| <!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.contrib.quantization — Apache MXNet documentation</title> |
| |
| <link rel="stylesheet" href="../../../_static/basic.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/mxnet.css" /> |
| <link rel="stylesheet" href="../../../_static/material-design-lite-1.3.0/material.blue-deep_orange.min.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/sphinx_materialdesign_theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/fontawesome/all.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/fonts.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/feedback.css" type="text/css" /> |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/matomo_analytics.js"></script> |
| <script src="../../../_static/autodoc.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "document", "processClass": "math|output_area"}})</script> |
| <script src="../../../_static/sphinx_materialdesign_theme.js"></script> |
| <link rel="shortcut icon" href="../../../_static/mxnet-icon.png"/> |
| <link rel="index" title="Index" href="../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| </head> |
| <body><header class="site-header" role="banner"> |
| <div class="wrapper"> |
| <a class="site-title" rel="author" href="/"><img |
| src="../../../_static/mxnet_logo.png" class="site-header-logo"></a> |
| <nav class="site-nav"> |
| <input type="checkbox" id="nav-trigger" class="nav-trigger"/> |
| <label for="nav-trigger"> |
| <span class="menu-icon"> |
| <svg viewBox="0 0 18 15" width="18px" height="15px"> |
| <path d="M18,1.484c0,0.82-0.665,1.484-1.484,1.484H1.484C0.665,2.969,0,2.304,0,1.484l0,0C0,0.665,0.665,0,1.484,0 h15.032C17.335,0,18,0.665,18,1.484L18,1.484z M18,7.516C18,8.335,17.335,9,16.516,9H1.484C0.665,9,0,8.335,0,7.516l0,0 c0-0.82,0.665-1.484,1.484-1.484h15.032C17.335,6.031,18,6.696,18,7.516L18,7.516z M18,13.516C18,14.335,17.335,15,16.516,15H1.484 C0.665,15,0,14.335,0,13.516l0,0c0-0.82,0.665-1.483,1.484-1.483h15.032C17.335,12.031,18,12.695,18,13.516L18,13.516z"/> |
| </svg> |
| </span> |
| </label> |
| |
| <div class="trigger"> |
| <a class="page-link" href="/get_started">Get Started</a> |
| <a class="page-link" href="/features">Features</a> |
| <a class="page-link" href="/ecosystem">Ecosystem</a> |
| <a class="page-link page-current" href="/api">Docs & Tutorials</a> |
| <a class="page-link" href="/trusted_by">Trusted By</a> |
| <a class="page-link" href="https://github.com/apache/mxnet">GitHub</a> |
| <div class="dropdown" style="min-width:100px"> |
| <span class="dropdown-header">Apache |
| <svg class="dropdown-caret" viewBox="0 0 32 32" class="icon icon-caret-bottom" aria-hidden="true"><path class="dropdown-caret-path" d="M24 11.305l-7.997 11.39L8 11.305z"></path></svg> |
| </span> |
| <div class="dropdown-content" style="min-width:250px"> |
| <a href="https://www.apache.org/foundation/">Apache Software Foundation</a> |
| <a href="https://incubator.apache.org/">Apache Incubator</a> |
| <a href="https://www.apache.org/licenses/">License</a> |
| <a href="/versions/1.9.1/api/faq/security.html">Security</a> |
| <a href="https://privacy.apache.org/policies/privacy-policy-public.html">Privacy</a> |
| <a href="https://www.apache.org/events/current-event">Events</a> |
| <a href="https://www.apache.org/foundation/sponsorship.html">Sponsorship</a> |
| <a href="https://www.apache.org/foundation/thanks.html">Thanks</a> |
| </div> |
| </div> |
| <div class="dropdown"> |
| <span class="dropdown-header">master |
| <svg class="dropdown-caret" viewBox="0 0 32 32" class="icon icon-caret-bottom" aria-hidden="true"><path class="dropdown-caret-path" d="M24 11.305l-7.997 11.39L8 11.305z"></path></svg> |
| </span> |
| <div class="dropdown-content"> |
| <a class="dropdown-option-active" href="/versions/master/">master</a><br> |
| <a class="dropdown-option" href="/versions/1.9.1/">1.9.1</a><br> |
| <a class="dropdown-option" href="/versions/1.8.0/">1.8.0</a><br> |
| <a class="dropdown-option" href="/versions/1.7.0/">1.7.0</a><br> |
| <a class="dropdown-option" href="/versions/1.6.0/">1.6.0</a><br> |
| <a class="dropdown-option" href="/versions/1.5.0/">1.5.0</a><br> |
| <a class="dropdown-option" href="/versions/1.4.1/">1.4.1</a><br> |
| <a class="dropdown-option" href="/versions/1.3.1/">1.3.1</a><br> |
| <a class="dropdown-option" href="/versions/1.2.1/">1.2.1</a><br> |
| <a class="dropdown-option" href="/versions/1.1.0/">1.1.0</a><br> |
| <a class="dropdown-option" href="/versions/1.0.0/">1.0.0</a><br> |
| <a class="dropdown-option" href="/versions/0.12.1/">0.12.1</a><br> |
| <a class="dropdown-option" href="/versions/0.11.0/">0.11.0</a> |
| </div> |
| </div> |
| </div> |
| </nav> |
| </div> |
| </header> |
| <div class="mdl-layout mdl-js-layout mdl-layout--fixed-header mdl-layout--fixed-drawer"><header class="mdl-layout__header mdl-layout__header--waterfall "> |
| <div class="mdl-layout__header-row"> |
| |
| <nav class="mdl-navigation breadcrumb"> |
| <a class="mdl-navigation__link" href="../../index.html">Module code</a><i class="material-icons">navigate_next</i> |
| <a class="mdl-navigation__link is-active">mxnet.contrib.quantization</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/contrib/quantization" 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">Crash Course</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/0-introduction.html">Introduction</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/1-nparray.html">Step 1: Manipulate data with NP on MXNet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/2-create-nn.html">Step 2: Create a neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/3-autograd.html">Step 3: Automatic differentiation with autograd</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/4-components.html">Step 4: Necessary components that are not in the network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html">Step 5: <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#Using-your-own-data-with-custom-Datasets">Using your own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#New-in-MXNet-2.0:-faster-C++-backend-dataloaders">New in MXNet 2.0: faster C++ backend dataloaders</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/6-train-nn.html">Step 6: Train a Neural Network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/7-use-gpus.html">Step 7: Load and Run a NN using GPU</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/index.html">Moving to MXNet from Other Frameworks</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/pytorch.html">PyTorch vs Apache MXNet</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_from_experiment_to_deployment.html">Gluon: from experiment to deployment</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_migration_guide.html">Gluon2.0: Migration Guide</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/logistic_regression_explained.html">Logistic regression explained</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/image/mnist.html">MNIST</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/packages/index.html">Packages</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/autograd/index.html">Automatic Differentiation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/gluon/index.html">Gluon</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/index.html">Blocks</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/custom-layer.html">Custom Layers</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/hybridize.html">Hybridize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/init.html">Initialization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/naming.html">Parameter and Block Naming</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/nn.html">Layers and Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/parameters.html">Parameter Management</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/activations/activations.html">Activation Blocks</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/data/index.html">Data Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html">Image Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html">Gluon <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-custom-Datasets">Using own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Appendix:-Upgrading-from-Module-DataIter-to-Gluon-DataLoader">Appendix: Upgrading from Module <code class="docutils literal notranslate"><span class="pre">DataIter</span></code> to Gluon <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/image/index.html">Image Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/info_gan.html">Image similarity search with InfoGAN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/mnist.html">Handwritten Digit Recognition</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/index.html">Losses</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/custom-loss.html">Custom Loss Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/kl_divergence.html">Kullback-Leibler (KL) Divergence</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/loss.html">Loss functions</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/text/index.html">Text Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/gnmt.html">Google Neural Machine Translation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/transformer.html">Machine Translation with Transformer</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/training/index.html">Training</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/fit_api_tutorial.html">MXNet Gluon Fit API</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/trainer.html">Trainer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/index.html">Learning Rates</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_finder.html">Learning Rate Finder</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules.html">Learning Rate Schedules</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules_advanced.html">Advanced Learning Rate Schedules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/normalization/index.html">Normalization Blocks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/kvstore/index.html">KVStore</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/kvstore/kvstore.html">Distributed Key-Value Store</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/legacy/index.html">Legacy</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/index.html">NDArray</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/01-ndarray-intro.html">An Intro: Manipulate Data the MXNet Way with NDArray</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/02-ndarray-operations.html">NDArray Operations</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/03-ndarray-contexts.html">NDArray Contexts</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/gotchas_numpy_in_mxnet.html">Gotchas using NumPy in Apache MXNet</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/index.html">Tutorials</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/csr.html">CSRNDArray - NDArray in Compressed Sparse Row Storage Format</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/row_sparse.html">RowSparseNDArray - NDArray for Sparse Gradient Updates</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/np/index.html">What is NP on MXNet</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/np/cheat-sheet.html">The NP on MXNet cheat sheet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/np/np-vs-numpy.html">Differences between NP on MXNet and NumPy</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/onnx/index.html">ONNX</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/fine_tuning_gluon.html">Fine-tuning an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/inference_on_onnx_model.html">Running inference on MXNet/Gluon from an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html">Export ONNX Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/optimizer/index.html">Optimizers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/viz/index.html">Visualization</a><ul> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/visualize_graph">Visualize networks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/performance/index.html">Performance</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/compression/index.html">Compression</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/compression/int8.html">Deploy with int-8</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/float16">Float16</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/gradient_compression">Gradient Compression</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html">GluonCV with Quantized Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/backend/index.html">Accelerated Backend Tools</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/index.html">oneDNN</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_readme.html">Install MXNet with oneDNN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_quantization.html">oneDNN Quantization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_quantization_inc.html">Improving accuracy with Intel® Neural Compressor</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tvm.html">Use TVM</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/profiler.html">Profiling MXNet Models</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/amp.html">Using AMP: Automatic Mixed Precision</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/deploy/index.html">Deployment</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/export/index.html">Export</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/export/onnx.html">Exporting to ONNX format</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/export_network.html">Export Gluon CV Models</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Save / Load Parameters</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/inference/index.html">Inference</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/cpp.html">Deploy into C++</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/image_classification_jetson.html">Image Classication using pretrained ResNet-50 model on Jetson module</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/index.html">Run on AWS</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_ec2.html">Run on an EC2 Instance</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_sagemaker.html">Run on Amazon SageMaker</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/cloud.html">MXNet on the Cloud</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/extend/index.html">Extend</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/extend/customop.html">Custom Numpy Operators</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/new_op">New Operator Creation</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/add_op_in_backend">New Operator in MXNet Backend</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/using_rtc">Using RTC for CUDA kernels</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><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></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.rollaxis.html">mxnet.np.rollaxis</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.atleast_1d.html">mxnet.np.atleast_1d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.atleast_2d.html">mxnet.np.atleast_2d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.atleast_3d.html">mxnet.np.atleast_3d</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.column_stack.html">mxnet.np.column_stack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.hstack.html">mxnet.np.hstack</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.array_split.html">mxnet.np.array_split</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.dsplit.html">mxnet.np.dsplit</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.delete.html">mxnet.np.delete</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.insert.html">mxnet.np.insert</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.append.html">mxnet.np.append</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.resize.html">mxnet.np.resize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.trim_zeros.html">mxnet.np.trim_zeros</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> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fliplr.html">mxnet.np.fliplr</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.flipud.html">mxnet.np.flipud</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> |
