containing values -1 or 1. <cite>label</cite> and <cite>pred</cite> must have the same number of |
| elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>margin</strong> (<em>float</em>) – The margin in hinge loss. Defaults to 1.0</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape.</p></li> |
| <li><p><strong>label</strong>: truth tensor with values -1 or 1. Must have the same size |
| as pred.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#HingeLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.forward" title="mxnet.gluon.loss.HingeLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.HingeLoss.forward" title="mxnet.gluon.loss.HingeLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.HingeLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.HingeLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss"> |
| <em class="property">class </em><code class="sig-name descname">SquaredHingeLoss</code><span class="sig-paren">(</span><em class="sig-param">margin=1</em>, <em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SquaredHingeLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Calculates the soft-margin loss function used in SVMs:</p> |
| <div class="math notranslate nohighlight"> |
| \[L = \sum_i max(0, {margin} - {pred}_i \cdot {label}_i)^2\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.apply" title="mxnet.gluon.loss.SquaredHingeLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.collect_params" title="mxnet.gluon.loss.SquaredHingeLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.export" title="mxnet.gluon.loss.SquaredHingeLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.forward" title="mxnet.gluon.loss.SquaredHingeLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.hybridize" title="mxnet.gluon.loss.SquaredHingeLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.infer_shape" title="mxnet.gluon.loss.SquaredHingeLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.infer_type" title="mxnet.gluon.loss.SquaredHingeLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.initialize" title="mxnet.gluon.loss.SquaredHingeLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.load" title="mxnet.gluon.loss.SquaredHingeLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.load_dict" title="mxnet.gluon.loss.SquaredHingeLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.load_parameters" title="mxnet.gluon.loss.SquaredHingeLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.optimize_for" title="mxnet.gluon.loss.SquaredHingeLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.register_forward_hook" title="mxnet.gluon.loss.SquaredHingeLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.register_forward_pre_hook" title="mxnet.gluon.loss.SquaredHingeLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.register_op_hook" title="mxnet.gluon.loss.SquaredHingeLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.reset_ctx" title="mxnet.gluon.loss.SquaredHingeLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.reset_device" title="mxnet.gluon.loss.SquaredHingeLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.save" title="mxnet.gluon.loss.SquaredHingeLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.save_parameters" title="mxnet.gluon.loss.SquaredHingeLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.setattr" title="mxnet.gluon.loss.SquaredHingeLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.share_parameters" title="mxnet.gluon.loss.SquaredHingeLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.summary" title="mxnet.gluon.loss.SquaredHingeLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.zero_grad" title="mxnet.gluon.loss.SquaredHingeLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.params" title="mxnet.gluon.loss.SquaredHingeLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p>where <cite>pred</cite> is the classifier prediction and <cite>label</cite> is the target tensor |
| containing values -1 or 1. <cite>label</cite> and <cite>pred</cite> can have arbitrary shape as |
| long as they have the same number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>margin</strong> (<em>float</em>) – The margin in hinge loss. Defaults to 1.0</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape</p></li> |
| <li><p><strong>label</strong>: truth tensor with values -1 or 1. Must have the same size |
| as pred.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SquaredHingeLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.forward" title="mxnet.gluon.loss.SquaredHingeLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.SquaredHingeLoss.forward" title="mxnet.gluon.loss.SquaredHingeLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SquaredHingeLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SquaredHingeLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.LogisticLoss"> |
| <em class="property">class </em><code class="sig-name descname">LogisticLoss</code><span class="sig-paren">(</span><em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">label_format='signed'</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#LogisticLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Calculates the logistic loss (for binary losses only):</p> |
| <div class="math notranslate nohighlight"> |
| \[L = \sum_i \log(1 + \exp(- {pred}_i \cdot {label}_i))\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.apply" title="mxnet.gluon.loss.LogisticLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.collect_params" title="mxnet.gluon.loss.LogisticLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.export" title="mxnet.gluon.loss.LogisticLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.forward" title="mxnet.gluon.loss.LogisticLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.hybridize" title="mxnet.gluon.loss.LogisticLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.infer_shape" title="mxnet.gluon.loss.LogisticLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.infer_type" title="mxnet.gluon.loss.LogisticLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.initialize" title="mxnet.gluon.loss.LogisticLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.load" title="mxnet.gluon.loss.LogisticLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.load_dict" title="mxnet.gluon.loss.LogisticLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.load_parameters" title="mxnet.gluon.loss.LogisticLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.optimize_for" title="mxnet.gluon.loss.LogisticLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.register_forward_hook" title="mxnet.gluon.loss.LogisticLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.register_forward_pre_hook" title="mxnet.gluon.loss.LogisticLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.register_op_hook" title="mxnet.gluon.loss.LogisticLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.reset_ctx" title="mxnet.gluon.loss.LogisticLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.reset_device" title="mxnet.gluon.loss.LogisticLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.save" title="mxnet.gluon.loss.LogisticLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.save_parameters" title="mxnet.gluon.loss.LogisticLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.setattr" title="mxnet.gluon.loss.LogisticLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.share_parameters" title="mxnet.gluon.loss.LogisticLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.summary" title="mxnet.gluon.loss.LogisticLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.zero_grad" title="mxnet.gluon.loss.LogisticLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.params" title="mxnet.gluon.loss.LogisticLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p>where <cite>pred</cite> is the classifier prediction and <cite>label</cite> is the target tensor |
| containing values -1 or 1 (0 or 1 if <cite>label_format</cite> is binary). |
