| <!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>mxnet.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/google_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" /> |
| </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="/blog">Blog</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="https://github.com/apache/incubator-mxnet">GitHub</a> |
| <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/1.7.0/">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">Module code</a><i class="material-icons">navigate_next</i> |
| <a class="mdl-navigation__link is-active">mxnet.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/_modules/mxnet/gluon/loss" 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> |
| <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">Getting started with NP on MXNet</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/1-ndarray.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-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-train.html">Step 4: Train the neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-predict.html">Step 5: Predict with a pretrained model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/6-use_gpus.html">Step 6: Use GPUs to increase efficiency</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/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/custom_layer_beginners.html">Customer Layers (Beginners)</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/data_augmentation.html#Spatial-Augmentation">Spatial Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Color-Augmentation">Color Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Composed-Augmentations">Composed Augmentations</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> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/train_gluon.html">Sparse NDArrays with Gluon</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/mkldnn/index.html">Intel MKL-DNN</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/mkldnn_readme.html">Install MXNet with MKL-DNN</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tensorrt/index.html">TensorRT</a><ul class="simple"> |
| </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"><a class="reference internal" href="../../../api/index.html">Python API</a><ul> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/np/index.html">mxnet.np</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/np/arrays.html">Array objects</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/arrays.ndarray.html">The N-dimensional array (<code class="xref py py-class docutils literal notranslate"><span class="pre">ndarray</span></code>)</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.html">mxnet.np.ndarray</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.shape.html">mxnet.np.ndarray.shape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.ndim.html">mxnet.np.ndarray.ndim</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.size.html">mxnet.np.ndarray.size</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.dtype.html">mxnet.np.ndarray.dtype</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.T.html">mxnet.np.ndarray.T</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.item.html">mxnet.np.ndarray.item</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.copy.html">mxnet.np.ndarray.copy</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.tolist.html">mxnet.np.ndarray.tolist</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.astype.html">mxnet.np.ndarray.astype</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.reshape.html">mxnet.np.ndarray.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.transpose.html">mxnet.np.ndarray.transpose</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.swapaxes.html">mxnet.np.ndarray.swapaxes</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.flatten.html">mxnet.np.ndarray.flatten</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.squeeze.html">mxnet.np.ndarray.squeeze</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.nonzero.html">mxnet.np.ndarray.nonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.take.html">mxnet.np.ndarray.take</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.repeat.html">mxnet.np.ndarray.repeat</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.max.html">mxnet.np.ndarray.max</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.argmax.html">mxnet.np.ndarray.argmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.min.html">mxnet.np.ndarray.min</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.argmin.html">mxnet.np.ndarray.argmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.clip.html">mxnet.np.ndarray.clip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.sum.html">mxnet.np.ndarray.sum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.mean.html">mxnet.np.ndarray.mean</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.prod.html">mxnet.np.ndarray.prod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.cumsum.html">mxnet.np.ndarray.cumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.var.html">mxnet.np.ndarray.var</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.std.html">mxnet.np.ndarray.std</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__lt__.html">mxnet.np.ndarray.__lt__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__le__.html">mxnet.np.ndarray.__le__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__gt__.html">mxnet.np.ndarray.__gt__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__ge__.html">mxnet.np.ndarray.__ge__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__eq__.html">mxnet.np.ndarray.__eq__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__ne__.html">mxnet.np.ndarray.__ne__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__bool__.html">mxnet.np.ndarray.__bool__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__neg__.html">mxnet.np.ndarray.__neg__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__add__.html">mxnet.np.ndarray.__add__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__sub__.html">mxnet.np.ndarray.__sub__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__mul__.html">mxnet.np.ndarray.__mul__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__truediv__.html">mxnet.np.ndarray.__truediv__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__mod__.html">mxnet.np.ndarray.__mod__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__pow__.html">mxnet.np.ndarray.__pow__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__iadd__.html">mxnet.np.ndarray.__iadd__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__isub__.html">mxnet.np.ndarray.__isub__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__imul__.html">mxnet.np.ndarray.__imul__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__itruediv__.html">mxnet.np.ndarray.__itruediv__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__imod__.html">mxnet.np.ndarray.__imod__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__reduce__.html">mxnet.np.ndarray.__reduce__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__setstate__.html">mxnet.np.ndarray.__setstate__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__len__.html">mxnet.np.ndarray.__len__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__getitem__.html">mxnet.np.ndarray.__getitem__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__setitem__.html">mxnet.np.ndarray.__setitem__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__int__.html">mxnet.np.ndarray.__int__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__float__.html">mxnet.np.ndarray.__float__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__str__.html">mxnet.np.ndarray.__str__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__repr__.html">mxnet.np.ndarray.__repr__</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/arrays.indexing.html">Indexing</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/np/routines.html">Routines</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.array-creation.html">Array creation routines</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.eye.html">mxnet.np.eye</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.empty.html">mxnet.np.empty</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.full.html">mxnet.np.full</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.identity.html">mxnet.np.identity</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ones.html">mxnet.np.ones</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ones_like.html">mxnet.np.ones_like</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.zeros.html">mxnet.np.zeros</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.zeros_like.html">mxnet.np.zeros_like</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.array.html">mxnet.np.array</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.copy.html">mxnet.np.copy</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arange.html">mxnet.np.arange</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linspace.html">mxnet.np.linspace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.logspace.html">mxnet.np.logspace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.meshgrid.html">mxnet.np.meshgrid</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tril.html">mxnet.np.tril</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.array-manipulation.html">Array manipulation routines</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.reshape.html">mxnet.np.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ravel.html">mxnet.np.ravel</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.flatten.html">mxnet.np.ndarray.flatten</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.swapaxes.html">mxnet.np.swapaxes</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.T.html">mxnet.np.ndarray.T</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.transpose.html">mxnet.np.transpose</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.moveaxis.html">mxnet.np.moveaxis</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.expand_dims.html">mxnet.np.expand_dims</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.squeeze.html">mxnet.np.squeeze</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.broadcast_to.html">mxnet.np.broadcast_to</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.broadcast_arrays.html">mxnet.np.broadcast_arrays</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.concatenate.html">mxnet.np.concatenate</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.stack.html">mxnet.np.stack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.dstack.html">mxnet.np.dstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.vstack.html">mxnet.np.vstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.split.html">mxnet.np.split</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.hsplit.html">mxnet.np.hsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.vsplit.html">mxnet.np.vsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tile.html">mxnet.np.tile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.repeat.html">mxnet.np.repeat</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.unique.html">mxnet.np.unique</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.reshape.html">mxnet.np.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.flip.html">mxnet.np.flip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.roll.html">mxnet.np.roll</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.rot90.html">mxnet.np.rot90</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.io.html">Input and output</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.genfromtxt.html">mxnet.np.genfromtxt</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/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="../../../api/np/generated/mxnet.np.dot.html">mxnet.np.dot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.vdot.html">mxnet.np.vdot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.inner.html">mxnet.np.inner</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.outer.html">mxnet.np.outer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tensordot.html">mxnet.np.tensordot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.einsum.html">mxnet.np.einsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.svd.html">mxnet.np.linalg.svd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.norm.html">mxnet.np.linalg.norm</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.trace.html">mxnet.np.trace</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.math.html">Mathematical functions</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sin.html">mxnet.np.sin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cos.html">mxnet.np.cos</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tan.html">mxnet.np.tan</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arcsin.html">mxnet.np.arcsin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arccos.html">mxnet.np.arccos</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arctan.html">mxnet.np.arctan</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.degrees.html">mxnet.np.degrees</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.radians.html">mxnet.np.radians</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.hypot.html">mxnet.np.hypot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arctan2.html">mxnet.np.arctan2</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.deg2rad.html">mxnet.np.deg2rad</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.rad2deg.html">mxnet.np.rad2deg</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sinh.html">mxnet.np.sinh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cosh.html">mxnet.np.cosh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tanh.html">mxnet.np.tanh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arcsinh.html">mxnet.np.arcsinh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arccosh.html">mxnet.np.arccosh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arctanh.html">mxnet.np.arctanh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.rint.html">mxnet.np.rint</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fix.html">mxnet.np.fix</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.floor.html">mxnet.np.floor</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ceil.html">mxnet.np.ceil</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.trunc.html">mxnet.np.trunc</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.around.html">mxnet.np.around</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sum.html">mxnet.np.sum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.prod.html">mxnet.np.prod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cumsum.html">mxnet.np.cumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.exp.html">mxnet.np.exp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.expm1.html">mxnet.np.expm1</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.log.html">mxnet.np.log</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.log10.html">mxnet.np.log10</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.log2.html">mxnet.np.log2</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.log1p.html">mxnet.np.log1p</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ldexp.html">mxnet.np.ldexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.lcm.html">mxnet.np.lcm</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.add.html">mxnet.np.add</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.reciprocal.html">mxnet.np.reciprocal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.negative.html">mxnet.np.negative</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.divide.html">mxnet.np.divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.power.html">mxnet.np.power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.subtract.html">mxnet.np.subtract</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.mod.html">mxnet.np.mod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.multiply.html">mxnet.np.multiply</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.true_divide.html">mxnet.np.true_divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.remainder.html">mxnet.np.remainder</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.clip.html">mxnet.np.clip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sqrt.html">mxnet.np.sqrt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cbrt.html">mxnet.np.cbrt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.square.html">mxnet.np.square</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.absolute.html">mxnet.np.absolute</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sign.html">mxnet.np.sign</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.maximum.html">mxnet.np.maximum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.minimum.html">mxnet.np.minimum</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/random/index.html">np.