| <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.set_printoptions.html">mxnet.np.set_printoptions</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.multi_dot.html">mxnet.np.linalg.multi_dot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.matmul.html">mxnet.np.matmul</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.matrix_power.html">mxnet.np.linalg.matrix_power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.kron.html">mxnet.np.kron</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.cholesky.html">mxnet.np.linalg.cholesky</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.qr.html">mxnet.np.linalg.qr</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.eig.html">mxnet.np.linalg.eig</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.eigh.html">mxnet.np.linalg.eigh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.eigvals.html">mxnet.np.linalg.eigvals</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.eigvalsh.html">mxnet.np.linalg.eigvalsh</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> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.cond.html">mxnet.np.linalg.cond</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.det.html">mxnet.np.linalg.det</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.matrix_rank.html">mxnet.np.linalg.matrix_rank</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.slogdet.html">mxnet.np.linalg.slogdet</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.solve.html">mxnet.np.linalg.solve</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.tensorsolve.html">mxnet.np.linalg.tensorsolve</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.lstsq.html">mxnet.np.linalg.lstsq</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.inv.html">mxnet.np.linalg.inv</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.pinv.html">mxnet.np.linalg.pinv</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.tensorinv.html">mxnet.np.linalg.tensorinv</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.unwrap.html">mxnet.np.unwrap</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.round_.html">mxnet.np.round_</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.nanprod.html">mxnet.np.nanprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nansum.html">mxnet.np.nansum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cumprod.html">mxnet.np.cumprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nancumprod.html">mxnet.np.nancumprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nancumsum.html">mxnet.np.nancumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.diff.html">mxnet.np.diff</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ediff1d.html">mxnet.np.ediff1d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cross.html">mxnet.np.cross</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.trapz.html">mxnet.np.trapz</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.logaddexp.html">mxnet.np.logaddexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.i0.html">mxnet.np.i0</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.signbit.html">mxnet.np.signbit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.copysign.html">mxnet.np.copysign</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.frexp.html">mxnet.np.frexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.spacing.html">mxnet.np.spacing</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.gcd.html">mxnet.np.gcd</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.positive.html">mxnet.np.positive</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.float_power.html">mxnet.np.float_power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fmod.html">mxnet.np.fmod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.modf.html">mxnet.np.modf</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.divmod.html">mxnet.np.divmod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.floor_divide.html">mxnet.np.floor_divide</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> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fabs.html">mxnet.np.fabs</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.heaviside.html">mxnet.np.heaviside</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fmax.html">mxnet.np.fmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fmin.html">mxnet.np.fmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nan_to_num.html">mxnet.np.nan_to_num</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.interp.html">mxnet.np.interp</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/random/index.html">np.random</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.choice.html">mxnet.np.random.choice</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.shuffle.html">mxnet.np.random.shuffle</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.normal.html">mxnet.np.random.normal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.uniform.html">mxnet.np.random.uniform</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.rand.html">mxnet.np.random.rand</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.randint.html">mxnet.np.random.randint</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.beta.html">mxnet.np.random.beta</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.chisquare.html">mxnet.np.random.chisquare</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.exponential.html">mxnet.np.random.exponential</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.f.html">mxnet.np.random.f</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.gamma.html">mxnet.np.random.gamma</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.gumbel.html">mxnet.np.random.gumbel</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.laplace.html">mxnet.np.random.laplace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.logistic.html">mxnet.np.random.logistic</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.lognormal.html">mxnet.np.random.lognormal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.multinomial.html">mxnet.np.random.multinomial</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.multivariate_normal.html">mxnet.np.random.multivariate_normal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.pareto.html">mxnet.np.random.pareto</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.power.html">mxnet.np.random.power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.rayleigh.html">mxnet.np.random.rayleigh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.weibull.html">mxnet.np.random.weibull</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../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.ndarray.sort.html">mxnet.np.ndarray.sort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sort.html">mxnet.np.sort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.lexsort.html">mxnet.np.lexsort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argsort.html">mxnet.np.argsort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.msort.html">mxnet.np.msort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.partition.html">mxnet.np.partition</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argpartition.html">mxnet.np.argpartition</a></li> |
| <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> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanargmax.html">mxnet.np.nanargmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanargmin.html">mxnet.np.nanargmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argwhere.html">mxnet.np.argwhere</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nonzero.html">mxnet.np.nonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.flatnonzero.html">mxnet.np.flatnonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.where.html">mxnet.np.where</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.searchsorted.html">mxnet.np.searchsorted</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.extract.html">mxnet.np.extract</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.count_nonzero.html">mxnet.np.count_nonzero</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.amin.html">mxnet.np.amin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.amax.html">mxnet.np.amax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanmin.html">mxnet.np.nanmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanmax.html">mxnet.np.nanmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ptp.html">mxnet.np.ptp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.percentile.html">mxnet.np.percentile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanpercentile.html">mxnet.np.nanpercentile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.quantile.html">mxnet.np.quantile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanquantile.html">mxnet.np.nanquantile</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.median.html">mxnet.np.median</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.average.html">mxnet.np.average</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanmedian.html">mxnet.np.nanmedian</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanstd.html">mxnet.np.nanstd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanvar.html">mxnet.np.nanvar</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.corrcoef.html">mxnet.np.corrcoef</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.correlate.html">mxnet.np.correlate</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cov.html">mxnet.np.cov</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogram.html">mxnet.np.histogram</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogram2d.html">mxnet.np.histogram2d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogramdd.html">mxnet.np.histogramdd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.bincount.html">mxnet.np.bincount</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogram_bin_edges.html">mxnet.np.histogram_bin_edges</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.digitize.html">mxnet.np.digitize</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../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_device.html">mxnet.npx.current_device</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.relu.html">mxnet.npx.relu</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.log_softmax.html">mxnet.npx.log_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/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">KVStore: Communication for Distributed Training</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore/index.html#horovod">Horovod</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.Horovod.html">mxnet.kvstore.Horovod</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore/index.html#byteps">BytePS</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.BytePS.html">mxnet.kvstore.BytePS</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore/index.html#kvstore-interface">KVStore Interface</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.KVStore.html">mxnet.kvstore.KVStore</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.KVStoreBase.html">mxnet.kvstore.KVStoreBase</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.KVStoreServer.html">mxnet.kvstore.KVStoreServer</a></li> |
| </ul> |
| </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/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/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/device/index.html">mxnet.device</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><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/runtime/generated/mxnet.runtime.Feature.html">mxnet.runtime.Feature</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/runtime/generated/mxnet.runtime.Features.html">mxnet.runtime.Features</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/runtime/generated/mxnet.runtime.feature_list.html">mxnet.runtime.feature_list</a></li> |
| </ul> |