| <cite>label</cite> and <cite>pred</cite> can have arbitrary shape as long as they have the same number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| <li><p><strong>label_format</strong> (<em>str</em><em>, </em><em>default 'signed'</em>) – Can be either ‘signed’ or ‘binary’. If the label_format is ‘signed’, all label values should |
| be either -1 or 1. If the label_format is ‘binary’, all label values should be either |
| 0 or 1.</p></li> |
| <li><p><strong>Inputs</strong> – <ul> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape.</p></li> |
| <li><p><strong>label</strong>: truth tensor with values -1/1 (label_format is ‘signed’) |
| or 0/1 (label_format is ‘binary’). Must have the same size as pred.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </p></li> |
| <li><p><strong>Outputs</strong> – <ul> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,). Dimenions other than |
| batch_axis are averaged out.</p></li> |
| </ul> |
| </p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#LogisticLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.forward" title="mxnet.gluon.loss.LogisticLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.LogisticLoss.forward" title="mxnet.gluon.loss.LogisticLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.LogisticLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.LogisticLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.TripletLoss"> |
| <em class="property">class </em><code class="sig-name descname">TripletLoss</code><span class="sig-paren">(</span><em class="sig-param">margin=1</em>, <em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#TripletLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Calculates triplet loss given three input tensors and a positive margin. |
| Triplet loss measures the relative similarity between a positive |
| example, a negative example, and prediction:</p> |
| <div class="math notranslate nohighlight"> |
| \[L = \sum_i \max(\Vert {pos_i}_i - {pred} \Vert_2^2 - |
| \Vert {neg_i}_i - {pred} \Vert_2^2 + {margin}, 0)\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.apply" title="mxnet.gluon.loss.TripletLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.collect_params" title="mxnet.gluon.loss.TripletLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.export" title="mxnet.gluon.loss.TripletLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.forward" title="mxnet.gluon.loss.TripletLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, positive, negative[, …])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.hybridize" title="mxnet.gluon.loss.TripletLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.infer_shape" title="mxnet.gluon.loss.TripletLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.infer_type" title="mxnet.gluon.loss.TripletLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.initialize" title="mxnet.gluon.loss.TripletLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.load" title="mxnet.gluon.loss.TripletLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.load_dict" title="mxnet.gluon.loss.TripletLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.load_parameters" title="mxnet.gluon.loss.TripletLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.optimize_for" title="mxnet.gluon.loss.TripletLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.register_forward_hook" title="mxnet.gluon.loss.TripletLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.register_forward_pre_hook" title="mxnet.gluon.loss.TripletLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.register_op_hook" title="mxnet.gluon.loss.TripletLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.reset_ctx" title="mxnet.gluon.loss.TripletLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.reset_device" title="mxnet.gluon.loss.TripletLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.save" title="mxnet.gluon.loss.TripletLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.save_parameters" title="mxnet.gluon.loss.TripletLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.setattr" title="mxnet.gluon.loss.TripletLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.share_parameters" title="mxnet.gluon.loss.TripletLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.summary" title="mxnet.gluon.loss.TripletLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.zero_grad" title="mxnet.gluon.loss.TripletLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.params" title="mxnet.gluon.loss.TripletLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><cite>positive</cite>, <cite>negative</cite>, and ‘pred’ can have arbitrary shape as long as they |
| have the same number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>margin</strong> (<em>float</em>) – Margin of separation between correct and incorrect pair.</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: prediction tensor with arbitrary shape</p></li> |
| <li><p><strong>positive</strong>: positive example tensor with arbitrary shape. Must have |
| the same size as pred.</p></li> |
| <li><p><strong>negative</strong>: negative example tensor with arbitrary shape Must have |
| the same size as pred.</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">positive</em>, <em class="sig-param">negative</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#TripletLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.forward" title="mxnet.gluon.loss.TripletLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.TripletLoss.forward" title="mxnet.gluon.loss.TripletLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.TripletLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.TripletLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss"> |
| <em class="property">class </em><code class="sig-name descname">PoissonNLLLoss</code><span class="sig-paren">(</span><em class="sig-param">weight=None</em>, <em class="sig-param">from_logits=True</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">compute_full=False</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#PoissonNLLLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>For a target (Random Variable) in a Poisson distribution, the function calculates the Negative |
| Log likelihood loss. |
| PoissonNLLLoss measures the loss accrued from a poisson regression prediction made by the model.</p> |
| <div class="math notranslate nohighlight"> |
| \[L = \text{pred} - \text{target} * \log(\text{pred}) +\log(\text{target!})\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.apply" title="mxnet.gluon.loss.PoissonNLLLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.collect_params" title="mxnet.gluon.loss.PoissonNLLLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.export" title="mxnet.gluon.loss.PoissonNLLLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.forward" title="mxnet.gluon.loss.PoissonNLLLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(pred, target[, sample_weight, epsilon])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.hybridize" title="mxnet.gluon.loss.PoissonNLLLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.infer_shape" title="mxnet.gluon.loss.PoissonNLLLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.infer_type" title="mxnet.gluon.loss.PoissonNLLLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.initialize" title="mxnet.gluon.loss.PoissonNLLLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.load" title="mxnet.gluon.loss.PoissonNLLLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.load_dict" title="mxnet.gluon.loss.PoissonNLLLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.load_parameters" title="mxnet.gluon.loss.PoissonNLLLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.optimize_for" title="mxnet.gluon.loss.PoissonNLLLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.register_forward_hook" title="mxnet.gluon.loss.PoissonNLLLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.register_forward_pre_hook" title="mxnet.gluon.loss.PoissonNLLLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.register_op_hook" title="mxnet.gluon.loss.PoissonNLLLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.reset_ctx" title="mxnet.gluon.loss.PoissonNLLLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.reset_device" title="mxnet.gluon.loss.PoissonNLLLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.save" title="mxnet.gluon.loss.PoissonNLLLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.save_parameters" title="mxnet.gluon.loss.PoissonNLLLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.setattr" title="mxnet.gluon.loss.PoissonNLLLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.share_parameters" title="mxnet.gluon.loss.PoissonNLLLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.summary" title="mxnet.gluon.loss.PoissonNLLLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.zero_grad" title="mxnet.gluon.loss.PoissonNLLLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.params" title="mxnet.gluon.loss.PoissonNLLLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><cite>target</cite>, ‘pred’ can have arbitrary shape as long as they have the same number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>from_logits</strong> (<em>boolean</em><em>, </em><em>default True</em>) – indicating whether log(predicted) value has already been computed. If True, the loss is computed as |
| <span class="math notranslate nohighlight">\(\exp(\text{pred}) - \text{target} * \text{pred}\)</span>, and if False, then loss is computed as |
| <span class="math notranslate nohighlight">\(\text{pred} - \text{target} * \log(\text{pred}+\text{epsilon})\)</span>.The default value</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| <li><p><strong>compute_full</strong> (<em>boolean</em><em>, </em><em>default False</em>) – Indicates whether to add an approximation(Stirling factor) for the Factorial term in the formula for the loss. |
| The Stirling factor is: |
| <span class="math notranslate nohighlight">\(\text{target} * \log(\text{target}) - \text{target} + 0.5 * \log(2 * \pi * \text{target})\)</span></p></li> |
| <li><p><strong>epsilon</strong> (<em>float</em><em>, </em><em>default 1e-08</em>) – This is to avoid calculating log(0) which is not defined.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>pred</strong>: Predicted value</p></li> |
| <li><p><strong>target</strong>: Random variable(count or number) which belongs to a Poisson distribution.</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as pred. For example, if pred has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: Average loss (shape=(1,1)) of the loss tensor with shape (batch_size,).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">pred</em>, <em class="sig-param">target</em>, <em class="sig-param">sample_weight=None</em>, <em class="sig-param">epsilon=1e-08</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#PoissonNLLLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.forward" title="mxnet.gluon.loss.PoissonNLLLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.PoissonNLLLoss.forward" title="mxnet.gluon.loss.PoissonNLLLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.PoissonNLLLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.PoissonNLLLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss"> |
| <em class="property">class </em><code class="sig-name descname">CosineEmbeddingLoss</code><span class="sig-paren">(</span><em class="sig-param">weight=None</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">margin=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#CosineEmbeddingLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>For a target label 1 or -1, vectors input1 and input2, the function computes the cosine distance |
| between the vectors. This can be interpreted as how similar/dissimilar two input vectors are.</p> |
| <div class="math notranslate nohighlight"> |
| \[\begin{split}L = \sum_i \begin{cases} 1 - {cos\_sim({input1}_i, {input2}_i)} & \text{ if } {label}_i = 1\\ |
| {cos\_sim({input1}_i, {input2}_i)} & \text{ if } {label}_i = -1 \end{cases}\\ |
| cos\_sim(input1, input2) = \frac{{input1}_i.{input2}_i}{||{input1}_i||.||{input2}_i||}\end{split}\]</div> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.apply" title="mxnet.gluon.loss.CosineEmbeddingLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.collect_params" title="mxnet.gluon.loss.CosineEmbeddingLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.export" title="mxnet.gluon.loss.CosineEmbeddingLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.forward" title="mxnet.gluon.loss.CosineEmbeddingLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(input1, input2, label[, sample_weight])</p></td> |
| <td><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.hybridize" title="mxnet.gluon.loss.CosineEmbeddingLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.infer_shape" title="mxnet.gluon.loss.CosineEmbeddingLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.infer_type" title="mxnet.gluon.loss.CosineEmbeddingLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.initialize" title="mxnet.gluon.loss.CosineEmbeddingLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.load" title="mxnet.gluon.loss.CosineEmbeddingLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.load_dict" title="mxnet.gluon.loss.CosineEmbeddingLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.load_parameters" title="mxnet.gluon.loss.CosineEmbeddingLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.optimize_for" title="mxnet.gluon.loss.CosineEmbeddingLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.register_forward_hook" title="mxnet.gluon.loss.CosineEmbeddingLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.register_forward_pre_hook" title="mxnet.gluon.loss.CosineEmbeddingLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.register_op_hook" title="mxnet.gluon.loss.CosineEmbeddingLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.reset_ctx" title="mxnet.gluon.loss.CosineEmbeddingLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.reset_device" title="mxnet.gluon.loss.CosineEmbeddingLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.save" title="mxnet.gluon.loss.CosineEmbeddingLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.save_parameters" title="mxnet.gluon.loss.CosineEmbeddingLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.setattr" title="mxnet.gluon.loss.CosineEmbeddingLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.share_parameters" title="mxnet.gluon.loss.CosineEmbeddingLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.summary" title="mxnet.gluon.loss.CosineEmbeddingLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.zero_grad" title="mxnet.gluon.loss.CosineEmbeddingLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.params" title="mxnet.gluon.loss.CosineEmbeddingLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><cite>input1</cite>, <cite>input2</cite> can have arbitrary shape as long as they have the same number of elements.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| <li><p><strong>margin</strong> (<em>float</em>) – Margin of separation between correct and incorrect pair.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="simple"> |
| <dt>Inputs:</dt><dd><ul class="simple"> |
| <li><p><strong>input1</strong>: a tensor with arbitrary shape</p></li> |
| <li><p><strong>input2</strong>: another tensor with same shape as pred to which input1 is |
| compared for similarity and loss calculation</p></li> |
| <li><p><strong>label</strong>: A 1-D tensor indicating for each pair input1 and input2, target label is 1 or -1</p></li> |
| <li><p><strong>sample_weight</strong>: element-wise weighting tensor. Must be broadcastable |
| to the same shape as input1. For example, if input1 has shape (64, 10) |
| and you want to weigh each sample in the batch separately, |
| sample_weight should have shape (64, 1).</p></li> |
| </ul> |
| </dd> |
| <dt>Outputs:</dt><dd><ul class="simple"> |