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.sort.html">Sorting, searching, and counting</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argmax.html">mxnet.np.argmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argmin.html">mxnet.np.argmin</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.statistics.html">Statistics</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.min.html">mxnet.np.min</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.max.html">mxnet.np.max</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.mean.html">mxnet.np.mean</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.std.html">mxnet.np.std</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.var.html">mxnet.np.var</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogram.html">mxnet.np.histogram</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/npx/index.html">NPX: NumPy Neural Network Extension</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.set_np.html">mxnet.npx.set_np</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.reset_np.html">mxnet.npx.reset_np</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.cpu.html">mxnet.npx.cpu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.cpu_pinned.html">mxnet.npx.cpu_pinned</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.gpu.html">mxnet.npx.gpu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.gpu_memory_info.html">mxnet.npx.gpu_memory_info</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.current_context.html">mxnet.npx.current_context</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.num_gpus.html">mxnet.npx.num_gpus</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.activation.html">mxnet.npx.activation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.batch_norm.html">mxnet.npx.batch_norm</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.convolution.html">mxnet.npx.convolution</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.dropout.html">mxnet.npx.dropout</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.embedding.html">mxnet.npx.embedding</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.fully_connected.html">mxnet.npx.fully_connected</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.layer_norm.html">mxnet.npx.layer_norm</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.pooling.html">mxnet.npx.pooling</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.rnn.html">mxnet.npx.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.leaky_relu.html">mxnet.npx.leaky_relu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.multibox_detection.html">mxnet.npx.multibox_detection</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.multibox_prior.html">mxnet.npx.multibox_prior</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.multibox_target.html">mxnet.npx.multibox_target</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.roi_pooling.html">mxnet.npx.roi_pooling</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.sigmoid.html">mxnet.npx.sigmoid</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.smooth_l1.html">mxnet.npx.smooth_l1</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.softmax.html">mxnet.npx.softmax</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.topk.html">mxnet.npx.topk</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.waitall.html">mxnet.npx.waitall</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.load.html">mxnet.npx.load</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.save.html">mxnet.npx.save</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.one_hot.html">mxnet.npx.one_hot</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.pick.html">mxnet.npx.pick</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.reshape_like.html">mxnet.npx.reshape_like</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.batch_flatten.html">mxnet.npx.batch_flatten</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.batch_dot.html">mxnet.npx.batch_dot</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.gamma.html">mxnet.npx.gamma</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.sequence_mask.html">mxnet.npx.sequence_mask</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/gluon/index.html">mxnet.gluon</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/block.html">gluon.Block</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/hybrid_block.html">gluon.HybridBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/symbol_block.html">gluon.SymbolBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/constant.html">gluon.Constant</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/parameter.html">gluon.Parameter</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/parameter_dict.html">gluon.ParameterDict</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/trainer.html">gluon.Trainer</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/contrib/index.html">gluon.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/data/index.html">gluon.data</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/gluon/data/vision/index.html">data.vision</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/gluon/data/vision/datasets/index.html">vision.datasets</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/gluon/data/vision/transforms/index.html">vision.transforms</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/loss/index.html">gluon.loss</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/metric/index.html">gluon.metric</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/model_zoo/index.html">gluon.model_zoo.vision</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/nn/index.html">gluon.nn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/rnn/index.html">gluon.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/utils/index.html">gluon.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/autograd/index.html">mxnet.autograd</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/initializer/index.html">mxnet.initializer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/optimizer/index.html">mxnet.optimizer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/lr_scheduler/index.html">mxnet.lr_scheduler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore/index.html">mxnet.kvstore</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/module/index.html">mxnet.module</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/contrib/index.html">mxnet.contrib</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/autograd/index.html">contrib.autograd</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/io/index.html">contrib.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/ndarray/index.html">contrib.ndarray</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/onnx/index.html">contrib.onnx</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/quantization/index.html">contrib.quantization</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/symbol/index.html">contrib.symbol</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/tensorboard/index.html">contrib.tensorboard</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/tensorrt/index.html">contrib.tensorrt</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/text/index.html">contrib.text</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/legacy/index.html">Legacy</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/callback/index.html">mxnet.callback</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/image/index.html">mxnet.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/io/index.html">mxnet.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/monitor/index.html">mxnet.monitor</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/ndarray/index.html">mxnet.ndarray</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/ndarray.html">ndarray</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/contrib/index.html">ndarray.contrib</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/image/index.html">ndarray.image</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/linalg/index.html">ndarray.linalg</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/op/index.html">ndarray.op</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/random/index.html">ndarray.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/register/index.html">ndarray.register</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/sparse/index.html">ndarray.sparse</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/utils/index.html">ndarray.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/recordio/index.html">mxnet.recordio</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/symbol/index.html">mxnet.symbol</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/symbol.html">symbol</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/contrib/index.html">symbol.contrib</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/image/index.html">symbol.image</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/linalg/index.html">symbol.linalg</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/op/index.html">symbol.op</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/random/index.html">symbol.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/register/index.html">symbol.register</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/sparse/index.html">symbol.sparse</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/visualization/index.html">mxnet.visualization</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/context/index.html">mxnet.context</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/engine/index.html">mxnet.engine</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/executor/index.html">mxnet.executor</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore_server/index.html">mxnet.kvstore_server</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/profiler/index.html">mxnet.profiler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/rtc/index.html">mxnet.rtc</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/runtime/index.html">mxnet.runtime</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/test_utils/index.html">mxnet.test_utils</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/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> |
| <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">Getting started with NP on MXNet</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/1-ndarray.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-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-train.html">Step 4: Train the neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-predict.html">Step 5: Predict with a pretrained model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/6-use_gpus.html">Step 6: Use GPUs to increase efficiency</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/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/custom_layer_beginners.html">Customer Layers (Beginners)</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/data_augmentation.html#Spatial-Augmentation">Spatial Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Color-Augmentation">Color Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html#Composed-Augmentations">Composed Augmentations</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> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/train_gluon.html">Sparse NDArrays with Gluon</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/mkldnn/index.html">Intel MKL-DNN</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/mkldnn/mkldnn_readme.html">Install MXNet with MKL-DNN</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tensorrt/index.html">TensorRT</a><ul class="simple"> |