| </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">Crash Course</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/0-introduction.html">Introduction</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/1-nparray.html">Step 1: Manipulate data with NP on MXNet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/2-create-nn.html">Step 2: Create a neural network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/3-autograd.html">Step 3: Automatic differentiation with autograd</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/4-components.html">Step 4: Necessary components that are not in the network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html">Step 5: <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#Using-your-own-data-with-custom-Datasets">Using your own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/5-datasets.html#New-in-MXNet-2.0:-faster-C++-backend-dataloaders">New in MXNet 2.0: faster C++ backend dataloaders</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/6-train-nn.html">Step 6: Train a Neural Network</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/crash-course/7-use-gpus.html">Step 7: Load and Run a NN using GPU</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/index.html">Moving to MXNet from Other Frameworks</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/getting-started/to-mxnet/pytorch.html">PyTorch vs Apache MXNet</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_from_experiment_to_deployment.html">Gluon: from experiment to deployment</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/gluon_migration_guide.html">Gluon2.0: Migration Guide</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/getting-started/logistic_regression_explained.html">Logistic regression explained</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/image/mnist.html">MNIST</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/packages/index.html">Packages</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/autograd/index.html">Automatic Differentiation</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/gluon/index.html">Gluon</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/index.html">Blocks</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/custom-layer.html">Custom Layers</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/hybridize.html">Hybridize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/init.html">Initialization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/naming.html">Parameter and Block Naming</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/nn.html">Layers and Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/parameters.html">Parameter Management</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/blocks/activations/activations.html">Activation Blocks</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/data/index.html">Data Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/data_augmentation.html">Image Augmentation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html">Gluon <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-custom-Datasets">Using own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/data/datasets.html#Appendix:-Upgrading-from-Module-DataIter-to-Gluon-DataLoader">Appendix: Upgrading from Module <code class="docutils literal notranslate"><span class="pre">DataIter</span></code> to Gluon <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/image/index.html">Image Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/info_gan.html">Image similarity search with InfoGAN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/image/mnist.html">Handwritten Digit Recognition</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/index.html">Losses</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/custom-loss.html">Custom Loss Blocks</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/kl_divergence.html">Kullback-Leibler (KL) Divergence</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/loss/loss.html">Loss functions</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/text/index.html">Text Tutorials</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/gnmt.html">Google Neural Machine Translation</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/text/transformer.html">Machine Translation with Transformer</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/gluon/training/index.html">Training</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/fit_api_tutorial.html">MXNet Gluon Fit API</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/trainer.html">Trainer</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/index.html">Learning Rates</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_finder.html">Learning Rate Finder</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules.html">Learning Rate Schedules</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/gluon/training/learning_rates/learning_rate_schedules_advanced.html">Advanced Learning Rate Schedules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/gluon/training/normalization/index.html">Normalization Blocks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/kvstore/index.html">KVStore</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/kvstore/kvstore.html">Distributed Key-Value Store</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/legacy/index.html">Legacy</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/index.html">NDArray</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/01-ndarray-intro.html">An Intro: Manipulate Data the MXNet Way with NDArray</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/02-ndarray-operations.html">NDArray Operations</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/03-ndarray-contexts.html">NDArray Contexts</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/gotchas_numpy_in_mxnet.html">Gotchas using NumPy in Apache MXNet</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/index.html">Tutorials</a><ul> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/csr.html">CSRNDArray - NDArray in Compressed Sparse Row Storage Format</a></li> |
| <li class="toctree-l6"><a class="reference internal" href="../../../tutorials/packages/legacy/ndarray/sparse/row_sparse.html">RowSparseNDArray - NDArray for Sparse Gradient Updates</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/np/index.html">What is NP on MXNet</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/np/cheat-sheet.html">The NP on MXNet cheat sheet</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/np/np-vs-numpy.html">Differences between NP on MXNet and NumPy</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/onnx/index.html">ONNX</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/fine_tuning_gluon.html">Fine-tuning an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/packages/onnx/inference_on_onnx_model.html">Running inference on MXNet/Gluon from an ONNX model</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html">Export ONNX Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/optimizer/index.html">Optimizers</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/packages/viz/index.html">Visualization</a><ul> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/visualize_graph">Visualize networks</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/performance/index.html">Performance</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/compression/index.html">Compression</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/compression/int8.html">Deploy with int-8</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/float16">Float16</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/gradient_compression">Gradient Compression</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html">GluonCV with Quantized Models</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/performance/backend/index.html">Accelerated Backend Tools</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/index.html">oneDNN</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_readme.html">Install MXNet with oneDNN</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_quantization.html">oneDNN Quantization</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../tutorials/performance/backend/dnnl/dnnl_quantization_inc.html">Improving accuracy with Intel® Neural Compressor</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/tvm.html">Use TVM</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/profiler.html">Profiling MXNet Models</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/performance/backend/amp.html">Using AMP: Automatic Mixed Precision</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/deploy/index.html">Deployment</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/export/index.html">Export</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/export/onnx.html">Exporting to ONNX format</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/export_network.html">Export Gluon CV Models</a></li> |
| <li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/blocks/save_load_params.html">Save / Load Parameters</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/inference/index.html">Inference</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/cpp.html">Deploy into C++</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/inference/image_classification_jetson.html">Image Classication using pretrained ResNet-50 model on Jetson module</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/index.html">Run on AWS</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_ec2.html">Run on an EC2 Instance</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/use_sagemaker.html">Run on Amazon SageMaker</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../tutorials/deploy/run-on-aws/cloud.html">MXNet on the Cloud</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../tutorials/extend/index.html">Extend</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../tutorials/extend/customop.html">Custom Numpy Operators</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/new_op">New Operator Creation</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/add_op_in_backend">New Operator in MXNet Backend</a></li> |
| <li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/faq/using_rtc">Using RTC for CUDA kernels</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><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></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.rollaxis.html">mxnet.np.rollaxis</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.atleast_1d.html">mxnet.np.atleast_1d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.atleast_2d.html">mxnet.np.atleast_2d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.atleast_3d.html">mxnet.np.atleast_3d</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.column_stack.html">mxnet.np.column_stack</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.hstack.html">mxnet.np.hstack</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.array_split.html">mxnet.np.array_split</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.dsplit.html">mxnet.np.dsplit</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.delete.html">mxnet.np.delete</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.insert.html">mxnet.np.insert</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.append.html">mxnet.np.append</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.resize.html">mxnet.np.resize</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.trim_zeros.html">mxnet.np.trim_zeros</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> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fliplr.html">mxnet.np.fliplr</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.flipud.html">mxnet.np.flipud</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> |
| <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.set_printoptions.html">mxnet.np.set_printoptions</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.multi_dot.html">mxnet.np.linalg.multi_dot</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.matmul.html">mxnet.np.matmul</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.matrix_power.html">mxnet.np.linalg.matrix_power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.kron.html">mxnet.np.kron</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.cholesky.html">mxnet.np.linalg.cholesky</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.qr.html">mxnet.np.linalg.qr</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.eig.html">mxnet.np.linalg.eig</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.eigh.html">mxnet.np.linalg.eigh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.eigvals.html">mxnet.np.linalg.eigvals</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.eigvalsh.html">mxnet.np.linalg.eigvalsh</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> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.cond.html">mxnet.np.linalg.cond</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.det.html">mxnet.np.linalg.det</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.matrix_rank.html">mxnet.np.linalg.matrix_rank</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.slogdet.html">mxnet.np.linalg.slogdet</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.solve.html">mxnet.np.linalg.solve</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.tensorsolve.html">mxnet.np.linalg.tensorsolve</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.lstsq.html">mxnet.np.linalg.lstsq</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.inv.html">mxnet.np.linalg.inv</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.pinv.html">mxnet.np.linalg.pinv</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.linalg.tensorinv.html">mxnet.np.linalg.tensorinv</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.unwrap.html">mxnet.np.unwrap</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.round_.html">mxnet.np.round_</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.nanprod.html">mxnet.np.nanprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nansum.html">mxnet.np.nansum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cumprod.html">mxnet.np.cumprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nancumprod.html">mxnet.np.nancumprod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nancumsum.html">mxnet.np.nancumsum</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.diff.html">mxnet.np.diff</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ediff1d.html">mxnet.np.ediff1d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cross.html">mxnet.np.cross</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.trapz.html">mxnet.np.trapz</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.logaddexp.html">mxnet.np.logaddexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.i0.html">mxnet.np.i0</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.signbit.html">mxnet.np.signbit</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.copysign.html">mxnet.np.copysign</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.frexp.html">mxnet.np.frexp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.spacing.html">mxnet.np.spacing</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.gcd.html">mxnet.np.gcd</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.positive.html">mxnet.np.positive</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.float_power.html">mxnet.np.float_power