| <li><p><strong>loss</strong>: The loss tensor with shape (batch_size,).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">input1</em>, <em class="sig-param">input2</em>, <em class="sig-param">label</em>, <em class="sig-param">sample_weight=None</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#CosineEmbeddingLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Overrides to construct symbolic graph for this <cite>Block</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol"><em>Symbol</em></a><em> or </em><a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – The first input tensor.</p></li> |
| <li><p><strong>*args</strong> (<em>list of Symbol</em><em> or </em><em>list of NDArray</em>) – Additional input tensors.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.forward" title="mxnet.gluon.loss.CosineEmbeddingLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.CosineEmbeddingLoss.forward" title="mxnet.gluon.loss.CosineEmbeddingLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.CosineEmbeddingLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.CosineEmbeddingLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="mxnet.gluon.loss.SDMLLoss"> |
| <em class="property">class </em><code class="sig-name descname">SDMLLoss</code><span class="sig-paren">(</span><em class="sig-param">smoothing_parameter=0.3</em>, <em class="sig-param">weight=1.0</em>, <em class="sig-param">batch_axis=0</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SDMLLoss"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#mxnet.gluon.loss.Loss" title="mxnet.gluon.loss.Loss"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.loss.Loss</span></code></a></p> |
| <p>Calculates Batchwise Smoothed Deep Metric Learning (SDML) Loss given two input tensors and a smoothing weight |
| SDM Loss learns similarity between paired samples by using unpaired samples in the minibatch |
| as potential negative examples.</p> |
| <p>The loss is described in greater detail in |
| “Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning.” |
| - by Bonadiman, Daniele, Anjishnu Kumar, and Arpit Mittal. arXiv preprint arXiv:1905.12786 (2019). |
| URL: https://arxiv.org/pdf/1905.12786.pdf</p> |
| <p>According to the authors, this loss formulation achieves comparable or higher accuracy to |
| Triplet Loss but converges much faster. |
| The loss assumes that the items in both tensors in each minibatch |
| are aligned such that x1[0] corresponds to x2[0] and all other datapoints in the minibatch are unrelated. |
| <cite>x1</cite> and <cite>x2</cite> are minibatches of vectors.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>smoothing_parameter</strong> (<em>float</em>) – Probability mass to be distributed over the minibatch. Must be < 1.0.</p></li> |
| <li><p><strong>weight</strong> (<em>float</em><em> or </em><em>None</em>) – Global scalar weight for loss.</p></li> |
| <li><p><strong>batch_axis</strong> (<em>int</em><em>, </em><em>default 0</em>) – The axis that represents mini-batch.</p></li> |
| <li><p><strong>Inputs</strong> – <ul> |
| <li><p><strong>x1</strong>: Minibatch of data points with shape (batch_size, vector_dim)</p></li> |
| <li><p><strong>x2</strong>: Minibatch of data points with shape (batch_size, vector_dim) |
| Each item in x2 is a positive sample for the same index in x1. |
| That is, x1[0] and x2[0] form a positive pair, x1[1] and x2[1] form a positive pair - and so on. |
| All data points in different rows should be decorrelated</p></li> |
| </ul> |
| </p></li> |
| <li><p><strong>Outputs</strong> – <ul> |
| <li><p><strong>loss</strong>: loss tensor with shape (batch_size,).</p></li> |
| </ul> |
| </p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p><strong>Methods</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.apply" title="mxnet.gluon.loss.SDMLLoss.apply"><code class="xref py py-obj docutils literal notranslate"><span class="pre">apply</span></code></a>(fn)</p></td> |
| <td><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.collect_params" title="mxnet.gluon.loss.SDMLLoss.collect_params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">collect_params</span></code></a>([select])</p></td> |
| <td><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> which match some given regular expressions.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.export" title="mxnet.gluon.loss.SDMLLoss.export"><code class="xref py py-obj docutils literal notranslate"><span class="pre">export</span></code></a>(path[, epoch, remove_amp_cast])</p></td> |
| <td><p>Export HybridBlock to json format that can be loaded by <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.forward" title="mxnet.gluon.loss.SDMLLoss.forward"><code class="xref py py-obj docutils literal notranslate"><span class="pre">forward</span></code></a>(x1, x2)</p></td> |
| <td><p>the function computes the kl divergence between the negative distances</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.hybridize" title="mxnet.gluon.loss.SDMLLoss.hybridize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">hybridize</span></code></a>([active, partition_if_dynamic, …])</p></td> |
| <td><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.infer_shape" title="mxnet.gluon.loss.SDMLLoss.infer_shape"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_shape</span></code></a>(*args)</p></td> |
| <td><p>Infers shape of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.infer_type" title="mxnet.gluon.loss.SDMLLoss.infer_type"><code class="xref py py-obj docutils literal notranslate"><span class="pre">infer_type</span></code></a>(*args)</p></td> |
| <td><p>Infers data type of Parameters from inputs.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.initialize" title="mxnet.gluon.loss.SDMLLoss.initialize"><code class="xref py py-obj docutils literal notranslate"><span class="pre">initialize</span></code></a>([init, device, verbose, force_reinit])</p></td> |
| <td><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.load" title="mxnet.gluon.loss.SDMLLoss.load"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load</span></code></a>(prefix)</p></td> |
| <td><p>Load a model saved using the <cite>save</cite> API</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.load_dict" title="mxnet.gluon.loss.SDMLLoss.load_dict"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_dict</span></code></a>(param_dict[, device, …])</p></td> |
| <td><p>Load parameters from dict</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.load_parameters" title="mxnet.gluon.loss.SDMLLoss.load_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">load_parameters</span></code></a>(filename[, device, …])</p></td> |
| <td><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.optimize_for" title="mxnet.gluon.loss.SDMLLoss.optimize_for"><code class="xref py py-obj docutils literal notranslate"><span class="pre">optimize_for</span></code></a>(x, *args[, backend, clear, …])</p></td> |
| <td><p>Partitions the current HybridBlock and optimizes it for a given backend without executing a forward pass.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.register_forward_hook" title="mxnet.gluon.loss.SDMLLoss.register_forward_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward hook on the block.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.register_forward_pre_hook" title="mxnet.gluon.loss.SDMLLoss.register_forward_pre_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_forward_pre_hook</span></code></a>(hook)</p></td> |
| <td><p>Registers a forward pre-hook on the block.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.register_op_hook" title="mxnet.gluon.loss.SDMLLoss.register_op_hook"><code class="xref py py-obj docutils literal notranslate"><span class="pre">register_op_hook</span></code></a>(callback[, monitor_all])</p></td> |
| <td><p>Install op hook for block recursively.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.reset_ctx" title="mxnet.gluon.loss.SDMLLoss.reset_ctx"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_ctx</span></code></a>(ctx)</p></td> |