| </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"><a class="reference internal" href="../../../api/index.html">Python API</a><ul> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/np/index.html">mxnet.np</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/np/arrays.html">Array objects</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/arrays.ndarray.html">The N-dimensional array (<code class="xref py py-class docutils literal notranslate"><span class="pre">ndarray</span></code>)</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.html">mxnet.np.ndarray</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.shape.html">mxnet.np.ndarray.shape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.ndim.html">mxnet.np.ndarray.ndim</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.size.html">mxnet.np.ndarray.size</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.dtype.html">mxnet.np.ndarray.dtype</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.T.html">mxnet.np.ndarray.T</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.item.html">mxnet.np.ndarray.item</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.copy.html">mxnet.np.ndarray.copy</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.tolist.html">mxnet.np.ndarray.tolist</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.astype.html">mxnet.np.ndarray.astype</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.reshape.html">mxnet.np.ndarray.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.transpose.html">mxnet.np.ndarray.transpose</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.swapaxes.html">mxnet.np.ndarray.swapaxes</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.flatten.html">mxnet.np.ndarray.flatten</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.squeeze.html">mxnet.np.ndarray.squeeze</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.nonzero.html">mxnet.np.ndarray.nonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.take.html">mxnet.np.ndarray.take</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.repeat.html">mxnet.np.ndarray.repeat</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.max.html">mxnet.np.ndarray.max</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.argmax.html">mxnet.np.ndarray.argmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.min.html">mxnet.np.ndarray.min</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.argmin.html">mxnet.np.ndarray.argmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.clip.html">mxnet.np.ndarray.clip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.sum.html">mxnet.np.ndarray.sum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.mean.html">mxnet.np.ndarray.mean</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.prod.html">mxnet.np.ndarray.prod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.cumsum.html">mxnet.np.ndarray.cumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.var.html">mxnet.np.ndarray.var</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.std.html">mxnet.np.ndarray.std</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__lt__.html">mxnet.np.ndarray.__lt__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__le__.html">mxnet.np.ndarray.__le__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__gt__.html">mxnet.np.ndarray.__gt__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__ge__.html">mxnet.np.ndarray.__ge__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__eq__.html">mxnet.np.ndarray.__eq__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__ne__.html">mxnet.np.ndarray.__ne__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__bool__.html">mxnet.np.ndarray.__bool__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__neg__.html">mxnet.np.ndarray.__neg__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__add__.html">mxnet.np.ndarray.__add__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__sub__.html">mxnet.np.ndarray.__sub__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__mul__.html">mxnet.np.ndarray.__mul__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__truediv__.html">mxnet.np.ndarray.__truediv__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__mod__.html">mxnet.np.ndarray.__mod__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__pow__.html">mxnet.np.ndarray.__pow__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__iadd__.html">mxnet.np.ndarray.__iadd__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__isub__.html">mxnet.np.ndarray.__isub__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__imul__.html">mxnet.np.ndarray.__imul__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__itruediv__.html">mxnet.np.ndarray.__itruediv__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__imod__.html">mxnet.np.ndarray.__imod__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__reduce__.html">mxnet.np.ndarray.__reduce__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__setstate__.html">mxnet.np.ndarray.__setstate__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__len__.html">mxnet.np.ndarray.__len__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__getitem__.html">mxnet.np.ndarray.__getitem__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__setitem__.html">mxnet.np.ndarray.__setitem__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__int__.html">mxnet.np.ndarray.__int__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__float__.html">mxnet.np.ndarray.__float__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__str__.html">mxnet.np.ndarray.__str__</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.__repr__.html">mxnet.np.ndarray.__repr__</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/arrays.indexing.html">Indexing</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/np/routines.html">Routines</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.array-creation.html">Array creation routines</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.eye.html">mxnet.np.eye</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.empty.html">mxnet.np.empty</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.full.html">mxnet.np.full</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.identity.html">mxnet.np.identity</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ones.html">mxnet.np.ones</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ones_like.html">mxnet.np.ones_like</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.zeros.html">mxnet.np.zeros</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.zeros_like.html">mxnet.np.zeros_like</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.array.html">mxnet.np.array</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.copy.html">mxnet.np.copy</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arange.html">mxnet.np.arange</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linspace.html">mxnet.np.linspace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.logspace.html">mxnet.np.logspace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.meshgrid.html">mxnet.np.meshgrid</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tril.html">mxnet.np.tril</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.array-manipulation.html">Array manipulation routines</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.reshape.html">mxnet.np.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ravel.html">mxnet.np.ravel</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.flatten.html">mxnet.np.ndarray.flatten</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.swapaxes.html">mxnet.np.swapaxes</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ndarray.T.html">mxnet.np.ndarray.T</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.transpose.html">mxnet.np.transpose</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.moveaxis.html">mxnet.np.moveaxis</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.expand_dims.html">mxnet.np.expand_dims</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.squeeze.html">mxnet.np.squeeze</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.broadcast_to.html">mxnet.np.broadcast_to</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.broadcast_arrays.html">mxnet.np.broadcast_arrays</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.concatenate.html">mxnet.np.concatenate</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.stack.html">mxnet.np.stack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.dstack.html">mxnet.np.dstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.vstack.html">mxnet.np.vstack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.split.html">mxnet.np.split</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.hsplit.html">mxnet.np.hsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.vsplit.html">mxnet.np.vsplit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tile.html">mxnet.np.tile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.repeat.html">mxnet.np.repeat</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.unique.html">mxnet.np.unique</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.reshape.html">mxnet.np.reshape</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.flip.html">mxnet.np.flip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.roll.html">mxnet.np.roll</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.rot90.html">mxnet.np.rot90</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.io.html">Input and output</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.genfromtxt.html">mxnet.np.genfromtxt</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/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="../../../api/np/generated/mxnet.np.dot.html">mxnet.np.dot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.vdot.html">mxnet.np.vdot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.inner.html">mxnet.np.inner</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.outer.html">mxnet.np.outer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tensordot.html">mxnet.np.tensordot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.einsum.html">mxnet.np.einsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.svd.html">mxnet.np.linalg.svd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.norm.html">mxnet.np.linalg.norm</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.trace.html">mxnet.np.trace</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.math.html">Mathematical functions</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sin.html">mxnet.np.sin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cos.html">mxnet.np.cos</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tan.html">mxnet.np.tan</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arcsin.html">mxnet.np.arcsin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arccos.html">mxnet.np.arccos</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arctan.html">mxnet.np.arctan</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.degrees.html">mxnet.np.degrees</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.radians.html">mxnet.np.radians</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.hypot.html">mxnet.np.hypot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arctan2.html">mxnet.np.arctan2</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.deg2rad.html">mxnet.np.deg2rad</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.rad2deg.html">mxnet.np.rad2deg</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sinh.html">mxnet.np.sinh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cosh.html">mxnet.np.cosh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.tanh.html">mxnet.np.tanh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arcsinh.html">mxnet.np.arcsinh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arccosh.html">mxnet.np.arccosh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.arctanh.html">mxnet.np.arctanh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.rint.html">mxnet.np.rint</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fix.html">mxnet.np.fix</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.floor.html">mxnet.np.floor</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ceil.html">mxnet.np.ceil</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.trunc.html">mxnet.np.trunc</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.around.html">mxnet.np.around</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sum.html">mxnet.np.sum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.prod.html">mxnet.np.prod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cumsum.html">mxnet.np.cumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.exp.html">mxnet.np.exp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.expm1.html">mxnet.np.expm1</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.log.html">mxnet.np.log</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.log10.html">mxnet.np.log10</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.log2.html">mxnet.np.log2</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.log1p.html">mxnet.np.log1p</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ldexp.html">mxnet.np.ldexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.lcm.html">mxnet.np.lcm</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.add.html">mxnet.np.add</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.reciprocal.html">mxnet.np.reciprocal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.negative.html">mxnet.np.negative</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.divide.html">mxnet.np.divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.power.html">mxnet.np.power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.subtract.html">mxnet.np.subtract</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.mod.html">mxnet.np.mod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.multiply.html">mxnet.np.multiply</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.true_divide.html">mxnet.np.true_divide</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.remainder.html">mxnet.np.remainder</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.clip.html">mxnet.np.clip</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sqrt.html">mxnet.np.sqrt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cbrt.html">mxnet.np.cbrt</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.square.html">mxnet.np.square</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.absolute.html">mxnet.np.absolute</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sign.html">mxnet.np.sign</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.maximum.html">mxnet.np.maximum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.minimum.html">mxnet.np.minimum</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/random/index.html">np.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.sort.html">Sorting, searching, and counting</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argmax.html">mxnet.np.argmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argmin.html">mxnet.np.argmin</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/routines.statistics.html">Statistics</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.min.html">mxnet.np.min</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.max.html">mxnet.np.max</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.mean.html">mxnet.np.mean</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.std.html">mxnet.np.std</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.var.html">mxnet.np.var</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogram.html">mxnet.np.histogram</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/npx/index.html">NPX: NumPy Neural Network Extension</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.set_np.html">mxnet.npx.set_np</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.reset_np.html">mxnet.npx.reset_np</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.cpu.html">mxnet.npx.cpu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.cpu_pinned.html">mxnet.npx.cpu_pinned</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.gpu.html">mxnet.npx.gpu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.gpu_memory_info.html">mxnet.npx.gpu_memory_info</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.current_context.html">mxnet.npx.current_context</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.num_gpus.html">mxnet.npx.num_gpus</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.activation.html">mxnet.npx.activation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.batch_norm.html">mxnet.npx.batch_norm</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.convolution.html">mxnet.npx.convolution</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.dropout.html">mxnet.npx.dropout</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.embedding.html">mxnet.npx.embedding</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.fully_connected.html">mxnet.npx.fully_connected</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.layer_norm.html">mxnet.npx.layer_norm</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.pooling.html">mxnet.npx.pooling</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.rnn.html">mxnet.npx.