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fmod.html">mxnet.np.fmod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.modf.html">mxnet.np.modf</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.divmod.html">mxnet.np.divmod</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.floor_divide.html">mxnet.np.floor_divide</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> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fabs.html">mxnet.np.fabs</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.heaviside.html">mxnet.np.heaviside</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fmax.html">mxnet.np.fmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.fmin.html">mxnet.np.fmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nan_to_num.html">mxnet.np.nan_to_num</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.interp.html">mxnet.np.interp</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../api/np/random/index.html">np.random</a><ul> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.choice.html">mxnet.np.random.choice</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.shuffle.html">mxnet.np.random.shuffle</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.normal.html">mxnet.np.random.normal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.uniform.html">mxnet.np.random.uniform</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.rand.html">mxnet.np.random.rand</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.randint.html">mxnet.np.random.randint</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.beta.html">mxnet.np.random.beta</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.chisquare.html">mxnet.np.random.chisquare</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.exponential.html">mxnet.np.random.exponential</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.f.html">mxnet.np.random.f</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.gamma.html">mxnet.np.random.gamma</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.gumbel.html">mxnet.np.random.gumbel</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.laplace.html">mxnet.np.random.laplace</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.logistic.html">mxnet.np.random.logistic</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.lognormal.html">mxnet.np.random.lognormal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.multinomial.html">mxnet.np.random.multinomial</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.multivariate_normal.html">mxnet.np.random.multivariate_normal</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.pareto.html">mxnet.np.random.pareto</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.power.html">mxnet.np.random.power</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.rayleigh.html">mxnet.np.random.rayleigh</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/random/generated/mxnet.np.random.weibull.html">mxnet.np.random.weibull</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../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.ndarray.sort.html">mxnet.np.ndarray.sort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.sort.html">mxnet.np.sort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.lexsort.html">mxnet.np.lexsort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argsort.html">mxnet.np.argsort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.msort.html">mxnet.np.msort</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.partition.html">mxnet.np.partition</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argpartition.html">mxnet.np.argpartition</a></li> |
| <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> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanargmax.html">mxnet.np.nanargmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanargmin.html">mxnet.np.nanargmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.argwhere.html">mxnet.np.argwhere</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nonzero.html">mxnet.np.nonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.flatnonzero.html">mxnet.np.flatnonzero</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.where.html">mxnet.np.where</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.searchsorted.html">mxnet.np.searchsorted</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.extract.html">mxnet.np.extract</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.count_nonzero.html">mxnet.np.count_nonzero</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.amin.html">mxnet.np.amin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.amax.html">mxnet.np.amax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanmin.html">mxnet.np.nanmin</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanmax.html">mxnet.np.nanmax</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.ptp.html">mxnet.np.ptp</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.percentile.html">mxnet.np.percentile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanpercentile.html">mxnet.np.nanpercentile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.quantile.html">mxnet.np.quantile</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanquantile.html">mxnet.np.nanquantile</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.median.html">mxnet.np.median</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.average.html">mxnet.np.average</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanmedian.html">mxnet.np.nanmedian</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanstd.html">mxnet.np.nanstd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.nanvar.html">mxnet.np.nanvar</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.corrcoef.html">mxnet.np.corrcoef</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.correlate.html">mxnet.np.correlate</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.cov.html">mxnet.np.cov</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogram.html">mxnet.np.histogram</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogram2d.html">mxnet.np.histogram2d</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogramdd.html">mxnet.np.histogramdd</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.bincount.html">mxnet.np.bincount</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.histogram_bin_edges.html">mxnet.np.histogram_bin_edges</a></li> |
| <li class="toctree-l5"><a class="reference internal" href="../../../api/np/generated/mxnet.np.digitize.html">mxnet.np.digitize</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../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_device.html">mxnet.npx.current_device</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.relu.html">mxnet.npx.relu</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.log_softmax.html">mxnet.npx.log_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/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">KVStore: Communication for Distributed Training</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore/index.html#horovod">Horovod</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.Horovod.html">mxnet.kvstore.Horovod</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore/index.html#byteps">BytePS</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.BytePS.html">mxnet.kvstore.BytePS</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../api/kvstore/index.html#kvstore-interface">KVStore Interface</a><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.KVStore.html">mxnet.kvstore.KVStore</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.KVStoreBase.html">mxnet.kvstore.KVStoreBase</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/kvstore/generated/mxnet.kvstore.KVStoreServer.html">mxnet.kvstore.KVStoreServer</a></li> |
| </ul> |
| </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/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/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/device/index.html">mxnet.device</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><ul> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/runtime/generated/mxnet.runtime.Feature.html">mxnet.runtime.Feature</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/runtime/generated/mxnet.runtime.Features.html">mxnet.runtime.Features</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../api/runtime/generated/mxnet.runtime.feature_list.html">mxnet.runtime.feature_list</a></li> |
| </ul> |
| </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.contrib.quantization</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="sd">"""Quantization module for generating quantized (INT8) models from FP32 models."""</span> |
| |
| <span class="kn">import</span> <span class="nn">abc</span> |
| <span class="kn">import</span> <span class="nn">ctypes</span> |
| <span class="kn">import</span> <span class="nn">logging</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">warnings</span> |
| <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="kn">import</span> <span class="nn">mxnet</span> <span class="k">as</span> <span class="nn">mx</span> |
| <span class="kn">from</span> <span class="nn">..base</span> <span class="kn">import</span> <span class="n">_LIB</span><span class="p">,</span> <span class="n">check_call</span><span class="p">,</span> <span class="n">py_str</span> |
| <span class="kn">from</span> <span class="nn">..base</span> <span class="kn">import</span> <span class="n">c_array</span><span class="p">,</span> <span class="n">c_str</span><span class="p">,</span> <span class="n">mx_uint</span><span class="p">,</span> <span class="n">mx_real_t</span><span class="p">,</span> <span class="n">c_str_array</span> |
| <span class="kn">from</span> <span class="nn">..base</span> <span class="kn">import</span> <span class="n">SymbolHandle</span> |
| <span class="kn">from</span> <span class="nn">..symbol</span> <span class="kn">import</span> <span class="n">Symbol</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">..io</span> <span class="kn">import</span> <span class="n">DataDesc</span> |
| <span class="kn">from</span> <span class="nn">..device</span> <span class="kn">import</span> <span class="n">cpu</span><span class="p">,</span> <span class="n">Device</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="p">,</span> <span class="n">wrap_ctx_to_device_func</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_multilist_iterator</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">func</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Iterate over multidiemnsional list and returns new list</span> |
| <span class="sd"> with same dimensions, but applied `func` function on list elements.</span> |
| <span class="sd"> E.g. _multilist_iterator([1, 2, [3, 4]], lambda x: x**2) = [1, 4, [9, 16]]</span> |
| <span class="sd"> """</span> |
| <span class="n">ret</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="k">for</span> <span class="n">el</span> <span class="ow">in</span> <span class="n">arg</span><span class="p">:</span> |
| <span class="n">ret</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">el</span><span class="p">,</span> <span class="n">func</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">func</span><span class="p">(</span><span class="n">arg</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">ret</span> |
| |
| <span class="k">def</span> <span class="nf">_quantize_params</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">params</span><span class="p">,</span> <span class="n">min_max_dict</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Given a quantized symbol and a dict of params that have not been quantized,</span> |
| <span class="sd"> generate quantized params. Currently only supports quantizing the arg_params</span> |
| <span class="sd"> with names of `weight` or `bias`, not aux_params. If `qsym` contains symbols</span> |
| <span class="sd"> that are excluded from being quantized, their corresponding params will</span> |
| <span class="sd"> not be quantized, but saved together with quantized params of the symbols that</span> |
| <span class="sd"> have been quantized.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> qsym : Symbol</span> |
| <span class="sd"> Quantized symbol from FP32 symbol.</span> |
| <span class="sd"> params : dict of str->NDArray</span> |
| <span class="sd"> min_max_dict : dict of min/max pairs of layers' output</span> |
| <span class="sd"> """</span> |
| <span class="n">inputs_name</span> <span class="o">=</span> <span class="n">qsym</span><span class="o">.</span><span class="n">list_arguments</span><span class="p">()</span> |
| <span class="n">quantized_params</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">quantize_fn</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">contrib_quantize</span> |
| <span class="n">min_fn</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">arr</span><span class="p">:</span> <span class="n">mx</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">mx</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">min</span><span class="p">(</span><span class="n">arr</span><span class="p">)])</span> |
| <span class="n">max_fn</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">arr</span><span class="p">:</span> <span class="n">mx</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">mx</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">arr</span><span class="p">)])</span> |
| <span class="n">array_cls</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">np</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">quantize_fn</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">contrib</span><span class="o">.</span><span class="n">quantize</span> |
| <span class="n">min_fn</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">min</span> |
| <span class="n">max_fn</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">max</span> |
| <span class="n">array_cls</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">nd</span> |
| |
| <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">inputs_name</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">((</span><span class="s1">'weight_quantize'</span><span class="p">,</span> <span class="s1">'bias_quantize'</span><span class="p">)):</span> |
| <span class="n">original_name</span> <span class="o">=</span> <span class="n">name</span><span class="p">[:</span><span class="o">-</span><span class="nb">len</span><span class="p">(</span><span class="s1">'_quantize'</span><span class="p">)]</span> |
| <span class="n">param</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="n">original_name</span><span class="p">]</span> |