| <td><p>This function has been deprecated.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.reset_device" title="mxnet.gluon.loss.SDMLLoss.reset_device"><code class="xref py py-obj docutils literal notranslate"><span class="pre">reset_device</span></code></a>(device)</p></td> |
| <td><p>Re-assign all Parameters to other devices.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.save" title="mxnet.gluon.loss.SDMLLoss.save"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save</span></code></a>(prefix)</p></td> |
| <td><p>Save the model architecture and parameters to load again later</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.save_parameters" title="mxnet.gluon.loss.SDMLLoss.save_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">save_parameters</span></code></a>(filename[, deduplicate])</p></td> |
| <td><p>Save parameters to file.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.setattr" title="mxnet.gluon.loss.SDMLLoss.setattr"><code class="xref py py-obj docutils literal notranslate"><span class="pre">setattr</span></code></a>(name, value)</p></td> |
| <td><p>Set an attribute to a new value for all Parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.share_parameters" title="mxnet.gluon.loss.SDMLLoss.share_parameters"><code class="xref py py-obj docutils literal notranslate"><span class="pre">share_parameters</span></code></a>(shared)</p></td> |
| <td><p>Share parameters recursively inside the model.</p></td> |
| </tr> |
| <tr class="row-even"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.summary" title="mxnet.gluon.loss.SDMLLoss.summary"><code class="xref py py-obj docutils literal notranslate"><span class="pre">summary</span></code></a>(*inputs)</p></td> |
| <td><p>Print the summary of the model’s output and parameters.</p></td> |
| </tr> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.zero_grad" title="mxnet.gluon.loss.SDMLLoss.zero_grad"><code class="xref py py-obj docutils literal notranslate"><span class="pre">zero_grad</span></code></a>()</p></td> |
| <td><p>Sets all Parameters’ gradient buffer to 0.</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <p><strong>Attributes</strong></p> |
| <table class="longtable docutils align-default"> |
| <colgroup> |
| <col style="width: 10%" /> |
| <col style="width: 90%" /> |
| </colgroup> |
| <tbody> |
| <tr class="row-odd"><td><p><a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.params" title="mxnet.gluon.loss.SDMLLoss.params"><code class="xref py py-obj docutils literal notranslate"><span class="pre">params</span></code></a></p></td> |
| <td><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its children’s parameters).</p></td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.apply"> |
| <code class="sig-name descname">apply</code><span class="sig-paren">(</span><em class="sig-param">fn</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.apply" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Applies <code class="docutils literal notranslate"><span class="pre">fn</span></code> recursively to every child block as well as self.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>fn</strong> (<em>callable</em>) – Function to be applied to each submodule, of form <cite>fn(block)</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.collect_params"> |
| <code class="sig-name descname">collect_params</code><span class="sig-paren">(</span><em class="sig-param">select=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.collect_params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns a <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> containing this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and all of its |
| children’s Parameters(default), also can returns the select <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code> |
| which match some given regular expressions.</p> |
| <p>For example, collect the specified parameters in [‘conv1.weight’, ‘conv1.bias’, ‘fc.weight’, |
| ‘fc.bias’]:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'conv1.weight|conv1.bias|fc.weight|fc.bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done |
| using regular expressions:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(</span><span class="s1">'.*weight|.*bias'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>select</strong> (<em>str</em>) – regular expressions</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>The selected <code class="xref py py-class docutils literal notranslate"><span class="pre">Dict</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.export"> |
| <code class="sig-name descname">export</code><span class="sig-paren">(</span><em class="sig-param">path</em>, <em class="sig-param">epoch=0</em>, <em class="sig-param">remove_amp_cast=True</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.export" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Export HybridBlock to json format that can be loaded by |
| <cite>gluon.SymbolBlock.imports</cite> or the C++ interface.</p> |
| <div class="admonition note"> |
| <p class="admonition-title">Note</p> |
| <p>When there are only one input, it will have name <cite>data</cite>. When there |
| Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc.</p> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>path</strong> (<em>str</em><em> or </em><em>None</em>) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> |
| will be created, where xxxx is the 4 digits epoch number. |
| If None, do not export to file but return Python Symbol object and |
| corresponding dictionary of parameters.</p></li> |
| <li><p><strong>epoch</strong> (<em>int</em>) – Epoch number of saved model.</p></li> |
| <li><p><strong>remove_amp_cast</strong> (<em>bool</em><em>, </em><em>optional</em>) – Whether to remove the amp_cast and amp_multicast operators, before saving the model.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p><ul class="simple"> |
| <li><p><strong>symbol_filename</strong> (<em>str</em>) – Filename to which model symbols were saved, including <cite>path</cite> prefix.</p></li> |
| <li><p><strong>params_filename</strong> (<em>str</em>) – Filename to which model parameters were saved, including <cite>path</cite> prefix.</p></li> |
| </ul> |
| </p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.forward"> |
| <code class="sig-name descname">forward</code><span class="sig-paren">(</span><em class="sig-param">x1</em>, <em class="sig-param">x2</em><span class="sig-paren">)</span><a class="reference internal" href="../../../_modules/mxnet/gluon/loss.html#SDMLLoss.forward"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.forward" title="Permalink to this definition">¶</a></dt> |
| <dd><p>the function computes the kl divergence between the negative distances |
| (internally it compute a softmax casting into probabilities) and the |
| identity matrix.</p> |
| <p>This assumes that the two batches are aligned therefore the more similar |
| vector should be the one having the same id.</p> |
| <p>Batch1 Batch2</p> |
| <p>President of France French President |
| President of US American President</p> |
| <p>Given the question president of France in batch 1 the model will |
| learn to predict french president comparing it with all the other |
| vectors in batch 2</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.hybridize"> |
| <code class="sig-name descname">hybridize</code><span class="sig-paren">(</span><em class="sig-param">active=True</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.hybridize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Activates or deactivates <code class="xref py py-class docutils literal notranslate"><span class="pre">HybridBlock</span></code> s recursively. Has no effect on |
| non-hybrid children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>active</strong> (<em>bool</em><em>, </em><em>default True</em>) – Whether to turn hybrid on or off.</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.infer_shape"> |