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.leaky_relu.html">mxnet.npx.leaky_relu</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.multibox_detection.html">mxnet.npx.multibox_detection</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.multibox_prior.html">mxnet.npx.multibox_prior</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.multibox_target.html">mxnet.npx.multibox_target</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.roi_pooling.html">mxnet.npx.roi_pooling</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.sigmoid.html">mxnet.npx.sigmoid</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.smooth_l1.html">mxnet.npx.smooth_l1</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.softmax.html">mxnet.npx.softmax</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.topk.html">mxnet.npx.topk</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.waitall.html">mxnet.npx.waitall</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.load.html">mxnet.npx.load</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.save.html">mxnet.npx.save</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.one_hot.html">mxnet.npx.one_hot</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.pick.html">mxnet.npx.pick</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.reshape_like.html">mxnet.npx.reshape_like</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.batch_flatten.html">mxnet.npx.batch_flatten</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.batch_dot.html">mxnet.npx.batch_dot</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.gamma.html">mxnet.npx.gamma</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/npx/generated/mxnet.npx.sequence_mask.html">mxnet.npx.sequence_mask</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/gluon/index.html">mxnet.gluon</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/block.html">gluon.Block</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/hybrid_block.html">gluon.HybridBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/symbol_block.html">gluon.SymbolBlock</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/constant.html">gluon.Constant</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/parameter.html">gluon.Parameter</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/parameter_dict.html">gluon.ParameterDict</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/trainer.html">gluon.Trainer</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/contrib/index.html">gluon.contrib</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/data/index.html">gluon.data</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/gluon/data/vision/index.html">data.vision</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/gluon/data/vision/datasets/index.html">vision.datasets</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/gluon/data/vision/transforms/index.html">vision.transforms</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/loss/index.html">gluon.loss</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/metric/index.html">gluon.metric</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/model_zoo/index.html">gluon.model_zoo.vision</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/nn/index.html">gluon.nn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/rnn/index.html">gluon.rnn</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/gluon/utils/index.html">gluon.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/autograd/index.html">mxnet.autograd</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/initializer/index.html">mxnet.initializer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/optimizer/index.html">mxnet.optimizer</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/lr_scheduler/index.html">mxnet.lr_scheduler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore/index.html">mxnet.kvstore</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/module/index.html">mxnet.module</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/contrib/index.html">mxnet.contrib</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/autograd/index.html">contrib.autograd</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/io/index.html">contrib.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/ndarray/index.html">contrib.ndarray</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/onnx/index.html">contrib.onnx</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/quantization/index.html">contrib.quantization</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/symbol/index.html">contrib.symbol</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/tensorboard/index.html">contrib.tensorboard</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/tensorrt/index.html">contrib.tensorrt</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/contrib/text/index.html">contrib.text</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/legacy/index.html">Legacy</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/callback/index.html">mxnet.callback</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/image/index.html">mxnet.image</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/io/index.html">mxnet.io</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/monitor/index.html">mxnet.monitor</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/ndarray/index.html">mxnet.ndarray</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/ndarray.html">ndarray</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/contrib/index.html">ndarray.contrib</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/image/index.html">ndarray.image</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/linalg/index.html">ndarray.linalg</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/op/index.html">ndarray.op</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/random/index.html">ndarray.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/register/index.html">ndarray.register</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/sparse/index.html">ndarray.sparse</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/ndarray/utils/index.html">ndarray.utils</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/recordio/index.html">mxnet.recordio</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/symbol/index.html">mxnet.symbol</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/symbol.html">symbol</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/contrib/index.html">symbol.contrib</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/image/index.html">symbol.image</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/linalg/index.html">symbol.linalg</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/op/index.html">symbol.op</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/random/index.html">symbol.random</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/register/index.html">symbol.register</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/legacy/symbol/sparse/index.html">symbol.sparse</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/legacy/visualization/index.html">mxnet.visualization</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/context/index.html">mxnet.context</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/engine/index.html">mxnet.engine</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/executor/index.html">mxnet.executor</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore_server/index.html">mxnet.kvstore_server</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/profiler/index.html">mxnet.profiler</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/rtc/index.html">mxnet.rtc</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/runtime/index.html">mxnet.runtime</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/test_utils/index.html">mxnet.test_utils</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/util/index.html">mxnet.util</a></li> |
| </ul> |
| </li> |
| </ul> |
| |
| </nav> |
| |
| </div> |
| |
| </header> |
| |
| <div class="document"> |
| <div class="page-content" role="main"> |
| |
| <h1>Source code for mxnet.gluon.loss</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| |
| <span class="c1"># coding: utf-8</span> |
| <span class="c1"># pylint: disable=arguments-differ</span> |
| <span class="sd">""" losses for training neural networks """</span> |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'Loss'</span><span class="p">,</span> <span class="s1">'L2Loss'</span><span class="p">,</span> <span class="s1">'L1Loss'</span><span class="p">,</span> |
| <span class="s1">'SigmoidBinaryCrossEntropyLoss'</span><span class="p">,</span> <span class="s1">'SigmoidBCELoss'</span><span class="p">,</span> |
| <span class="s1">'SoftmaxCrossEntropyLoss'</span><span class="p">,</span> <span class="s1">'SoftmaxCELoss'</span><span class="p">,</span> |
| <span class="s1">'KLDivLoss'</span><span class="p">,</span> <span class="s1">'CTCLoss'</span><span class="p">,</span> <span class="s1">'HuberLoss'</span><span class="p">,</span> <span class="s1">'HingeLoss'</span><span class="p">,</span> |
| <span class="s1">'SquaredHingeLoss'</span><span class="p">,</span> <span class="s1">'LogisticLoss'</span><span class="p">,</span> <span class="s1">'TripletLoss'</span><span class="p">,</span> <span class="s1">'PoissonNLLLoss'</span><span class="p">,</span> <span class="s1">'CosineEmbeddingLoss'</span><span class="p">,</span> <span class="s1">'SDMLLoss'</span><span class="p">]</span> |
| |
| <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="kn">from</span> <span class="nn">..</span> <span class="kn">import</span> <span class="n">ndarray</span> |
| <span class="kn">from</span> <span class="nn">..base</span> <span class="kn">import</span> <span class="n">numeric_types</span> |
| <span class="kn">from</span> <span class="nn">.block</span> <span class="kn">import</span> <span class="n">HybridBlock</span> |
| <span class="kn">from</span> <span class="nn">..util</span> <span class="kn">import</span> <span class="n">is_np_array</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""Apply weighting to loss.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> loss : Symbol</span> |
| <span class="sd"> The loss to be weighted.</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> sample_weight : Symbol or None</span> |
| <span class="sd"> Per sample weighting. Must be broadcastable to</span> |
| <span class="sd"> the same shape as loss. For example, if loss has</span> |
| <span class="sd"> shape (64, 10) and you want to weight each sample</span> |
| <span class="sd"> in the batch separately, `sample_weight` should have</span> |
| <span class="sd"> shape (64, 1).</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> loss : Symbol</span> |
| <span class="sd"> Weighted loss</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">sample_weight</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">loss</span> <span class="o">*</span> <span class="n">sample_weight</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">broadcast_mul</span><span class="p">(</span><span class="n">loss</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">weight</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">numeric_types</span><span class="p">),</span> <span class="s2">"weight must be a number"</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">loss</span> <span class="o">*</span> <span class="n">weight</span> |
| |
| <span class="k">return</span> <span class="n">loss</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">):</span> |
| <span class="sd">"""Reshapes x to the same shape as y."""</span> |
| <span class="k">if</span> <span class="n">F</span> <span class="ow">is</span> <span class="n">ndarray</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">y</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">F</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">reshape_like</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">):</span> |
| <span class="sd">"""Return mean on the specified batch axis, not keeping the axis"""</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">F</span> <span class="ow">is</span> <span class="n">ndarray</span><span class="p">:</span> |
| <span class="n">axes</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">loss</span><span class="o">.</span><span class="n">ndim</span><span class="p">))</span> |
| <span class="k">del</span> <span class="n">axes</span><span class="p">[</span><span class="n">batch_axis</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">loss</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="n">axes</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">batch_axis</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span> <span class="s1">'Currently, we have not supported the "exclude" '</span> \ |
| <span class="s1">'flag in mean. So we only support batch_axis=0.'</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">batch_flatten</span><span class="p">(</span><span class="n">loss</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">loss</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="n">batch_axis</span><span class="p">,</span> <span class="n">exclude</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_batch_sum</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">):</span> |
| <span class="sd">"""Return sum on the specified batch axis, not keeping the axis"""</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">F</span> <span class="ow">is</span> <span class="n">ndarray</span><span class="p">:</span> |
| <span class="n">axes</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">loss</span><span class="o">.</span><span class="n">ndim</span><span class="p">))</span> |
| <span class="k">del</span> <span class="n">axes</span><span class="p">[</span><span class="n">batch_axis</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">loss</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="n">axes</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">batch_axis</span> <span class="o">==</span> <span class="mi">0</span><span class="p">,</span> <span class="s1">'Currently, we have not supported the "exclude" '</span> \ |
| <span class="s1">'flag in mean. So we only support batch_axis=0.'</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">batch_flatten</span><span class="p">(</span><span class="n">loss</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">loss</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="n">batch_axis</span><span class="p">,</span> <span class="n">exclude</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| |
| |
| |
| <div class="viewcode-block" id="Loss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.Loss">[docs]</a><span class="k">class</span> <span class="nc">Loss</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span> |
| <span class="sd">"""Base class for loss.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">Loss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span> <span class="o">=</span> <span class="n">weight</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span> <span class="o">=</span> <span class="n">batch_axis</span> |
| |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(batch_axis=</span><span class="si">{_batch_axis}</span><span class="s1">, w=</span><span class="si">{_weight}</span><span class="s1">)'</span> |
| <span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="Loss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.Loss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="sd">"""Overrides to construct symbolic graph for this `Block`.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> x : Symbol or NDArray</span> |