| <span class="c1"># pylint: disable=unbalanced-tuple-unpacking</span> |
| <span class="n">param_min</span> <span class="o">=</span> <span class="n">min_fn</span><span class="p">(</span><span class="n">param</span><span class="p">)</span> |
| <span class="n">param_max</span> <span class="o">=</span> <span class="n">max_fn</span><span class="p">(</span><span class="n">param</span><span class="p">)</span> |
| <span class="n">val</span><span class="p">,</span> <span class="n">vmin</span><span class="p">,</span> <span class="n">vmax</span> <span class="o">=</span> <span class="n">quantize_fn</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">param</span><span class="p">,</span> |
| <span class="n">min_range</span><span class="o">=</span><span class="n">param_min</span><span class="p">,</span> |
| <span class="n">max_range</span><span class="o">=</span><span class="n">param_max</span><span class="p">,</span> |
| <span class="n">out_type</span><span class="o">=</span><span class="s1">'int8'</span><span class="p">)</span> |
| <span class="n">quantized_params</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">val</span> |
| <span class="n">quantized_params</span><span class="p">[</span><span class="n">name</span><span class="o">+</span><span class="s1">'_min'</span><span class="p">]</span> <span class="o">=</span> <span class="n">vmin</span> |
| <span class="n">quantized_params</span><span class="p">[</span><span class="n">name</span><span class="o">+</span><span class="s1">'_max'</span><span class="p">]</span> <span class="o">=</span> <span class="n">vmax</span> |
| <span class="k">elif</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">params</span><span class="p">:</span> |
| <span class="n">quantized_params</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> |
| <span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">((</span><span class="s1">'_min'</span><span class="p">)):</span> |
| <span class="n">output</span> <span class="o">=</span> <span class="n">name</span><span class="p">[:</span> <span class="o">-</span> <span class="nb">len</span><span class="p">(</span><span class="s1">'_min'</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">min_max_dict</span><span class="p">:</span> |
| <span class="n">quantized_params</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">array_cls</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">min_max_dict</span><span class="p">[</span><span class="n">output</span><span class="p">][</span><span class="mi">0</span><span class="p">]])</span> |
| <span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">((</span><span class="s1">'_max'</span><span class="p">)):</span> |
| <span class="n">output</span> <span class="o">=</span> <span class="n">name</span><span class="p">[:</span> <span class="o">-</span> <span class="nb">len</span><span class="p">(</span><span class="s1">'_min'</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="n">output</span> <span class="ow">in</span> <span class="n">min_max_dict</span><span class="p">:</span> |
| <span class="n">quantized_params</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">array_cls</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">min_max_dict</span><span class="p">[</span><span class="n">output</span><span class="p">][</span><span class="mi">1</span><span class="p">]])</span> |
| <span class="k">return</span> <span class="n">quantized_params</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_quantize_symbol</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">device</span><span class="p">,</span> <span class="n">excluded_symbols</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">excluded_operators</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">offline_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">quantized_dtype</span><span class="o">=</span><span class="s1">'int8'</span><span class="p">,</span> <span class="n">quantize_mode</span><span class="o">=</span><span class="s1">'smart'</span><span class="p">,</span> |
| <span class="n">quantize_granularity</span><span class="o">=</span><span class="s1">'tensor-wise'</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Given a symbol object representing a neural network of data type FP32,</span> |
| <span class="sd"> quantize it into a INT8 network.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sym : Symbol</span> |
| <span class="sd"> FP32 neural network symbol.</span> |
| <span class="sd"> device : Device</span> |
| <span class="sd"> Defines the device that users want to run quantized symbol.</span> |
| <span class="sd"> excluded_symbols : list of strings</span> |
| <span class="sd"> A list of strings representing the names of the symbols that users want to excluding</span> |
| <span class="sd"> from being quantized.</span> |
| <span class="sd"> excluded_operators : list of strings</span> |
| <span class="sd"> A list of strings representing the names of the operators that users want to excluding</span> |
| <span class="sd"> from being quantized.</span> |
| <span class="sd"> offline_params : list of strs</span> |
| <span class="sd"> Names of the parameters that users want to quantize offline. It's always recommended to</span> |
| <span class="sd"> quantize parameters offline so that quantizing parameters during the inference can be</span> |
| <span class="sd"> avoided.</span> |
| <span class="sd"> quantized_dtype : str</span> |
| <span class="sd"> The quantized destination type for input data.</span> |
| <span class="sd"> quantize_mode : str</span> |
| <span class="sd"> The mode that quantization pass to apply.</span> |
| <span class="sd"> quantize_granularity : str</span> |
| <span class="sd"> The granularity of quantization, currently supports 'tensor-wise' and 'channel-wise'</span> |
| <span class="sd"> quantization. The default value is 'tensor-wise'.</span> |
| <span class="sd"> """</span> |
| <span class="n">num_excluded_symbols</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">if</span> <span class="n">excluded_symbols</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">excluded_symbols</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span> |
| <span class="n">num_excluded_symbols</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">excluded_symbols</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">excluded_symbols</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="n">num_excluded_ops</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">if</span> <span class="n">excluded_operators</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">excluded_operators</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span> |
| <span class="n">num_excluded_ops</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">excluded_operators</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">excluded_operators</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="n">num_offline</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">offline</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="n">offline_params</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">num_offline</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">offline_params</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">offline_params</span><span class="p">:</span> |
| <span class="n">offline</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">c_str</span><span class="p">(</span><span class="n">k</span><span class="p">))</span> |
| |
| <span class="n">out</span> <span class="o">=</span> <span class="n">SymbolHandle</span><span class="p">()</span> |
| <span class="n">size</span> <span class="o">=</span> <span class="n">mx_uint</span><span class="p">()</span> |
| <span class="n">calib_str</span> <span class="o">=</span> <span class="n">ctypes</span><span class="o">.</span><span class="n">POINTER</span><span class="p">(</span><span class="n">ctypes</span><span class="o">.</span><span class="n">c_char_p</span><span class="p">)()</span> |
| <span class="n">check_call</span><span class="p">(</span><span class="n">_LIB</span><span class="o">.</span><span class="n">MXQuantizeSymbol</span><span class="p">(</span><span class="n">sym</span><span class="o">.</span><span class="n">handle</span><span class="p">,</span> |
| <span class="n">ctypes</span><span class="o">.</span><span class="n">byref</span><span class="p">(</span><span class="n">out</span><span class="p">),</span> |
| <span class="n">ctypes</span><span class="o">.</span><span class="n">byref</span><span class="p">(</span><span class="n">ctypes</span><span class="o">.</span><span class="n">c_int</span><span class="p">(</span><span class="n">device</span><span class="o">.</span><span class="n">device_typeid</span><span class="p">)),</span> |
| <span class="n">mx_uint</span><span class="p">(</span><span class="n">num_excluded_symbols</span><span class="p">),</span> |
| <span class="n">c_str_array</span><span class="p">(</span><span class="n">excluded_symbols</span><span class="p">),</span> |
| <span class="n">mx_uint</span><span class="p">(</span><span class="n">num_excluded_ops</span><span class="p">),</span> |
| <span class="n">c_str_array</span><span class="p">(</span><span class="n">excluded_operators</span><span class="p">),</span> |
| <span class="n">mx_uint</span><span class="p">(</span><span class="n">num_offline</span><span class="p">),</span> |
| <span class="n">c_array</span><span class="p">(</span><span class="n">ctypes</span><span class="o">.</span><span class="n">c_char_p</span><span class="p">,</span> <span class="n">offline</span><span class="p">),</span> |
| <span class="n">c_str</span><span class="p">(</span><span class="n">quantized_dtype</span><span class="p">),</span> |
| <span class="n">ctypes</span><span class="o">.</span><span class="n">c_bool</span><span class="p">(</span><span class="kc">True</span><span class="p">),</span> |
| <span class="n">c_str</span><span class="p">(</span><span class="n">quantize_mode</span><span class="p">),</span> |
| <span class="n">c_str</span><span class="p">(</span><span class="n">quantize_granularity</span><span class="p">),</span> |
| <span class="n">ctypes</span><span class="o">.</span><span class="n">byref</span><span class="p">(</span><span class="n">size</span><span class="p">),</span> |
| <span class="n">ctypes</span><span class="o">.</span><span class="n">byref</span><span class="p">(</span><span class="n">calib_str</span><span class="p">)))</span> |
| <span class="n">calib_layers</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">calib_layers</span> <span class="o">=</span> <span class="p">[</span><span class="n">py_str</span><span class="p">(</span><span class="n">calib_str</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">size</span><span class="o">.</span><span class="n">value</span><span class="p">)]</span> |
| <span class="k">return</span> <span class="n">Symbol</span><span class="p">(</span><span class="n">out</span><span class="p">),</span> <span class="n">calib_layers</span> |
| |
| |
| <div class="viewcode-block" id="CalibrationCollector"><a class="viewcode-back" href="../../../api/contrib/quantization/index.html#mxnet.contrib.quantization.CalibrationCollector">[docs]</a><span class="k">class</span> <span class="nc">CalibrationCollector</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Base class for all other collectors used with quantization"""</span> |
| <span class="n">__metaclass__</span> <span class="o">=</span> <span class="n">abc</span><span class="o">.</span><span class="n">ABCMeta</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="bp">self</span><span class="o">.</span><span class="n">include_layers</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">min_max_dict</span> <span class="o">=</span> <span class="p">{}</span> |
| |
| <div class="viewcode-block" id="CalibrationCollector.collect"><a class="viewcode-back" href="../../../api/contrib/quantization/index.html#mxnet.contrib.quantization.CalibrationCollector.collect">[docs]</a> <span class="nd">@abc</span><span class="o">.</span><span class="n">abstractmethod</span> |
| <span class="k">def</span> <span class="nf">collect</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">op_name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Function which is registered to Block as monitor callback. Names of layers</span> |
| <span class="sd"> requiring calibration are stored in `self.include_layers` variable.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> name : str</span> |
| <span class="sd"> Node name from which collected data comes from.</span> |
| <span class="sd"> op_name : str</span> |
| <span class="sd"> Operator name from which collected data comes from. Single operator</span> |
| <span class="sd"> can have multiple input/ouput nodes - each should have different name.</span> |
| <span class="sd"> arr : NDArray</span> |
| <span class="sd"> NDArray containing data of monitored node.</span> |
| <span class="sd"> """</span></div> |
| |
| <div class="viewcode-block" id="CalibrationCollector.post_collect"><a class="viewcode-back" href="../../../api/contrib/quantization/index.html#mxnet.contrib.quantization.CalibrationCollector.post_collect">[docs]</a> <span class="k">def</span> <span class="nf">post_collect</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">""" Function called after collecting parameters. Returns dictionary of min and max values</span> |
| <span class="sd"> for each calibrated layer. If not overriden, returns content of `self.min_max_dict`.</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">min_max_dict</span></div></div> |
| |
| |
| <span class="k">class</span> <span class="nc">_LayerHistogramCollector</span><span class="p">(</span><span class="n">CalibrationCollector</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Saves layer histogram in a dict with layer names as keys and lists of NDArrays as</span> |
| <span class="sd"> values. The collected histogram will be used for calculating the optimal thresholds for</span> |
| <span class="sd"> quantization using KL 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">quantized_dtype</span><span class="p">,</span> <span class="n">num_bins</span><span class="o">=</span><span class="mi">8001</span><span class="p">,</span> <span class="n">include_layers</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_LayerHistogramCollector</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="bp">self</span><span class="o">.</span><span class="n">hist_dict</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">num_bins</span> <span class="o">=</span> <span class="n">num_bins</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">include_layers</span> <span class="o">=</span> <span class="n">include_layers</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">quantized_dtype</span> <span class="o">=</span> <span class="n">quantized_dtype</span> |