| <code class="sig-name descname">infer_shape</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.infer_shape" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers shape of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.infer_type"> |
| <code class="sig-name descname">infer_type</code><span class="sig-paren">(</span><em class="sig-param">*args</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.infer_type" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Infers data type of Parameters from inputs.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.initialize"> |
| <code class="sig-name descname">initialize</code><span class="sig-paren">(</span><em class="sig-param">init=<mxnet.initializer.Uniform object></em>, <em class="sig-param">device=None</em>, <em class="sig-param">verbose=False</em>, <em class="sig-param">force_reinit=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.initialize" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Initializes <code class="xref py py-class docutils literal notranslate"><span class="pre">Parameter</span></code> s of this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code> and its children.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>init</strong> (<a class="reference internal" href="../../initializer/index.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer"><em>Initializer</em></a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> is <code class="docutils literal notranslate"><span class="pre">None</span></code>. |
| Otherwise, <code class="xref py py-meth docutils literal notranslate"><span class="pre">Parameter.init()</span></code> takes precedence.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em>) – Keeps a copy of Parameters on one or many device(s).</p></li> |
| <li><p><strong>verbose</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to verbosely print out details on initialization.</p></li> |
| <li><p><strong>force_reinit</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to force re-initialization if parameter is already initialized.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.load"> |
| <code class="sig-name descname">load</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.load" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load a model saved using the <cite>save</cite> API</p> |
| <p>Reconfigures a model using the saved configuration. This function |
| does not regenerate the model architecture. It resets each Block’s |
| parameter UUIDs as they were when saved in order to match the names of the |
| saved parameters.</p> |
| <p>This function assumes the Blocks in the model were created in the same |
| order they were when the model was saved. This is because each Block is |
| uniquely identified by Block class name and a unique ID in order (since |
| its an OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph (Symbol & inputs) and settings are |
| restored if it had been hybridized before saving.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for loading this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.load_dict"> |
| <code class="sig-name descname">load_dict</code><span class="sig-paren">(</span><em class="sig-param">param_dict</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.load_dict" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from dict</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>param_dict</strong> (<em>dict</em>) – Dictionary containing model parameters</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em>, </em><em>optional</em>) – Device context on which the memory is allocated. Default is |
| <cite>mxnet.device.current_device()</cite>.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represented in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this dict.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.load_parameters"> |
| <code class="sig-name descname">load_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">device=None</em>, <em class="sig-param">allow_missing=False</em>, <em class="sig-param">ignore_extra=False</em>, <em class="sig-param">cast_dtype=False</em>, <em class="sig-param">dtype_source='current'</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.load_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Load parameters from file previously saved by <cite>save_parameters</cite>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to parameter file.</p></li> |
| <li><p><strong>device</strong> (<a class="reference internal" href="../../device/index.html#mxnet.device.Device" title="mxnet.device.Device"><em>Device</em></a><em> or </em><em>list of Device</em><em>, </em><em>default cpu</em><em>(</em><em>)</em>) – Device(s) to initialize loaded parameters on.</p></li> |
| <li><p><strong>allow_missing</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently skip loading parameters not represents in the file.</p></li> |
| <li><p><strong>ignore_extra</strong> (<em>bool</em><em>, </em><em>default False</em>) – Whether to silently ignore parameters from the file that are not |
| present in this Block.</p></li> |
| <li><p><strong>cast_dtype</strong> (<em>bool</em><em>, </em><em>default False</em>) – Cast the data type of the NDArray loaded from the checkpoint to the dtype |
| provided by the Parameter if any.</p></li> |
| <li><p><strong>dtype_source</strong> (<em>str</em><em>, </em><em>default 'current'</em>) – must be in {‘current’, ‘saved’} |
| Only valid if cast_dtype=True, specify the source of the dtype for casting |
| the parameters</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.optimize_for"> |
| <code class="sig-name descname">optimize_for</code><span class="sig-paren">(</span><em class="sig-param">x</em>, <em class="sig-param">*args</em>, <em class="sig-param">backend=None</em>, <em class="sig-param">clear=False</em>, <em class="sig-param">partition_if_dynamic=True</em>, <em class="sig-param">static_alloc=False</em>, <em class="sig-param">static_shape=False</em>, <em class="sig-param">inline_limit=2</em>, <em class="sig-param">forward_bulk_size=None</em>, <em class="sig-param">backward_bulk_size=None</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.optimize_for" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Partitions the current HybridBlock and optimizes it for a given backend |
| without executing a forward pass. Modifies the HybridBlock in-place.</p> |
| <p>Immediately partitions a HybridBlock using the specified backend. Combines |
| the work done in the hybridize API with part of the work done in the forward |
| pass without calling the CachedOp. Can be used in place of hybridize, |
| afterwards <cite>export</cite> can be called or inference can be run. See README.md in |
| example/extensions/lib_subgraph/README.md for more details.</p> |
| <p class="rubric">Examples</p> |
| <p># partition and then export to file |
| block.optimize_for(x, backend=’myPart’) |
| block.export(‘partitioned’)</p> |
| <p># partition and then run inference |
| block.optimize_for(x, backend=’myPart’) |
| block(x)</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>x</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – first input to model</p></li> |
| <li><p><strong>*args</strong> (<a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><em>NDArray</em></a>) – other inputs to model</p></li> |
| <li><p><strong>backend</strong> (<em>str</em>) – The name of backend, as registered in <cite>SubgraphBackendRegistry</cite>, default None</p></li> |
| <li><p><strong>backend_opts</strong> (<em>dict of user-specified options to pass to the backend for partitioning</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| <li><p><strong>clear</strong> (<em>bool</em><em>, </em><em>default False</em>) – clears any previous optimizations</p></li> |
| <li><p><strong>partition_if_dynamic</strong> (<em>bool</em><em>, </em><em>default False</em>) – whether to partition the graph when dynamic shape op exists</p></li> |