| <span class="sd"> The first input tensor.</span> |
| <span class="sd"> *args : list of Symbol or list of NDArray</span> |
| <span class="sd"> Additional input tensors.</span> |
| |
| <span class="sd"> """</span> |
| <span class="c1"># pylint: disable= invalid-name</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div></div> |
| |
| |
| <div class="viewcode-block" id="L2Loss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.L2Loss">[docs]</a><span class="k">class</span> <span class="nc">L2Loss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Calculates the mean squared error between `label` and `pred`.</span> |
| |
| <span class="sd"> .. math:: L = \frac{1}{2} \sum_i \vert {label}_i - {pred}_i \vert^2.</span> |
| |
| <span class="sd"> `label` and `pred` can have arbitrary shape as long as they have the same</span> |
| <span class="sd"> number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape</span> |
| <span class="sd"> - **label**: target tensor with the same size as pred.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="mf">1.</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">L2Loss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="L2Loss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.L2Loss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="n">square_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">square</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">square</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">square_fn</span><span class="p">(</span><span class="n">label</span> <span class="o">-</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span> <span class="o">/</span> <span class="mi">2</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="L1Loss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.L1Loss">[docs]</a><span class="k">class</span> <span class="nc">L1Loss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Calculates the mean absolute error between `label` and `pred`.</span> |
| |
| <span class="sd"> .. math:: L = \sum_i \vert {label}_i - {pred}_i \vert.</span> |
| |
| <span class="sd"> `label` and `pred` can have arbitrary shape as long as they have the same</span> |
| <span class="sd"> number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape</span> |
| <span class="sd"> - **label**: target tensor with the same size as pred.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">L1Loss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="L1Loss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.L1Loss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="n">abs_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">abs</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">abs</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">abs_fn</span><span class="p">(</span><span class="n">label</span> <span class="o">-</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="SigmoidBinaryCrossEntropyLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss">[docs]</a><span class="k">class</span> <span class="nc">SigmoidBinaryCrossEntropyLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""The cross-entropy loss for binary classification. (alias: SigmoidBCELoss)</span> |
| |
| <span class="sd"> BCE loss is useful when training logistic regression. If `from_sigmoid`</span> |
| <span class="sd"> is False (default), this loss computes:</span> |
| |
| <span class="sd"> .. math::</span> |
| |
| <span class="sd"> prob = \frac{1}{1 + \exp(-{pred})}</span> |
| |
| <span class="sd"> L = - \sum_i {label}_i * \log({prob}_i) * pos\_weight +</span> |
| <span class="sd"> (1 - {label}_i) * \log(1 - {prob}_i)</span> |
| |
| <span class="sd"> If `from_sigmoid` is True, this loss computes:</span> |
| |
| <span class="sd"> .. math::</span> |
| |
| <span class="sd"> L = - \sum_i {label}_i * \log({pred}_i) * pos\_weight +</span> |
| <span class="sd"> (1 - {label}_i) * \log(1 - {pred}_i)</span> |
| |
| <span class="sd"> A tensor `pos_weight > 1` decreases the false negative count, hence increasing</span> |
| <span class="sd"> the recall.</span> |
| <span class="sd"> Conversely setting `pos_weight < 1` decreases the false positive count and</span> |
| <span class="sd"> increases the precision.</span> |
| |
| <span class="sd"> `pred` and `label` can have arbitrary shape as long as they have the same</span> |
| <span class="sd"> number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> from_sigmoid : bool, default is `False`</span> |
| <span class="sd"> Whether the input is from the output of sigmoid. Set this to false will make</span> |
| <span class="sd"> the loss calculate sigmoid and BCE together, which is more numerically</span> |
| <span class="sd"> stable through log-sum-exp trick.</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape</span> |
| <span class="sd"> - **label**: target tensor with values in range `[0, 1]`. Must have the</span> |
| <span class="sd"> same size as `pred`.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| <span class="sd"> - **pos_weight**: a weighting tensor of positive examples. Must be a vector with length</span> |
| <span class="sd"> equal to the number of classes.For example, if pred has shape (64, 10),</span> |
| <span class="sd"> pos_weight should have shape (1, 10).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">from_sigmoid</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">SigmoidBinaryCrossEntropyLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_from_sigmoid</span> <span class="o">=</span> <span class="n">from_sigmoid</span> |
| |
| <div class="viewcode-block" id="SigmoidBinaryCrossEntropyLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.SigmoidBinaryCrossEntropyLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">pos_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">act_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">activation</span> |
| <span class="n">abs_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">abs</span> |
| <span class="n">mul_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">multiply</span> |
| <span class="n">log_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">log</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">act_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">Activation</span> |
| <span class="n">abs_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">abs</span> |
| <span class="n">mul_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">broadcast_mul</span> |
| <span class="n">log_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">log</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_from_sigmoid</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">pos_weight</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="c1"># We use the stable formula: max(x, 0) - x * z + log(1 + exp(-abs(x)))</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">relu_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">)</span> <span class="o">-</span> <span class="n">pred</span> <span class="o">*</span> <span class="n">label</span> <span class="o">+</span> \ |
| <span class="n">act_fn</span><span class="p">(</span><span class="o">-</span><span class="n">abs_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">),</span> <span class="n">act_type</span><span class="o">=</span><span class="s1">'softrelu'</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># We use the stable formula: x - x * z + (1 + z * pos_weight - z) * \</span> |
| <span class="c1"># (log(1 + exp(-abs(x))) + max(-x, 0))</span> |
| <span class="n">log_weight</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">+</span> <span class="n">mul_fn</span><span class="p">(</span><span class="n">pos_weight</span> <span class="o">-</span> <span class="mi">1</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">pred</span> <span class="o">-</span> <span class="n">pred</span> <span class="o">*</span> <span class="n">label</span> <span class="o">+</span> <span class="n">log_weight</span> <span class="o">*</span> \ |
| <span class="p">(</span><span class="n">act_fn</span><span class="p">(</span><span class="o">-</span><span class="n">abs_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">),</span> <span class="n">act_type</span><span class="o">=</span><span class="s1">'softrelu'</span><span class="p">)</span> <span class="o">+</span> <span class="n">relu_fn</span><span class="p">(</span><span class="o">-</span><span class="n">pred</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">eps</span> <span class="o">=</span> <span class="mf">1e-12</span> |
| <span class="k">if</span> <span class="n">pos_weight</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="o">-</span><span class="p">(</span><span class="n">log_fn</span><span class="p">(</span><span class="n">pred</span> <span class="o">+</span> <span class="n">eps</span><span class="p">)</span> <span class="o">*</span> <span class="n">label</span> |
| <span class="o">+</span> <span class="n">log_fn</span><span class="p">(</span><span class="mf">1.</span> <span class="o">-</span> <span class="n">pred</span> <span class="o">+</span> <span class="n">eps</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="mf">1.</span> <span class="o">-</span> <span class="n">label</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="o">-</span><span class="p">(</span><span class="n">mul_fn</span><span class="p">(</span><span class="n">log_fn</span><span class="p">(</span><span class="n">pred</span> <span class="o">+</span> <span class="n">eps</span><span class="p">)</span> <span class="o">*</span> <span class="n">label</span><span class="p">,</span> <span class="n">pos_weight</span><span class="p">)</span> |
| <span class="o">+</span> <span class="n">log_fn</span><span class="p">(</span><span class="mf">1.</span> <span class="o">-</span> <span class="n">pred</span> <span class="o">+</span> <span class="n">eps</span><span class="p">)</span> <span class="o">*</span> <span class="p">(</span><span class="mf">1.</span> <span class="o">-</span> <span class="n">label</span><span class="p">))</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <span class="n">SigmoidBCELoss</span> <span class="o">=</span> <span class="n">SigmoidBinaryCrossEntropyLoss</span> |
| |
| |
| <div class="viewcode-block" id="SoftmaxCrossEntropyLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.SoftmaxCrossEntropyLoss">[docs]</a><span class="k">class</span> <span class="nc">SoftmaxCrossEntropyLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Computes the softmax cross entropy loss. (alias: SoftmaxCELoss)</span> |
| |
| <span class="sd"> If `sparse_label` is `True` (default), label should contain integer</span> |
| <span class="sd"> category indicators:</span> |
| |
| <span class="sd"> .. math::</span> |
| |
| <span class="sd"> \DeclareMathOperator{softmax}{softmax}</span> |
| |
| <span class="sd"> p = \softmax({pred})</span> |
| |
| <span class="sd"> L = -\sum_i \log p_{i,{label}_i}</span> |
| |
| <span class="sd"> `label`'s shape should be `pred`'s shape with the `axis` dimension removed.</span> |
| <span class="sd"> i.e. for `pred` with shape (1,2,3,4) and `axis = 2`, `label`'s shape should</span> |
| <span class="sd"> be (1,2,4).</span> |
| |
| <span class="sd"> If `sparse_label` is `False`, `label` should contain probability distribution</span> |
| <span class="sd"> and `label`'s shape should be the same with `pred`:</span> |
| |
| <span class="sd"> .. math::</span> |
| |
| <span class="sd"> p = \softmax({pred})</span> |
| |
| <span class="sd"> L = -\sum_i \sum_j {label}_j \log p_{ij}</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> axis : int, default -1</span> |
| <span class="sd"> The axis to sum over when computing softmax and entropy.</span> |
| <span class="sd"> sparse_label : bool, default True</span> |
| <span class="sd"> Whether label is an integer array instead of probability distribution.</span> |
| <span class="sd"> from_logits : bool, default False</span> |
| <span class="sd"> Whether input is a log probability (usually from log_softmax) instead</span> |
| <span class="sd"> of unnormalized numbers.</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: the prediction tensor, where the `batch_axis` dimension</span> |
| <span class="sd"> ranges over batch size and `axis` dimension ranges over the number</span> |
| <span class="sd"> of classes.</span> |
| <span class="sd"> - **label**: the truth tensor. When `sparse_label` is True, `label`'s</span> |
| <span class="sd"> shape should be `pred`'s shape with the `axis` dimension removed.</span> |
| <span class="sd"> i.e. for `pred` with shape (1,2,3,4) and `axis = 2`, `label`'s shape</span> |
| <span class="sd"> should be (1,2,4) and values should be integers between 0 and 2. If</span> |
| <span class="sd"> `sparse_label` is False, `label`'s shape must be the same as `pred`</span> |
| <span class="sd"> and values should be floats in the range `[0, 1]`.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">sparse_label</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">from_logits</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">SoftmaxCrossEntropyLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span> |
| <span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span> <span class="o">=</span> <span class="n">axis</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_sparse_label</span> <span class="o">=</span> <span class="n">sparse_label</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_from_logits</span> <span class="o">=</span> <span class="n">from_logits</span> |
| |
| <div class="viewcode-block" id="SoftmaxCrossEntropyLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.SoftmaxCrossEntropyLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">log_softmax_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">log_softmax</span> |
| <span class="n">pick_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">pick</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">log_softmax_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">log_softmax</span> |
| <span class="n">pick_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">pick</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_from_logits</span><span class="p">:</span> |
| <span class="n">pred</span> <span class="o">=</span> <span class="n">log_softmax_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_sparse_label</span><span class="p">:</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="o">-</span><span class="n">pick_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">,</span> <span class="n">keepdims</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="o">-</span><span class="p">(</span><span class="n">pred</span> <span class="o">*</span> <span class="n">label</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">,</span> <span class="n">keepdims</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <span class="n">SoftmaxCELoss</span> <span class="o">=</span> <span class="n">SoftmaxCrossEntropyLoss</span> |
| |
| |
| <div class="viewcode-block" id="KLDivLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.KLDivLoss">[docs]</a><span class="k">class</span> <span class="nc">KLDivLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""The Kullback-Leibler divergence loss.</span> |