| |
| <span class="k">def</span> <span class="nf">collect</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">op_name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Callback function for collecting layer output NDArrays."""</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">include_layers</span><span class="p">:</span> |
| <span class="k">return</span> |
| <span class="n">arr</span> <span class="o">=</span> <span class="n">arr</span><span class="o">.</span><span class="n">copyto</span><span class="p">(</span><span class="n">cpu</span><span class="p">())</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Collecting layer </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> histogram of shape </span><span class="si">{</span><span class="n">arr</span><span class="o">.</span><span class="n">shape</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span> |
| <span class="n">min_range</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">min</span><span class="p">(</span><span class="n">arr</span><span class="p">)</span> |
| <span class="n">max_range</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">arr</span><span class="p">)</span> |
| <span class="n">th</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span><span class="nb">abs</span><span class="p">(</span><span class="n">min_range</span><span class="p">),</span> <span class="nb">abs</span><span class="p">(</span><span class="n">max_range</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">hist_dict</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hist_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">combine_histogram</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">hist_dict</span><span class="p">[</span><span class="n">name</span><span class="p">],</span> <span class="n">arr</span><span class="p">,</span> <span class="n">min_range</span><span class="p">,</span> <span class="n">max_range</span><span class="p">,</span> <span class="n">th</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">hist</span><span class="p">,</span> <span class="n">hist_edges</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">histogram</span><span class="p">(</span><span class="n">arr</span><span class="p">,</span> <span class="n">bins</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">num_bins</span><span class="p">,</span> <span class="nb">range</span><span class="o">=</span><span class="p">(</span><span class="o">-</span><span class="n">th</span><span class="p">,</span> <span class="n">th</span><span class="p">))</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">hist_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">hist</span><span class="p">,</span> <span class="n">hist_edges</span><span class="p">,</span> <span class="n">min_range</span><span class="p">,</span> <span class="n">max_range</span><span class="p">,</span> <span class="n">th</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">post_collect</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">min_max_dict</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_optimal_thresholds</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">hist_dict</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">quantized_dtype</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">min_max_dict</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">combine_histogram</span><span class="p">(</span><span class="n">old_hist</span><span class="p">,</span> <span class="n">arr</span><span class="p">,</span> <span class="n">new_min</span><span class="p">,</span> <span class="n">new_max</span><span class="p">,</span> <span class="n">new_th</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Collect layer histogram for arr and combine it with old histogram."""</span> |
| <span class="p">(</span><span class="n">old_hist</span><span class="p">,</span> <span class="n">old_hist_edges</span><span class="p">,</span> <span class="n">old_min</span><span class="p">,</span> <span class="n">old_max</span><span class="p">,</span> <span class="n">old_th</span><span class="p">)</span> <span class="o">=</span> <span class="n">old_hist</span> |
| <span class="k">if</span> <span class="n">new_th</span> <span class="o"><=</span> <span class="n">old_th</span><span class="p">:</span> |
| <span class="n">hist</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">histogram</span><span class="p">(</span><span class="n">arr</span><span class="p">,</span> <span class="n">bins</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="n">old_hist</span><span class="p">),</span> <span class="nb">range</span><span class="o">=</span><span class="p">(</span><span class="o">-</span><span class="n">old_th</span><span class="p">,</span> <span class="n">old_th</span><span class="p">))</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">old_hist</span> <span class="o">+</span> <span class="n">hist</span><span class="p">,</span> <span class="n">old_hist_edges</span><span class="p">,</span> <span class="nb">min</span><span class="p">(</span><span class="n">old_min</span><span class="p">,</span> <span class="n">new_min</span><span class="p">),</span> <span class="nb">max</span><span class="p">(</span><span class="n">old_max</span><span class="p">,</span> <span class="n">new_max</span><span class="p">),</span> <span class="n">old_th</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="c1"># Need to generate new histogram with new_th</span> |
| <span class="n">old_num_bins</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">old_hist</span><span class="p">)</span> |
| <span class="n">old_step</span> <span class="o">=</span> <span class="mi">2</span> <span class="o">*</span> <span class="n">old_th</span> <span class="o">/</span> <span class="n">old_num_bins</span> |
| <span class="n">half_increased_bins</span> <span class="o">=</span> <span class="nb">int</span><span class="p">((</span><span class="n">new_th</span> <span class="o">-</span> <span class="n">old_th</span><span class="p">)</span> <span class="o">//</span> <span class="n">old_step</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="n">new_num_bins</span> <span class="o">=</span> <span class="n">half_increased_bins</span> <span class="o">*</span> <span class="mi">2</span> <span class="o">+</span> <span class="n">old_num_bins</span> |
| <span class="n">new_th</span> <span class="o">=</span> <span class="n">half_increased_bins</span> <span class="o">*</span> <span class="n">old_step</span> <span class="o">+</span> <span class="n">old_th</span> |
| <span class="n">hist</span><span class="p">,</span> <span class="n">hist_edges</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">histogram</span><span class="p">(</span><span class="n">arr</span><span class="p">,</span> <span class="n">bins</span><span class="o">=</span><span class="n">new_num_bins</span><span class="p">,</span> <span class="nb">range</span><span class="o">=</span><span class="p">(</span><span class="o">-</span><span class="n">new_th</span><span class="p">,</span> <span class="n">new_th</span><span class="p">))</span> |
| <span class="n">hist</span><span class="p">[</span><span class="n">half_increased_bins</span><span class="p">:</span><span class="n">new_num_bins</span> <span class="o">-</span> <span class="n">half_increased_bins</span><span class="p">]</span> <span class="o">+=</span> <span class="n">old_hist</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">hist</span><span class="p">,</span> <span class="n">hist_edges</span><span class="p">,</span> <span class="nb">min</span><span class="p">(</span><span class="n">old_min</span><span class="p">,</span> <span class="n">new_min</span><span class="p">),</span> <span class="nb">max</span><span class="p">(</span><span class="n">old_max</span><span class="p">,</span> <span class="n">new_max</span><span class="p">),</span> <span class="n">new_th</span><span class="p">)</span> |
| |
| <span class="c1"># pylint: disable=line-too-long</span> |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">get_optimal_threshold</span><span class="p">(</span><span class="n">hist_data</span><span class="p">,</span> <span class="n">quantized_dtype</span><span class="p">,</span> <span class="n">num_quantized_bins</span><span class="o">=</span><span class="mi">255</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Given a dataset, find the optimal threshold for quantizing it.</span> |
| <span class="sd"> The reference distribution is `q`, and the candidate distribution is `p`.</span> |
| <span class="sd"> `q` is a truncated version of the original distribution.</span> |
| |
| <span class="sd"> Ref: http://on-demand.gputechconf.com/gtc/2017/presentation/s7310-8-bit-inference-with-tensorrt.pdf</span> |
| <span class="sd"> """</span> |
| <span class="p">(</span><span class="n">hist</span><span class="p">,</span> <span class="n">hist_edges</span><span class="p">,</span> <span class="n">min_val</span><span class="p">,</span> <span class="n">max_val</span><span class="p">,</span> <span class="n">_</span><span class="p">)</span> <span class="o">=</span> <span class="n">hist_data</span> |
| <span class="n">num_bins</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">hist</span><span class="p">)</span> |
| <span class="k">assert</span> <span class="p">(</span><span class="n">num_bins</span> <span class="o">%</span> <span class="mi">2</span> <span class="o">==</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">min_val</span> <span class="o">>=</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">quantized_dtype</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'auto'</span><span class="p">,</span> <span class="s1">'uint8'</span><span class="p">]:</span> |
| <span class="c1"># We need to move negative bins to positive bins to fit uint8 range.</span> |
| <span class="n">num_quantized_bins</span> <span class="o">=</span> <span class="n">num_quantized_bins</span> <span class="o">*</span> <span class="mi">2</span> <span class="o">+</span> <span class="mi">1</span> |
| <span class="n">hist</span> <span class="o">=</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">hist</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">cpu</span><span class="p">())</span> |
| <span class="n">hist_edges</span> <span class="o">=</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">hist_edges</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">cpu</span><span class="p">())</span> |
| <span class="n">threshold</span><span class="p">,</span> <span class="n">divergence</span> <span class="o">=</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">contrib</span><span class="o">.</span><span class="n">calibrate_entropy</span><span class="p">(</span><span class="n">hist</span><span class="o">=</span><span class="n">hist</span><span class="p">,</span> |
| <span class="n">hist_edges</span><span class="o">=</span><span class="n">hist_edges</span><span class="p">,</span> |
| <span class="n">num_quantized_bins</span><span class="o">=</span><span class="n">num_quantized_bins</span><span class="p">)</span> |
| <span class="n">threshold</span> <span class="o">=</span> <span class="n">threshold</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> |
| <span class="n">divergence</span> <span class="o">=</span> <span class="n">divergence</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">min_val</span><span class="p">,</span> <span class="n">max_val</span><span class="p">,</span> <span class="n">threshold</span><span class="p">,</span> <span class="n">divergence</span> |
| <span class="c1"># pylint: enable=line-too-long</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="k">def</span> <span class="nf">get_optimal_thresholds</span><span class="p">(</span><span class="n">hist_dict</span><span class="p">,</span> <span class="n">quantized_dtype</span><span class="p">,</span> <span class="n">num_quantized_bins</span><span class="o">=</span><span class="mi">255</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Given a ndarray dict, find the optimal threshold for quantizing each value of the key."""</span> |
| <span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">hist_dict</span><span class="p">,</span> <span class="nb">dict</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">logger</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Calculating optimal thresholds for quantization using KL divergence'</span> |
| <span class="sa">f</span><span class="s1">' with num_quantized_bins=</span><span class="si">{</span><span class="n">num_quantized_bins</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="n">th_dict</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="c1"># copy hist_dict keys since the keys() only returns a view in python3</span> |
| <span class="n">layer_names</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">hist_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span> |
| <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">layer_names</span><span class="p">:</span> |
| <span class="k">assert</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">hist_dict</span> |
| <span class="n">min_val</span><span class="p">,</span> <span class="n">max_val</span><span class="p">,</span> <span class="n">th</span><span class="p">,</span> <span class="n">divergence</span> <span class="o">=</span> \ |
| <span class="n">_LayerHistogramCollector</span><span class="o">.</span><span class="n">get_optimal_threshold</span><span class="p">(</span><span class="n">hist_dict</span><span class="p">[</span><span class="n">name</span><span class="p">],</span> <span class="n">quantized_dtype</span><span class="p">,</span> |
| <span class="n">num_quantized_bins</span><span class="o">=</span><span class="n">num_quantized_bins</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">min_val</span> <span class="o">>=</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">quantized_dtype</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'auto'</span><span class="p">,</span> <span class="s1">'uint8'</span><span class="p">]:</span> |
| <span class="n">th_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">th</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">th_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="o">-</span><span class="n">th</span><span class="p">,</span> <span class="n">th</span><span class="p">)</span> |