| <li><p><strong>static_alloc</strong> (<em>bool</em><em>, </em><em>default False</em>) – Statically allocate memory to improve speed. Memory usage may increase.</p></li> |
| <li><p><strong>static_shape</strong> (<em>bool</em><em>, </em><em>default False</em>) – Optimize for invariant input shapes between iterations. Must also |
| set static_alloc to True. Change of input shapes is still allowed |
| but slower.</p></li> |
| <li><p><strong>inline_limit</strong> (<em>optional int</em><em>, </em><em>default 2</em>) – Maximum number of operators that can be inlined.</p></li> |
| <li><p><strong>forward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during forward pass.</p></li> |
| <li><p><strong>backward_bulk_size</strong> (<em>optional int</em><em>, </em><em>default None</em>) – Segment size of bulk execution during backward pass.</p></li> |
| <li><p><strong>**kwargs</strong> (<em>The backend options</em><em>, </em><em>optional</em>) – Passed on to <cite>PrePartition</cite> and <cite>PostPartition</cite> functions of <cite>SubgraphProperty</cite></p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.params"> |
| <em class="property">property </em><code class="sig-name descname">params</code><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.params" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Returns this <code class="xref py py-class docutils literal notranslate"><span class="pre">Block</span></code>’s parameter dictionary (does not include its |
| children’s parameters).</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.register_forward_hook"> |
| <code class="sig-name descname">register_forward_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.register_forward_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward hook on the block.</p> |
| <p>The hook function is called immediately after <a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.forward" title="mxnet.gluon.loss.SDMLLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input, output) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.register_forward_pre_hook"> |
| <code class="sig-name descname">register_forward_pre_hook</code><span class="sig-paren">(</span><em class="sig-param">hook</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.register_forward_pre_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Registers a forward pre-hook on the block.</p> |
| <p>The hook function is called immediately before <a class="reference internal" href="#mxnet.gluon.loss.SDMLLoss.forward" title="mxnet.gluon.loss.SDMLLoss.forward"><code class="xref py py-func docutils literal notranslate"><span class="pre">forward()</span></code></a>. |
| It should not modify the input or output.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>hook</strong> (<em>callable</em>) – The forward hook function of form <cite>hook(block, input) -> None</cite>.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.gluon.utils.HookHandle</span></code></p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.register_op_hook"> |
| <code class="sig-name descname">register_op_hook</code><span class="sig-paren">(</span><em class="sig-param">callback</em>, <em class="sig-param">monitor_all=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.register_op_hook" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Install op hook for block recursively.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>callback</strong> (<em>function</em>) – Function called to inspect the values of the intermediate outputs |
| of blocks after hybridization. It takes 3 parameters: |
| name of the tensor being inspected (str) |
| name of the operator producing or consuming that tensor (str) |
| tensor being inspected (NDArray).</p></li> |
| <li><p><strong>monitor_all</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, monitor both input and output, otherwise monitor output only.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.reset_ctx"> |
| <code class="sig-name descname">reset_ctx</code><span class="sig-paren">(</span><em class="sig-param">ctx</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.reset_ctx" title="Permalink to this definition">¶</a></dt> |
| <dd><p>This function has been deprecated. Please refer to <code class="docutils literal notranslate"><span class="pre">HybridBlock.reset_device</span></code>.</p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.reset_device"> |
| <code class="sig-name descname">reset_device</code><span class="sig-paren">(</span><em class="sig-param">device</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.reset_device" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Re-assign all Parameters to other devices. If the Block is hybridized, it will reset the _cached_op_args.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>device</strong> (Device or list of Device, default <code class="xref py py-meth docutils literal notranslate"><span class="pre">device.current_device()</span></code>.) – Assign Parameter to given device. If device is a list of Device, a |
| copy will be made for each device.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.save"> |
| <code class="sig-name descname">save</code><span class="sig-paren">(</span><em class="sig-param">prefix</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.save" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save the model architecture and parameters to load again later</p> |
| <p>Saves the model architecture as a nested dictionary where each Block |
| in the model is a dictionary and its children are sub-dictionaries.</p> |
| <p>Each Block is uniquely identified by Block class name and a unique ID. |
| We save each Block’s parameter UUID to restore later in order to match |
| the saved parameters.</p> |
| <p>Recursively traverses a Block’s children in order (since its an |
| OrderedDict) and uses the unique ID to denote that specific Block.</p> |
| <p>Assumes that the model is created in an identical order every time. |
| If the model is not able to be recreated deterministically do not |
| use this set of APIs to save/load your model.</p> |
| <p>For HybridBlocks, the cached_graph is saved (Symbol & inputs) if |
| it has already been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>prefix</strong> (<em>str</em>) – The prefix to use in filenames for saving this model: |
| <prefix>-model.json and <prefix>-model.params</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.save_parameters"> |
| <code class="sig-name descname">save_parameters</code><span class="sig-paren">(</span><em class="sig-param">filename</em>, <em class="sig-param">deduplicate=False</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.save_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Save parameters to file.</p> |
| <p>Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this |
| method only saves parameters, not model structure. If you want to save |
| model structures, please use <code class="xref py py-meth docutils literal notranslate"><span class="pre">HybridBlock.export()</span></code>.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>filename</strong> (<em>str</em>) – Path to file.</p></li> |
| <li><p><strong>deduplicate</strong> (<em>bool</em><em>, </em><em>default False</em>) – If True, save shared parameters only once. Otherwise, if a Block |
| contains multiple sub-blocks that share parameters, each of the |
| shared parameters will be separately saved for every sub-block.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p class="rubric">References</p> |
| <p><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></p> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.setattr"> |
| <code class="sig-name descname">setattr</code><span class="sig-paren">(</span><em class="sig-param">name</em>, <em class="sig-param">value</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.setattr" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Set an attribute to a new value for all Parameters.</p> |