| |
| <span class="sd"> KL divergence measures the distance between contiguous distributions. It</span> |
| <span class="sd"> can be used to minimize information loss when approximating a distribution.</span> |
| <span class="sd"> If `from_logits` is True (default), loss is defined as:</span> |
| |
| <span class="sd"> .. math::</span> |
| |
| <span class="sd"> L = \sum_i {label}_i * \big[\log({label}_i) - {pred}_i\big]</span> |
| |
| <span class="sd"> If `from_logits` is False, loss is defined as:</span> |
| |
| <span class="sd"> .. math::</span> |
| |
| <span class="sd"> \DeclareMathOperator{softmax}{softmax}</span> |
| |
| <span class="sd"> prob = \softmax({pred})</span> |
| |
| <span class="sd"> L = \sum_i {label}_i * \big[\log({label}_i) - \log({prob}_i)\big]</span> |
| |
| |
| <span class="sd"> `label` and `pred` can have arbitrary shape as long as they have the same</span> |
| <span class="sd"> number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> from_logits : bool, default is `True`</span> |
| <span class="sd"> Whether the input is log probability (usually from log_softmax) instead</span> |
| <span class="sd"> of unnormalized numbers.</span> |
| <span class="sd"> axis : int, default -1</span> |
| <span class="sd"> The dimension along with to compute softmax. Only used when `from_logits`</span> |
| <span class="sd"> is False.</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape. If `from_logits` is</span> |
| <span class="sd"> True, `pred` should be log probabilities. Otherwise, it should be</span> |
| <span class="sd"> unnormalized predictions, i.e. from a dense layer.</span> |
| <span class="sd"> - **label**: truth tensor with values in range `(0, 1)`. Must have</span> |
| <span class="sd"> the same size as `pred`.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| |
| |
| <span class="sd"> References</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> `Kullback-Leibler divergence</span> |
| <span class="sd"> <https://en.wikipedia.org/wiki/Kullback-Leibler_divergence>`_</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">from_logits</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">KLDivLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_from_logits</span> <span class="o">=</span> <span class="n">from_logits</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span> <span class="o">=</span> <span class="n">axis</span> |
| |
| <div class="viewcode-block" id="KLDivLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.KLDivLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">log_softmax_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">log_softmax</span> |
| <span class="n">log_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">log</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">log_softmax_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">log_softmax</span> |
| <span class="n">log_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">log</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_from_logits</span><span class="p">:</span> |
| <span class="n">pred</span> <span class="o">=</span> <span class="n">log_softmax_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">label</span> <span class="o">*</span> <span class="p">(</span><span class="n">log_fn</span><span class="p">(</span><span class="n">label</span> <span class="o">+</span> <span class="mf">1e-12</span><span class="p">)</span> <span class="o">-</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="CTCLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.CTCLoss">[docs]</a><span class="k">class</span> <span class="nc">CTCLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Connectionist Temporal Classification Loss.</span> |
| |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> layout : str, default 'NTC'</span> |
| <span class="sd"> Layout of prediction tensor. 'N', 'T', 'C' stands for batch size,</span> |
| <span class="sd"> sequence length, and alphabet_size respectively.</span> |
| <span class="sd"> label_layout : str, default 'NT'</span> |
| <span class="sd"> Layout of the labels. 'N', 'T' stands for batch size, and sequence</span> |
| <span class="sd"> length respectively.</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: unnormalized prediction tensor (before softmax).</span> |
| <span class="sd"> Its shape depends on `layout`. If `layout` is 'TNC', pred</span> |
| <span class="sd"> should have shape `(sequence_length, batch_size, alphabet_size)`.</span> |
| <span class="sd"> Note that in the last dimension, index `alphabet_size-1` is reserved</span> |
| <span class="sd"> for internal use as blank label. So `alphabet_size` is one plus the</span> |
| <span class="sd"> actual alphabet size.</span> |
| |
| <span class="sd"> - **label**: zero-based label tensor. Its shape depends on `label_layout`.</span> |
| <span class="sd"> If `label_layout` is 'TN', `label` should have shape</span> |
| <span class="sd"> `(label_sequence_length, batch_size)`.</span> |
| |
| <span class="sd"> - **pred_lengths**: optional (default None), used for specifying the</span> |
| <span class="sd"> length of each entry when different `pred` entries in the same batch</span> |
| <span class="sd"> have different lengths. `pred_lengths` should have shape `(batch_size,)`.</span> |
| |
| <span class="sd"> - **label_lengths**: optional (default None), used for specifying the</span> |
| <span class="sd"> length of each entry when different `label` entries in the same batch</span> |
| <span class="sd"> have different lengths. `label_lengths` should have shape `(batch_size,)`.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: output loss has shape `(batch_size,)`.</span> |
| |
| |
| <span class="sd"> **Example**: suppose the vocabulary is `[a, b, c]`, and in one batch we</span> |
| <span class="sd"> have three sequences 'ba', 'cbb', and 'abac'. We can index the labels as</span> |
| <span class="sd"> `{'a': 0, 'b': 1, 'c': 2, blank: 3}`. Then `alphabet_size` should be 4,</span> |
| <span class="sd"> where label 3 is reserved for internal use by `CTCLoss`. We then need to</span> |
| <span class="sd"> pad each sequence with `-1` to make a rectangular `label` tensor::</span> |
| |
| <span class="sd"> [[1, 0, -1, -1],</span> |
| <span class="sd"> [2, 1, 1, -1],</span> |
| <span class="sd"> [0, 1, 0, 2]]</span> |
| |
| |
| <span class="sd"> References</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> `Connectionist Temporal Classification: Labelling Unsegmented</span> |
| <span class="sd"> Sequence Data with Recurrent Neural Networks</span> |
| <span class="sd"> <http://www.cs.toronto.edu/~graves/icml_2006.pdf>`_</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'NTC'</span><span class="p">,</span> <span class="n">label_layout</span><span class="o">=</span><span class="s1">'NT'</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">assert</span> <span class="n">layout</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'NTC'</span><span class="p">,</span> <span class="s1">'TNC'</span><span class="p">],</span>\ |
| <span class="s2">"Only 'NTC' and 'TNC' layouts for pred are supported. Got: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">layout</span> |
| <span class="k">assert</span> <span class="n">label_layout</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'NT'</span><span class="p">,</span> <span class="s1">'TN'</span><span class="p">],</span>\ |
| <span class="s2">"Only 'NT' and 'TN' layouts for label are supported. Got: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">label_layout</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_layout</span> <span class="o">=</span> <span class="n">layout</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_label_layout</span> <span class="o">=</span> <span class="n">label_layout</span> |
| <span class="n">batch_axis</span> <span class="o">=</span> <span class="n">label_layout</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'N'</span><span class="p">)</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">CTCLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="CTCLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.CTCLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> |
| <span class="n">pred_lengths</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">label_lengths</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">swapaxes_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">swapaxes</span> |
| <span class="n">ctc_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">ctc_loss</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">swapaxes_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">swapaxes</span> |
| <span class="n">ctc_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">ctc_loss</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_layout</span> <span class="o">==</span> <span class="s1">'NTC'</span><span class="p">:</span> |
| <span class="n">pred</span> <span class="o">=</span> <span class="n">swapaxes_fn</span><span class="p">(</span><span class="n">pred</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="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">swapaxes_fn</span><span class="p">(</span><span class="n">label</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="n">loss</span> <span class="o">=</span> <span class="n">ctc_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred_lengths</span><span class="p">,</span> <span class="n">label_lengths</span><span class="p">,</span> |
| <span class="n">use_data_lengths</span><span class="o">=</span><span class="n">pred_lengths</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">use_label_lengths</span><span class="o">=</span><span class="n">label_lengths</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> |
| <span class="n">blank_label</span><span class="o">=</span><span class="s1">'last'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="HuberLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.HuberLoss">[docs]</a><span class="k">class</span> <span class="nc">HuberLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Calculates smoothed L1 loss that is equal to L1 loss if absolute error</span> |
| <span class="sd"> exceeds rho but is equal to L2 loss otherwise. Also called SmoothedL1 loss.</span> |
| |
| <span class="sd"> .. math::</span> |
| <span class="sd"> L = \sum_i \begin{cases} \frac{1}{2 {rho}} ({label}_i - {pred}_i)^2 &</span> |
| <span class="sd"> \text{ if } |{label}_i - {pred}_i| < {rho} \\</span> |
| <span class="sd"> |{label}_i - {pred}_i| - \frac{{rho}}{2} &</span> |
| <span class="sd"> \text{ otherwise }</span> |
| <span class="sd"> \end{cases}</span> |
| |
| <span class="sd"> `label` and `pred` can have arbitrary shape as long as they have the same</span> |
| <span class="sd"> number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> rho : float, default 1</span> |
| <span class="sd"> Threshold for trimmed mean estimator.</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape</span> |
| <span class="sd"> - **label**: target tensor with the same size as pred.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rho</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">HuberLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_rho</span> <span class="o">=</span> <span class="n">rho</span> |
| |
| <div class="viewcode-block" id="HuberLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.HuberLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">abs_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">abs</span> |
| <span class="n">where_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">where</span> |
| <span class="n">square_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">square</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">abs_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">abs</span> |
| <span class="n">where_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">where</span> |
| <span class="n">square_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">square</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">abs_fn</span><span class="p">(</span><span class="n">label</span> <span class="o">-</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">where_fn</span><span class="p">(</span><span class="n">loss</span> <span class="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">_rho</span><span class="p">,</span> <span class="n">loss</span> <span class="o">-</span> <span class="mf">0.5</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rho</span><span class="p">,</span> |
| <span class="p">(</span><span class="mf">0.5</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rho</span><span class="p">)</span> <span class="o">*</span> <span class="n">square_fn</span><span class="p">(</span><span class="n">loss</span><span class="p">))</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="HingeLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.HingeLoss">[docs]</a><span class="k">class</span> <span class="nc">HingeLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Calculates the hinge loss function often used in SVMs:</span> |
| |
| <span class="sd"> .. math::</span> |
| <span class="sd"> L = \sum_i max(0, {margin} - {pred}_i \cdot {label}_i)</span> |
| |
| <span class="sd"> where `pred` is the classifier prediction and `label` is the target tensor</span> |
| <span class="sd"> containing values -1 or 1. `label` and `pred` must have the same number of</span> |
| <span class="sd"> elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> margin : float</span> |
| <span class="sd"> The margin in hinge loss. Defaults to 1.0</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape.</span> |
| <span class="sd"> - **label**: truth tensor with values -1 or 1. Must have the same size</span> |
| <span class="sd"> as pred.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">margin</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">HingeLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_margin</span> <span class="o">=</span> <span class="n">margin</span> |
| |
| <div class="viewcode-block" id="HingeLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.HingeLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">relu</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">relu_fn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_margin</span> <span class="o">-</span> <span class="n">pred</span> <span class="o">*</span> <span class="n">label</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="SquaredHingeLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.SquaredHingeLoss">[docs]</a><span class="k">class</span> <span class="nc">SquaredHingeLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Calculates the soft-margin loss function used in SVMs:</span> |
| |
| <span class="sd"> .. math::</span> |
| <span class="sd"> L = \sum_i max(0, {margin} - {pred}_i \cdot {label}_i)^2</span> |
| |
| <span class="sd"> where `pred` is the classifier prediction and `label` is the target tensor</span> |
| <span class="sd"> containing values -1 or 1. `label` and `pred` can have arbitrary shape as</span> |
| <span class="sd"> long as they have the same number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> margin : float</span> |
| <span class="sd"> The margin in hinge loss. Defaults to 1.0</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape</span> |