| <span class="k">del</span> <span class="n">hist_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="c1"># release the memory</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="sa">f</span><span class="s2">"layer=</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">, min_val=</span><span class="si">{</span><span class="n">min_val</span><span class="si">}</span><span class="s2">, max_val=</span><span class="si">{</span><span class="n">max_val</span><span class="si">}</span><span class="s2">, th=</span><span class="si">{</span><span class="n">th</span><span class="si">}</span><span class="s2">, divergence=</span><span class="si">{</span><span class="n">divergence</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">th_dict</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_LayerOutputMinMaxCollector</span><span class="p">(</span><span class="n">CalibrationCollector</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Saves layer output min and max values in a dict with layer names as keys.</span> |
| <span class="sd"> The collected min and max values will be directly used as thresholds for quantization.</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">quantized_dtype</span><span class="p">,</span> <span class="n">include_layers</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">_LayerOutputMinMaxCollector</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="bp">self</span><span class="o">.</span><span class="n">min_max_dict</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">quantized_dtype</span> <span class="o">=</span> <span class="n">quantized_dtype</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">include_layers</span> <span class="o">=</span> <span class="n">include_layers</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span> |
| |
| <span class="k">def</span> <span class="nf">collect</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">op_name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Callback function for collecting min and max values from an NDArray."""</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">include_layers</span><span class="p">:</span> |
| <span class="k">return</span> |
| <span class="n">arr</span> <span class="o">=</span> <span class="n">arr</span><span class="o">.</span><span class="n">copyto</span><span class="p">(</span><span class="n">cpu</span><span class="p">())</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span> |
| <span class="n">min_range</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">min</span><span class="p">(</span><span class="n">arr</span><span class="p">)</span> |
| <span class="n">max_range</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">arr</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">min_max_dict</span><span class="p">:</span> |
| <span class="n">cur_min_max</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">min_max_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">min_max_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="nb">min</span><span class="p">(</span><span class="n">cur_min_max</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">min_range</span><span class="p">),</span> |
| <span class="nb">max</span><span class="p">(</span><span class="n">cur_min_max</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">max_range</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">min_max_dict</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="n">min_range</span><span class="p">,</span> <span class="n">max_range</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Collecting layer </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> min_range=</span><span class="si">{</span><span class="n">min_range</span><span class="si">}</span><span class="s2">, max_range=</span><span class="si">{</span><span class="n">max_range</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_calibrate_quantized_sym</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">min_max_dict</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Given a dictionary containing the thresholds for quantizing the layers,</span> |
| <span class="sd"> set the thresholds into the quantized symbol as the params of requantize operators.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">min_max_dict</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="n">min_max_dict</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">qsym</span> |
| <span class="n">num_layer_outputs</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">min_max_dict</span><span class="p">)</span> |
| <span class="n">layer_output_names</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">min_vals</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">max_vals</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">min_max_dict</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">layer_output_names</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">k</span><span class="p">)</span> |
| <span class="n">min_vals</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">v</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> |
| <span class="n">max_vals</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">v</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> |
| |
| <span class="n">calibrated_sym</span> <span class="o">=</span> <span class="n">SymbolHandle</span><span class="p">()</span> |
| <span class="n">check_call</span><span class="p">(</span><span class="n">_LIB</span><span class="o">.</span><span class="n">MXSetCalibTableToQuantizedSymbol</span><span class="p">(</span><span class="n">qsym</span><span class="o">.</span><span class="n">handle</span><span class="p">,</span> |
| <span class="n">mx_uint</span><span class="p">(</span><span class="n">num_layer_outputs</span><span class="p">),</span> |
| <span class="n">c_str_array</span><span class="p">(</span><span class="n">layer_output_names</span><span class="p">),</span> |
| <span class="n">c_array</span><span class="p">(</span><span class="n">ctypes</span><span class="o">.</span><span class="n">c_float</span><span class="p">,</span> <span class="n">min_vals</span><span class="p">),</span> |
| <span class="n">c_array</span><span class="p">(</span><span class="n">ctypes</span><span class="o">.</span><span class="n">c_float</span><span class="p">,</span> <span class="n">max_vals</span><span class="p">),</span> |
| <span class="n">ctypes</span><span class="o">.</span><span class="n">byref</span><span class="p">(</span><span class="n">calibrated_sym</span><span class="p">)))</span> |
| <span class="k">return</span> <span class="n">Symbol</span><span class="p">(</span><span class="n">calibrated_sym</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_collect_layer_statistics</span><span class="p">(</span><span class="n">sym_block</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">collector</span><span class="p">,</span> <span class="n">num_inputs</span><span class="p">,</span> <span class="n">num_calib_batches</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">mx</span><span class="o">.</span><span class="n">gluon</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'Only supports data as a type of DataLoader, while received type </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">data</span><span class="p">))</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="n">sym_block</span><span class="o">.</span><span class="n">register_op_hook</span><span class="p">(</span><span class="n">collector</span><span class="o">.</span><span class="n">collect</span><span class="p">,</span> <span class="n">monitor_all</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="n">num_batches</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">data</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="n">batch</span> <span class="o">=</span> <span class="p">[</span><span class="n">batch</span><span class="p">]</span> |
| <span class="n">batch</span> <span class="o">=</span> <span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">b</span><span class="p">:</span> <span class="n">b</span><span class="o">.</span><span class="n">as_in_context</span><span class="p">(</span><span class="n">mx</span><span class="o">.</span><span class="n">cpu</span><span class="p">()))</span> |
| <span class="n">sym_block</span><span class="p">(</span><span class="o">*</span><span class="n">batch</span><span class="p">[:</span><span class="n">num_inputs</span><span class="p">])</span> |
| <span class="n">num_batches</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">if</span> <span class="n">num_calib_batches</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">num_batches</span> <span class="o">>=</span> <span class="n">num_calib_batches</span><span class="p">:</span> |
| <span class="k">break</span> |
| <span class="k">if</span> <span class="n">logger</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Collected statistics from </span><span class="si">{</span><span class="n">num_batches</span><span class="si">}</span><span class="s2"> batches"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">num_batches</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_generate_list_of_data_desc</span><span class="p">(</span><span class="n">data_shapes</span><span class="p">,</span> <span class="n">data_types</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Convert list of tuples to list of DataDesc."""</span> |
| <span class="k">def</span> <span class="nf">flatten_list</span><span class="p">(</span><span class="n">arg</span><span class="p">):</span> |
| <span class="n">ret</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">el</span> <span class="ow">in</span> <span class="n">arg</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">el</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="n">ret</span> <span class="o">+=</span> <span class="n">flatten_list</span><span class="p">(</span><span class="n">el</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">ret</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">el</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">ret</span> |
| |
| <span class="n">flattened_data_types</span> <span class="o">=</span> <span class="n">flatten_list</span><span class="p">(</span><span class="n">data_types</span><span class="p">)</span> |
| <span class="n">flattened_data_shapes</span> <span class="o">=</span> <span class="n">flatten_list</span><span class="p">(</span><span class="n">data_shapes</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="nb">all</span><span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">DataDesc</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">flattened_data_shapes</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">data_shapes</span> |
| |
| <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">flattened_data_types</span><span class="p">)</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="n">flattened_data_shapes</span><span class="p">)</span> |
| |
| <span class="c1"># pass integral type as reference</span> |
| <span class="n">counter</span> <span class="o">=</span> <span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="k">def</span> <span class="nf">get_data_desc</span><span class="p">(</span><span class="n">data_shape</span><span class="p">,</span> <span class="n">counter</span><span class="o">=</span><span class="n">counter</span><span class="p">,</span> <span class="n">data_types</span><span class="o">=</span><span class="n">flattened_data_types</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data_shape</span><span class="p">,</span> <span class="n">DataDesc</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">data_shape</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data_shape</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">):</span> |
| <span class="n">desc</span> <span class="o">=</span> <span class="n">DataDesc</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">'data'</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">counter</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span> <span class="n">shape</span><span class="o">=</span><span class="n">data_shape</span><span class="p">,</span> |
| <span class="n">dtype</span><span class="o">=</span><span class="n">data_types</span><span class="p">[</span><span class="n">counter</span><span class="p">[</span><span class="mi">0</span><span class="p">]])</span> |
| <span class="n">counter</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+=</span> <span class="mi">1</span> |
| <span class="k">return</span> <span class="n">desc</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'data_shapes must be either a list of DataDesc or a list of Tuple'</span><span class="p">)</span> |
| |
| |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">data_shapes</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data_shapes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="n">data_descs</span> <span class="o">=</span> <span class="p">[</span><span class="n">DataDesc</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">'data'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="n">data_shapes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="n">data_types</span><span class="p">[</span><span class="mi">0</span><span class="p">])]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">data_descs</span> <span class="o">=</span> <span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">data_shapes</span><span class="p">,</span> <span class="n">get_data_desc</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">data_descs</span> |
| |
| <div class="viewcode-block" id="quantize_model"><a class="viewcode-back" href="../../../api/contrib/quantization/index.html#mxnet.contrib.quantization.quantize_model">[docs]</a><span class="nd">@wrap_ctx_to_device_func</span> |
| <span class="k">def</span> <span class="nf">quantize_model</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">aux_params</span><span class="p">,</span> <span class="n">data_names</span><span class="o">=</span><span class="p">(</span><span class="s1">'data'</span><span class="p">,),</span> |
| <span class="n">device</span><span class="o">=</span><span class="n">cpu</span><span class="p">(),</span> <span class="n">excluded_sym_names</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">excluded_op_names</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">calib_mode</span><span class="o">=</span><span class="s1">'entropy'</span><span class="p">,</span> |