| <p>For example, set grad_req to null if you don’t need gradient w.r.t a |
| model’s Parameters:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'grad_req'</span><span class="p">,</span> <span class="s1">'null'</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>or change the learning rate multiplier:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">model</span><span class="o">.</span><span class="n">setattr</span><span class="p">(</span><span class="s1">'lr_mult'</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>name</strong> (<em>str</em>) – Name of the attribute.</p></li> |
| <li><p><strong>value</strong> (<em>valid type for attribute name</em>) – The new value for the attribute.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.share_parameters"> |
| <code class="sig-name descname">share_parameters</code><span class="sig-paren">(</span><em class="sig-param">shared</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.share_parameters" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Share parameters recursively inside the model.</p> |
| <p>For example, if you want <code class="docutils literal notranslate"><span class="pre">dense1</span></code> to share <code class="docutils literal notranslate"><span class="pre">dense0</span></code>’s weights, you can do:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">dense0</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">20</span><span class="p">)</span> |
| <span class="n">dense1</span><span class="o">.</span><span class="n">share_parameters</span><span class="p">(</span><span class="n">dense0</span><span class="o">.</span><span class="n">collect_params</span><span class="p">())</span> |
| </pre></div> |
| </div> |
| <dl class="simple"> |
| <dt>which equals to</dt><dd><p>dense1.weight = dense0.weight |
| dense1.bias = dense0.bias</p> |
| </dd> |
| </dl> |
| <p>Note that unlike the <cite>load_parameters</cite> or <cite>load_dict</cite> functions, |
| <cite>share_parameters</cite> results in the <cite>Parameter</cite> object being shared (or |
| tied) between the models, whereas <cite>load_parameters</cite> or <cite>load_dict</cite> only |
| set the value of the data dictionary of a model. If you call |
| <cite>load_parameters</cite> or <cite>load_dict</cite> after <cite>share_parameters</cite>, the loaded |
| value will be reflected in all networks that use the shared (or tied) |
| <cite>Parameter</cite> object.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>shared</strong> (<em>Dict</em>) – Dict of the shared parameters.</p> |
| </dd> |
| <dt class="field-even">Returns</dt> |
| <dd class="field-even"><p></p> |
| </dd> |
| <dt class="field-odd">Return type</dt> |
| <dd class="field-odd"><p>this block</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.summary"> |
| <code class="sig-name descname">summary</code><span class="sig-paren">(</span><em class="sig-param">*inputs</em><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.summary" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Print the summary of the model’s output and parameters.</p> |
| <p>The network must have been initialized, and must not have been hybridized.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><p><strong>inputs</strong> (<em>object</em>) – Any input that the model supports. For any tensor in the input, only |
| <a class="reference internal" href="../../legacy/ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray"><code class="xref py py-class docutils literal notranslate"><span class="pre">mxnet.ndarray.NDArray</span></code></a> is supported.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="method"> |
| <dt id="mxnet.gluon.loss.SDMLLoss.zero_grad"> |
| <code class="sig-name descname">zero_grad</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#mxnet.gluon.loss.SDMLLoss.zero_grad" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Sets all Parameters’ gradient buffer to 0.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| </div> |
| |
| |
| <hr class="feedback-hr-top" /> |
| <div class="feedback-container"> |
| <div class="feedback-question">Did this page help you?</div> |
| <div class="feedback-answer-container"> |
| <div class="feedback-answer yes-link" data-response="yes">Yes</div> |
| <div class="feedback-answer no-link" data-response="no">No</div> |
| </div> |
| <div class="feedback-thank-you">Thanks for your feedback!</div> |
| </div> |
| <hr class="feedback-hr-bottom" /> |
| </div> |
| <div class="side-doc-outline"> |
| <div class="side-doc-outline--content"> |
| </div> |
| </div> |
| |
| <div class="clearer"></div> |
| </div><div class="pagenation"> |
| <a id="button-prev" href="../data/vision/transforms/index.html" class="mdl-button mdl-js-button mdl-js-ripple-effect mdl-button--colored" role="botton" accesskey="P"> |
| <i class="pagenation-arrow-L fas fa-arrow-left fa-lg"></i> |
| <div class="pagenation-text"> |
| <span class="pagenation-direction">Previous</span> |
| <div>vision.transforms</div> |
| </div> |
| </a> |
| <a id="button-next" href="../metric/index.html" class="mdl-button mdl-js-button mdl-js-ripple-effect mdl-button--colored" role="botton" accesskey="N"> |
| <i class="pagenation-arrow-R fas fa-arrow-right fa-lg"></i> |
| <div class="pagenation-text"> |
| <span class="pagenation-direction">Next</span> |
| <div>gluon.metric</div> |
| </div> |
| </a> |
| </div> |
| <footer class="site-footer h-card"> |
| <div class="wrapper"> |
| <div class="row"> |
| <div class="col-4"> |
| <h4 class="footer-category-title">Resources</h4> |
| <ul class="contact-list"> |
| <li><a href="https://lists.apache.org/list.html?dev@mxnet.apache.org">Mailing list</a> <a class="u-email" href="mailto:dev-subscribe@mxnet.apache.org">(subscribe)</a></li> |
| <li><a href="https://discuss.mxnet.io">MXNet Discuss forum</a></li> |
| <li><a href="https://github.com/apache/mxnet/issues">Github Issues</a></li> |
| <li><a href="https://github.com/apache/mxnet/projects">Projects</a></li> |
| <li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li> |
| <li><a href="/community">Contribute To MXNet</a></li> |
| </ul> |
| </div> |
| |
| <div class="col-4"><ul class="social-media-list"><li><a href="https://github.com/apache/mxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#github"></use></svg> <span class="username">apache/mxnet</span></a></li><li><a href="https://www.twitter.com/apachemxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#twitter"></use></svg> <span class="username">apachemxnet</span></a></li><li><a href="https://youtube.com/apachemxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#youtube"></use></svg> <span class="username">apachemxnet</span></a></li></ul> |
| </div> |
| |
| <div class="col-4 footer-text"> |
| <p>A flexible and efficient library for deep learning.</p> |
| </div> |
| </div> |
| </div> |
| </footer> |
| |
| <footer class="site-footer2"> |
| <div class="wrapper"> |
| <div class="row"> |
| <div class="col-3"> |
| <img src="../../../_static/apache_incubator_logo.png" class="footer-logo col-2"> |
| </div> |
| <div class="footer-bottom-warning col-9"> |
| <p>Apache MXNet is an effort undergoing incubation at <a href="http://www.apache.org/">The Apache Software Foundation</a> (ASF), <span style="font-weight:bold">sponsored by the <i>Apache Incubator</i></span>. Incubation is required |
| of all newly accepted projects until a further review indicates that the infrastructure, |
| communications, and decision making process have stabilized in a manner consistent with other |
| successful ASF projects. While incubation status is not necessarily a reflection of the completeness |
| or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF. |
| </p><p>"Copyright © 2017-2018, The Apache Software Foundation Apache MXNet, MXNet, Apache, the Apache |
| feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the |
| Apache Software Foundation."</p> |
| </div> |
| </div> |
| </div> |
| </footer> |
| |
| </body> |
| </html> |