| <span class="sd"> - **label**: truth tensor with values -1 or 1. Must have the same size</span> |
| <span class="sd"> as pred.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">margin</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">SquaredHingeLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_margin</span> <span class="o">=</span> <span class="n">margin</span> |
| |
| <div class="viewcode-block" id="SquaredHingeLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.SquaredHingeLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">square_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">square</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">square_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">square</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">square_fn</span><span class="p">(</span><span class="n">relu_fn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_margin</span> <span class="o">-</span> <span class="n">pred</span> <span class="o">*</span> <span class="n">label</span><span class="p">))</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="LogisticLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.LogisticLoss">[docs]</a><span class="k">class</span> <span class="nc">LogisticLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Calculates the logistic loss (for binary losses only):</span> |
| |
| <span class="sd"> .. math::</span> |
| <span class="sd"> L = \sum_i \log(1 + \exp(- {pred}_i \cdot {label}_i))</span> |
| |
| <span class="sd"> where `pred` is the classifier prediction and `label` is the target tensor</span> |
| <span class="sd"> containing values -1 or 1 (0 or 1 if `label_format` is binary).</span> |
| <span class="sd"> `label` and `pred` can have arbitrary shape as long as they have the same number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| <span class="sd"> label_format : str, default 'signed'</span> |
| <span class="sd"> Can be either 'signed' or 'binary'. If the label_format is 'signed', all label values should</span> |
| <span class="sd"> be either -1 or 1. If the label_format is 'binary', all label values should be either</span> |
| <span class="sd"> 0 or 1.</span> |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape.</span> |
| <span class="sd"> - **label**: truth tensor with values -1/1 (label_format is 'signed')</span> |
| <span class="sd"> or 0/1 (label_format is 'binary'). Must have the same size as pred.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,). Dimenions other than</span> |
| <span class="sd"> batch_axis are averaged out.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">label_format</span><span class="o">=</span><span class="s1">'signed'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">LogisticLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_label_format</span> <span class="o">=</span> <span class="n">label_format</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_label_format</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s2">"signed"</span><span class="p">,</span> <span class="s2">"binary"</span><span class="p">]:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"label_format can only be signed or binary, recieved </span><span class="si">%s</span><span class="s2">."</span> |
| <span class="o">%</span> <span class="n">label_format</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="LogisticLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.LogisticLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">act_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">activation</span> |
| <span class="n">abs_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">abs</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">act_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">Activation</span> |
| <span class="n">abs_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">abs</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_label_format</span> <span class="o">==</span> <span class="s1">'signed'</span><span class="p">:</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="p">(</span><span class="n">label</span> <span class="o">+</span> <span class="mf">1.0</span><span class="p">)</span> <span class="o">/</span> <span class="mf">2.0</span> <span class="c1"># Transform label to be either 0 or 1</span> |
| <span class="c1"># Use a stable formula in computation</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">relu_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">)</span> <span class="o">-</span> <span class="n">pred</span> <span class="o">*</span> <span class="n">label</span> <span class="o">+</span> \ |
| <span class="n">act_fn</span><span class="p">(</span><span class="o">-</span><span class="n">abs_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">),</span> <span class="n">act_type</span><span class="o">=</span><span class="s1">'softrelu'</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="TripletLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.TripletLoss">[docs]</a><span class="k">class</span> <span class="nc">TripletLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Calculates triplet loss given three input tensors and a positive margin.</span> |
| <span class="sd"> Triplet loss measures the relative similarity between a positive</span> |
| <span class="sd"> example, a negative example, and prediction:</span> |
| |
| <span class="sd"> .. math::</span> |
| <span class="sd"> L = \sum_i \max(\Vert {pos_i}_i - {pred} \Vert_2^2 -</span> |
| <span class="sd"> \Vert {neg_i}_i - {pred} \Vert_2^2 + {margin}, 0)</span> |
| |
| <span class="sd"> `positive`, `negative`, and 'pred' can have arbitrary shape as long as they</span> |
| <span class="sd"> have the same number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> margin : float</span> |
| <span class="sd"> Margin of separation between correct and incorrect pair.</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: prediction tensor with arbitrary shape</span> |
| <span class="sd"> - **positive**: positive example tensor with arbitrary shape. Must have</span> |
| <span class="sd"> the same size as pred.</span> |
| <span class="sd"> - **negative**: negative example tensor with arbitrary shape Must have</span> |
| <span class="sd"> the same size as pred.</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,).</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">margin</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">TripletLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_margin</span> <span class="o">=</span> <span class="n">margin</span> |
| |
| <div class="viewcode-block" id="TripletLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.TripletLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">positive</span><span class="p">,</span> <span class="n">negative</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">square_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">square</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">relu_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span> |
| <span class="n">square_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">square</span> |
| <span class="n">positive</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">positive</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">negative</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">negative</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_batch_sum</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">square_fn</span><span class="p">(</span><span class="n">positive</span> <span class="o">-</span> <span class="n">pred</span><span class="p">)</span> <span class="o">-</span> <span class="n">square_fn</span><span class="p">(</span><span class="n">negative</span> <span class="o">-</span> <span class="n">pred</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">relu_fn</span><span class="p">(</span><span class="n">loss</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">_margin</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="PoissonNLLLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.PoissonNLLLoss">[docs]</a><span class="k">class</span> <span class="nc">PoissonNLLLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""For a target (Random Variable) in a Poisson distribution, the function calculates the Negative</span> |
| <span class="sd"> Log likelihood loss.</span> |
| <span class="sd"> PoissonNLLLoss measures the loss accrued from a poisson regression prediction made by the model.</span> |
| |
| <span class="sd"> .. math::</span> |
| <span class="sd"> L = \text{pred} - \text{target} * \log(\text{pred}) +\log(\text{target!})</span> |
| |
| <span class="sd"> `target`, 'pred' can have arbitrary shape as long as they have the same number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> from_logits : boolean, default True</span> |
| <span class="sd"> indicating whether log(predicted) value has already been computed. If True, the loss is computed as</span> |
| <span class="sd"> :math:`\exp(\text{pred}) - \text{target} * \text{pred}`, and if False, then loss is computed as</span> |
| <span class="sd"> :math:`\text{pred} - \text{target} * \log(\text{pred}+\text{epsilon})`.The default value</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| <span class="sd"> compute_full: boolean, default False</span> |
| <span class="sd"> Indicates whether to add an approximation(Stirling factor) for the Factorial term in the formula for the loss.</span> |
| <span class="sd"> The Stirling factor is:</span> |
| <span class="sd"> :math:`\text{target} * \log(\text{target}) - \text{target} + 0.5 * \log(2 * \pi * \text{target})`</span> |
| <span class="sd"> epsilon: float, default 1e-08</span> |
| <span class="sd"> This is to avoid calculating log(0) which is not defined.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **pred**: Predicted value</span> |
| <span class="sd"> - **target**: Random variable(count or number) which belongs to a Poisson distribution.</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as pred. For example, if pred has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: Average loss (shape=(1,1)) of the loss tensor with shape (batch_size,).</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">from_logits</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">compute_full</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">PoissonNLLLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_from_logits</span> <span class="o">=</span> <span class="n">from_logits</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_compute_full</span> <span class="o">=</span> <span class="n">compute_full</span> |
| |
| <div class="viewcode-block" id="PoissonNLLLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.PoissonNLLLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">pred</span><span class="p">,</span> <span class="n">target</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-08</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">exp_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">exp</span> |
| <span class="n">log_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">log</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">exp_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">exp</span> |
| <span class="n">log_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">log</span> |
| <span class="n">target</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">target</span><span class="p">,</span> <span class="n">pred</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_from_logits</span><span class="p">:</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">exp_fn</span><span class="p">(</span><span class="n">pred</span><span class="p">)</span> <span class="o">-</span> <span class="n">target</span> <span class="o">*</span> <span class="n">pred</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">pred</span> <span class="o">-</span> <span class="n">target</span> <span class="o">*</span> <span class="n">log_fn</span><span class="p">(</span><span class="n">pred</span> <span class="o">+</span> <span class="n">epsilon</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compute_full</span><span class="p">:</span> |
| <span class="c1"># Using numpy's pi value</span> |
| <span class="n">stirling_factor</span> <span class="o">=</span> <span class="n">target</span> <span class="o">*</span> \ |
| <span class="n">log_fn</span><span class="p">(</span><span class="n">target</span><span class="p">)</span> <span class="o">-</span> <span class="n">target</span> <span class="o">+</span> <span class="mf">0.5</span> <span class="o">*</span> <span class="n">log_fn</span><span class="p">(</span><span class="mi">2</span> <span class="o">*</span> <span class="n">target</span> <span class="o">*</span> <span class="n">np</span><span class="o">.</span><span class="n">pi</span><span class="p">)</span> |
| <span class="n">target_gt_1</span> <span class="o">=</span> <span class="n">target</span> <span class="o">></span> <span class="mi">1</span> |
| <span class="n">stirling_factor</span> <span class="o">=</span> <span class="n">stirling_factor</span> <span class="o">*</span> <span class="n">target_gt_1</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">loss</span> <span class="o">+</span> <span class="n">stirling_factor</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="CosineEmbeddingLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.CosineEmbeddingLoss">[docs]</a><span class="k">class</span> <span class="nc">CosineEmbeddingLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""For a target label 1 or -1, vectors input1 and input2, the function computes the cosine distance</span> |
| <span class="sd"> between the vectors. This can be interpreted as how similar/dissimilar two input vectors are.</span> |
| |
| <span class="sd"> .. math::</span> |
| |
| <span class="sd"> L = \sum_i \begin{cases} 1 - {cos\_sim({input1}_i, {input2}_i)} & \text{ if } {label}_i = 1\\</span> |
| <span class="sd"> {cos\_sim({input1}_i, {input2}_i)} & \text{ if } {label}_i = -1 \end{cases}\\</span> |
| <span class="sd"> cos\_sim(input1, input2) = \frac{{input1}_i.{input2}_i}{||{input1}_i||.||{input2}_i||}</span> |
| |
| <span class="sd"> `input1`, `input2` can have arbitrary shape as long as they have the same number of elements.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| <span class="sd"> margin : float</span> |
| <span class="sd"> Margin of separation between correct and incorrect pair.</span> |
| |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **input1**: a tensor with arbitrary shape</span> |
| <span class="sd"> - **input2**: another tensor with same shape as pred to which input1 is</span> |
| <span class="sd"> compared for similarity and loss calculation</span> |
| <span class="sd"> - **label**: A 1-D tensor indicating for each pair input1 and input2, target label is 1 or -1</span> |
| <span class="sd"> - **sample_weight**: element-wise weighting tensor. Must be broadcastable</span> |
| <span class="sd"> to the same shape as input1. For example, if input1 has shape (64, 10)</span> |
| <span class="sd"> and you want to weigh each sample in the batch separately,</span> |
| <span class="sd"> sample_weight should have shape (64, 1).</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: The loss tensor with shape (batch_size,).</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">margin</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">CosineEmbeddingLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_margin</span> <span class="o">=</span> <span class="n">margin</span> |
| |
| <div class="viewcode-block" id="CosineEmbeddingLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.CosineEmbeddingLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">input1</span><span class="p">,</span> <span class="n">input2</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">sample_weight</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">where_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">where</span> |
| <span class="n">clip_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">clip</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">where_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">where</span> |
| <span class="n">clip_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">clip</span> |
| |
| <span class="n">input1</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">input1</span><span class="p">,</span> <span class="n">input2</span><span class="p">)</span> |
| <span class="n">cos_sim</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cosine_similarity</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">input1</span><span class="p">,</span> <span class="n">input2</span><span class="p">)</span> |
| <span class="n">label</span> <span class="o">=</span> <span class="n">_reshape_like</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">label</span><span class="p">,</span> <span class="n">cos_sim</span><span class="p">)</span> |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">where_fn</span><span class="p">(</span><span class="n">label</span> <span class="o">==</span> <span class="mi">1</span><span class="p">,</span> |
| <span class="mi">1</span> <span class="o">-</span> <span class="n">cos_sim</span><span class="p">,</span> |
| <span class="n">clip_fn</span><span class="p">(</span><span class="n">cos_sim</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_margin</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">_margin</span><span class="p">))</span> |
| |
| <span class="n">loss</span> <span class="o">=</span> <span class="n">_apply_weighting</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_weight</span><span class="p">,</span> <span class="n">sample_weight</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_batch_mean</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_axis</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_cosine_similarity</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">reshape_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">reshape</span> |
| <span class="n">norm_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">norm</span> |
| <span class="n">sum_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">sum</span> |
| <span class="n">full_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">full</span> |
| <span class="n">max_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">maximum</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">reshape_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">reshape</span> |
| <span class="n">norm_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">norm</span> |
| <span class="n">sum_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">sum</span> |
| <span class="n">full_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">full</span> |
| <span class="n">max_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">broadcast_maximum</span> |
| <span class="c1"># Calculates the cosine similarity between 2 vectors</span> |
| <span class="n">x_norm</span> <span class="o">=</span> <span class="n">reshape_fn</span><span class="p">(</span><span class="n">norm_fn</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="n">axis</span><span class="p">),</span> <span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span> |
| <span class="n">y_norm</span> <span class="o">=</span> <span class="n">reshape_fn</span><span class="p">(</span><span class="n">norm_fn</span><span class="p">(</span><span class="n">y</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="n">axis</span><span class="p">),</span> <span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span> |
| <span class="n">x_dot_y</span> <span class="o">=</span> <span class="n">reshape_fn</span><span class="p">(</span><span class="n">sum_fn</span><span class="p">(</span><span class="n">x</span> <span class="o">*</span> <span class="n">y</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="n">axis</span><span class="p">),</span> <span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span> |
| <span class="n">eps_arr</span> <span class="o">=</span> <span class="n">full_fn</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="mf">1e-12</span><span class="p">)</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">x_dot_y</span> <span class="o">/</span> <span class="n">max_fn</span><span class="p">(</span><span class="n">x_norm</span> <span class="o">*</span> <span class="n">y_norm</span><span class="p">,</span> <span class="n">eps_arr</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="SDMLLoss"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.SDMLLoss">[docs]</a><span class="k">class</span> <span class="nc">SDMLLoss</span><span class="p">(</span><span class="n">Loss</span><span class="p">):</span> |
| <span class="sa">r</span><span class="sd">"""Calculates Batchwise Smoothed Deep Metric Learning (SDML) Loss given two input tensors and a smoothing weight</span> |
| <span class="sd"> SDM Loss learns similarity between paired samples by using unpaired samples in the minibatch</span> |
| <span class="sd"> as potential negative examples.</span> |
| |
| <span class="sd"> The loss is described in greater detail in</span> |
| <span class="sd"> "Large Scale Question Paraphrase Retrieval with Smoothed Deep Metric Learning."</span> |
| <span class="sd"> - by Bonadiman, Daniele, Anjishnu Kumar, and Arpit Mittal. arXiv preprint arXiv:1905.12786 (2019).</span> |
| <span class="sd"> URL: https://arxiv.org/pdf/1905.12786.pdf</span> |
| |
| <span class="sd"> According to the authors, this loss formulation achieves comparable or higher accuracy to</span> |
| <span class="sd"> Triplet Loss but converges much faster.</span> |
| <span class="sd"> The loss assumes that the items in both tensors in each minibatch</span> |
| <span class="sd"> are aligned such that x1[0] corresponds to x2[0] and all other datapoints in the minibatch are unrelated.</span> |
| <span class="sd"> `x1` and `x2` are minibatches of vectors.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> smoothing_parameter : float</span> |
| <span class="sd"> Probability mass to be distributed over the minibatch. Must be < 1.0.</span> |
| <span class="sd"> weight : float or None</span> |
| <span class="sd"> Global scalar weight for loss.</span> |
| <span class="sd"> batch_axis : int, default 0</span> |
| <span class="sd"> The axis that represents mini-batch.</span> |
| |
| <span class="sd"> Inputs:</span> |
| <span class="sd"> - **x1**: Minibatch of data points with shape (batch_size, vector_dim)</span> |
| <span class="sd"> - **x2**: Minibatch of data points with shape (batch_size, vector_dim)</span> |
| <span class="sd"> Each item in x2 is a positive sample for the same index in x1.</span> |
| <span class="sd"> That is, x1[0] and x2[0] form a positive pair, x1[1] and x2[1] form a positive pair - and so on.</span> |
| <span class="sd"> All data points in different rows should be decorrelated</span> |
| |
| <span class="sd"> Outputs:</span> |
| <span class="sd"> - **loss**: loss tensor with shape (batch_size,).</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">smoothing_parameter</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">weight</span><span class="o">=</span><span class="mf">1.</span><span class="p">,</span> <span class="n">batch_axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">SDMLLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">weight</span><span class="p">,</span> <span class="n">batch_axis</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">kl_loss</span> <span class="o">=</span> <span class="n">KLDivLoss</span><span class="p">(</span><span class="n">from_logits</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="c1"># Smoothing probability mass</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">smoothing_parameter</span> <span class="o">=</span> <span class="n">smoothing_parameter</span> |
| |
| <span class="k">def</span> <span class="nf">_compute_distances</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x1</span><span class="p">,</span> <span class="n">x2</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> This function computes the euclidean distance between every vector</span> |
| <span class="sd"> in the two batches in input.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">expand_dims_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">expand_dims</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">expand_dims_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">expand_dims</span> |
| |
| <span class="c1"># expanding x1 form [batch_size, dim] to [batch_size, 1, dim]</span> |
| <span class="c1"># and x2 to [1, batch_size, dim]</span> |
| <span class="n">x1_</span> <span class="o">=</span> <span class="n">expand_dims_fn</span><span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="n">x2_</span> <span class="o">=</span> <span class="n">expand_dims_fn</span><span class="p">(</span><span class="n">x2</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
| <span class="c1"># pointwise squared differences</span> |
| <span class="n">squared_diffs</span> <span class="o">=</span> <span class="p">(</span><span class="n">x1_</span> <span class="o">-</span> <span class="n">x2_</span><span class="p">)</span><span class="o">**</span><span class="mi">2</span> |
| <span class="c1"># sum of squared differences distance</span> |
| <span class="k">return</span> <span class="n">squared_diffs</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_compute_labels</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> The function creates the label matrix for the loss.</span> |
| <span class="sd"> It is an identity matrix of size [BATCH_SIZE x BATCH_SIZE]</span> |
| <span class="sd"> labels:</span> |
| <span class="sd"> [[1, 0]</span> |
| <span class="sd"> [0, 1]]</span> |
| |
| <span class="sd"> after the proces the labels are smoothed by a small amount to</span> |
| <span class="sd"> account for errors.</span> |
| |
| <span class="sd"> labels:</span> |
| <span class="sd"> [[0.9, 0.1]</span> |
| <span class="sd"> [0.1, 0.9]]</span> |
| |
| |
| <span class="sd"> Pereyra, Gabriel, et al. "Regularizing neural networks by penalizing</span> |
| <span class="sd"> confident output distributions." arXiv preprint arXiv:1701.06548 (2017).</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">gold</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">eye</span><span class="p">(</span><span class="n">batch_size</span><span class="p">)</span> |
| <span class="n">labels</span> <span class="o">=</span> <span class="n">gold</span> <span class="o">*</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">smoothing_parameter</span><span class="p">)</span> <span class="o">+</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="n">gold</span><span class="p">)</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">smoothing_parameter</span> <span class="o">/</span> <span class="p">(</span><span class="n">batch_size</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">labels</span> |
| |
| <div class="viewcode-block" id="SDMLLoss.hybrid_forward"><a class="viewcode-back" href="../../../api/gluon/loss/index.html#mxnet.gluon.loss.SDMLLoss.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x1</span><span class="p">,</span> <span class="n">x2</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> the function computes the kl divergence between the negative distances</span> |
| <span class="sd"> (internally it compute a softmax casting into probabilities) and the</span> |
| <span class="sd"> identity matrix.</span> |
| |
| <span class="sd"> This assumes that the two batches are aligned therefore the more similar</span> |
| <span class="sd"> vector should be the one having the same id.</span> |
| |
| <span class="sd"> Batch1 Batch2</span> |
| |
| <span class="sd"> President of France French President</span> |
| <span class="sd"> President of US American President</span> |
| |
| <span class="sd"> Given the question president of France in batch 1 the model will</span> |
| <span class="sd"> learn to predict french president comparing it with all the other</span> |
| <span class="sd"> vectors in batch 2</span> |
| <span class="sd"> """</span> |
| <span class="k">assert</span> <span class="n">F</span> <span class="ow">is</span> <span class="n">ndarray</span><span class="p">,</span> <span class="s1">'SDMLLoss does not support symbolic '</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">log_softmax_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">log_softmax</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">log_softmax_fn</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">log_softmax</span> |
| <span class="n">batch_size</span> <span class="o">=</span> <span class="n">x1</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">labels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compute_labels</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">)</span> |
| <span class="n">distances</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compute_distances</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">x1</span><span class="p">,</span> <span class="n">x2</span><span class="p">)</span> |
| <span class="n">log_probabilities</span> <span class="o">=</span> <span class="n">log_softmax_fn</span><span class="p">(</span><span class="o">-</span><span class="n">distances</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> |
| <span class="c1"># multiply for the number of labels to obtain the correct loss (gluon kl_loss averages instead of sum)</span> |
| <span class="c1"># PR#18423:multiply for the number of labels should multiply x1.shape[1] rather than x1.shape[0])</span> |
| <span class="c1"># After PR#18423, it is no need to multiply it anymore.</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">kl_loss</span><span class="p">(</span><span class="n">log_probabilities</span><span class="p">,</span> <span class="n">labels</span><span class="o">.</span><span class="n">as_in_context</span><span class="p">(</span><span class="n">distances</span><span class="o">.</span><span class="n">context</span><span class="p">))</span></div></div> |
| </pre></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"> |
| </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/incubator-mxnet/issues">Github Issues</a></li> |
| <li><a href="https://github.com/apache/incubator-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/incubator-mxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#github"></use></svg> <span class="username">apache/incubator-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 The Apache Software Foundation (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> |