| <span class="n">calib_data</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_calib_batches</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">quantized_dtype</span><span class="o">=</span><span class="s1">'int8'</span><span class="p">,</span> <span class="n">quantize_mode</span><span class="o">=</span><span class="s1">'smart'</span><span class="p">,</span> |
| <span class="n">quantize_granularity</span><span class="o">=</span><span class="s1">'tensor-wise'</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""User-level API for generating a quantized model from a FP32 model w/ or w/o calibration.</span> |
| <span class="sd"> The backend quantized operators are only enabled for Linux systems. Please do not run</span> |
| <span class="sd"> inference using the quantized models on Windows for now.</span> |
| <span class="sd"> The quantization implementation adopts the TensorFlow's approach:</span> |
| <span class="sd"> https://www.tensorflow.org/lite/performance/post_training_quantization.</span> |
| <span class="sd"> The calibration implementation borrows the idea of Nvidia's 8-bit Inference with TensorRT:</span> |
| <span class="sd"> http://on-demand.gputechconf.com/gtc/2017/presentation/s7310-8-bit-inference-with-tensorrt.pdf</span> |
| <span class="sd"> and adapts the method to MXNet.</span> |
| |
| <span class="sd"> .. _`quantize_model_params`:</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sym : Symbol</span> |
| <span class="sd"> Defines the structure of a neural network for FP32 data types.</span> |
| <span class="sd"> arg_params : dict</span> |
| <span class="sd"> Dictionary of name to `NDArray`.</span> |
| <span class="sd"> aux_params : dict</span> |
| <span class="sd"> Dictionary of name to `NDArray`.</span> |
| <span class="sd"> data_names : list of strings</span> |
| <span class="sd"> Data names required for creating a Module object to run forward propagation on the</span> |
| <span class="sd"> calibration dataset.</span> |
| <span class="sd"> device : Device</span> |
| <span class="sd"> Defines the device that users want to run forward propagation on the calibration</span> |
| <span class="sd"> dataset for collecting layer output statistics. Currently, only supports single device.</span> |
| <span class="sd"> excluded_sym_names : list of strings</span> |
| <span class="sd"> A list of strings representing the names of the symbols that users want to excluding</span> |
| <span class="sd"> from being quantized.</span> |
| <span class="sd"> excluded_op_names : list of strings</span> |
| <span class="sd"> A list of strings representing the names of the operators that users want to excluding</span> |
| <span class="sd"> from being quantized.</span> |
| <span class="sd"> calib_mode : str</span> |
| <span class="sd"> If calib_mode='none', no calibration will be used and the thresholds for</span> |
| <span class="sd"> requantization after the corresponding layers will be calculated at runtime by</span> |
| <span class="sd"> calling min and max operators. The quantized models generated in this</span> |
| <span class="sd"> mode are normally 10-20% slower than those with calibrations during inference.</span> |
| <span class="sd"> If calib_mode='naive', the min and max values of the layer outputs from a calibration</span> |
| <span class="sd"> dataset will be directly taken as the thresholds for quantization.</span> |
| <span class="sd"> If calib_mode='entropy' (default mode), the thresholds for quantization will be</span> |
| <span class="sd"> derived such that the KL divergence between the distributions of FP32 layer outputs and</span> |
| <span class="sd"> quantized layer outputs is minimized based upon the calibration dataset.</span> |
| <span class="sd"> calib_data : DataLoader</span> |
| <span class="sd"> A DataLoader initialized by the calibration dataset.</span> |
| <span class="sd"> num_calib_batches : int or None</span> |
| <span class="sd"> The maximum number of batches that user would like to use for calibration. If not provided,</span> |
| <span class="sd"> the whole calibration dataset will be used.</span> |
| <span class="sd"> quantized_dtype : str</span> |
| <span class="sd"> The quantized destination type for input data. Currently support 'int8', 'uint8' and 'auto'.</span> |
| <span class="sd"> 'auto' means automatically select output type according to calibration result.</span> |
| <span class="sd"> Default value is 'int8'.</span> |
| <span class="sd"> quantize_mode : str</span> |
| <span class="sd"> The mode that quantization pass to apply. Support 'full' and 'smart'.</span> |
| <span class="sd"> 'full' means quantize all operator if possible.</span> |
| <span class="sd"> 'smart' means quantization pass will smartly choice which operator should be quantized.</span> |
| <span class="sd"> quantize_granularity : str</span> |
| <span class="sd"> The granularity of quantization, currently supports 'tensor-wise' and 'channel-wise'</span> |
| <span class="sd"> quantization. The default value is 'tensor-wise'.</span> |
| <span class="sd"> logger : Object</span> |
| <span class="sd"> A logging object for printing information during the process of quantization.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> quantized_model : tuple</span> |
| <span class="sd"> A tuple of quantized symbol, quantized arg_params, and aux_params.</span> |
| <span class="sd"> """</span> |
| <span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'WARNING: This will be deprecated please use quantize_net with Gluon models'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">excluded_sym_names</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">excluded_sym_names</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">excluded_sym_names</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'excluded_sym_names must be a list of strings representing'</span> |
| <span class="s1">' the names of the symbols that will not be quantized,'</span> |
| <span class="sa">f</span><span class="s1">' while received type </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">excluded_sym_names</span><span class="p">))</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">excluded_op_names</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">excluded_op_names</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">excluded_op_names</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'excluded_op_names must be a list of strings representing'</span> |
| <span class="s1">' the names of the operators that will not be quantized,'</span> |
| <span class="sa">f</span><span class="s1">' while received type </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">excluded_op_names</span><span class="p">))</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'MXNET_QUANTIZATION_VERBOSE'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'1'</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Quantizing symbol'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">quantized_dtype</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'int8'</span><span class="p">,</span> <span class="s1">'uint8'</span><span class="p">,</span> <span class="s1">'auto'</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'unknown quantized_dtype </span><span class="si">{</span><span class="n">quantized_dtype</span><span class="si">}</span><span class="s1"> received,'</span> |
| <span class="s1">' expected `int8`, `uint8` or `auto`'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">quantize_granularity</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'tensor-wise'</span><span class="p">,</span> <span class="s1">'channel-wise'</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'unkonwn quantize_granularity </span><span class="si">{</span><span class="n">quantize_granularity</span><span class="si">}</span><span class="s1"> received,'</span> |
| <span class="s1">' expected `tensor-wise` or `channel-wise`.'</span><span class="p">)</span> |
| <span class="n">qsym</span><span class="p">,</span> <span class="n">calib_layers</span> <span class="o">=</span> <span class="n">_quantize_symbol</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">device</span><span class="p">,</span> <span class="n">excluded_symbols</span><span class="o">=</span><span class="n">excluded_sym_names</span><span class="p">,</span> |
| <span class="n">excluded_operators</span><span class="o">=</span><span class="n">excluded_op_names</span><span class="p">,</span> |
| <span class="n">offline_params</span><span class="o">=</span><span class="nb">list</span><span class="p">(</span><span class="n">arg_params</span><span class="o">.</span><span class="n">keys</span><span class="p">()),</span> |
| <span class="n">quantized_dtype</span><span class="o">=</span><span class="n">quantized_dtype</span><span class="p">,</span> |
| <span class="n">quantize_mode</span><span class="o">=</span><span class="n">quantize_mode</span><span class="p">,</span> |
| <span class="n">quantize_granularity</span><span class="o">=</span><span class="n">quantize_granularity</span><span class="p">)</span> |
| <span class="n">min_max_dict</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">calib_mode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">calib_mode</span> <span class="o">!=</span> <span class="s1">'none'</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">device</span><span class="p">,</span> <span class="n">Device</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'currently only supports single device, while received </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="n">device</span><span class="p">)</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">calib_data</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'calib_data must be provided when calib_mode=</span><span class="si">{</span><span class="n">calib_mode</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">calib_data</span><span class="p">,</span> <span class="n">mx</span><span class="o">.</span><span class="n">gluon</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'calib_data must be of DataLoader type when calib_mode=</span><span class="si">{</span><span class="n">calib_mode</span><span class="si">}</span><span class="s1">,'</span> |
| <span class="sa">f</span><span class="s1">' while received type </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">calib_data</span><span class="p">))</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| |
| <span class="n">inputs</span> <span class="o">=</span> <span class="p">[</span><span class="n">mx</span><span class="o">.</span><span class="n">sym</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="n">dname</span><span class="p">)</span> <span class="k">for</span> <span class="n">dname</span> <span class="ow">in</span> <span class="n">data_names</span><span class="p">]</span> |
| <span class="n">param_dict</span> <span class="o">=</span> <span class="n">arg_params</span> |
| <span class="n">param_dict</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">aux_params</span><span class="p">)</span> |
| <span class="n">sym_block</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">gluon</span><span class="o">.</span><span class="n">SymbolBlock</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">inputs</span><span class="p">)</span> |
| <span class="n">sym_block</span><span class="o">.</span><span class="n">load_dict</span><span class="p">(</span><span class="n">param_dict</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">calib_mode</span> <span class="o">==</span> <span class="s1">'entropy'</span><span class="p">:</span> |
| <span class="n">collector</span> <span class="o">=</span> <span class="n">_LayerHistogramCollector</span><span class="p">(</span><span class="n">quantized_dtype</span><span class="o">=</span><span class="n">quantized_dtype</span><span class="p">,</span> |
| <span class="n">include_layers</span><span class="o">=</span><span class="n">calib_layers</span><span class="p">,</span> |
| <span class="n">logger</span><span class="o">=</span><span class="n">logger</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">calib_mode</span> <span class="o">==</span> <span class="s1">'naive'</span><span class="p">:</span> |
| <span class="n">collector</span> <span class="o">=</span> <span class="n">_LayerOutputMinMaxCollector</span><span class="p">(</span><span class="n">quantized_dtype</span><span class="o">=</span><span class="n">quantized_dtype</span><span class="p">,</span> |
| <span class="n">include_layers</span><span class="o">=</span><span class="n">calib_layers</span><span class="p">,</span> |
| <span class="n">logger</span><span class="o">=</span><span class="n">logger</span><span class="p">)</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'unknown calibration mode </span><span class="si">{</span><span class="n">calib_mode</span><span class="si">}</span><span class="s1"> received,'</span> |
| <span class="s1">' expected `none`, `naive`, or `entropy`'</span><span class="p">)</span> |
| |
| <span class="n">num_batches</span> <span class="o">=</span> <span class="n">_collect_layer_statistics</span><span class="p">(</span><span class="n">sym_block</span><span class="p">,</span> <span class="n">calib_data</span><span class="p">,</span> <span class="n">collector</span><span class="p">,</span> |
| <span class="nb">len</span><span class="p">(</span><span class="n">inputs</span><span class="p">),</span> <span class="n">num_calib_batches</span><span class="p">,</span> <span class="n">logger</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s1">'Collected layer output min/max values from FP32 model using </span><span class="si">{</span><span class="n">num_batches</span><span class="si">}</span><span class="s1"> batches'</span><span class="p">)</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Performing calibration post collecting operations'</span><span class="p">)</span> |
| |
| <span class="n">min_max_dict</span> <span class="o">=</span> <span class="n">collector</span><span class="o">.</span><span class="n">post_collect</span><span class="p">()</span> |
| <span class="n">qsym</span> <span class="o">=</span> <span class="n">_calibrate_quantized_sym</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">min_max_dict</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Quantizing parameters'</span><span class="p">)</span> |
| <span class="n">qarg_params</span> <span class="o">=</span> <span class="n">_quantize_params</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">min_max_dict</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">qsym</span> <span class="o">=</span> <span class="n">qsym</span><span class="o">.</span><span class="n">as_np_ndarray</span><span class="p">()</span> |
| |
| <span class="k">return</span> <span class="n">qsym</span><span class="p">,</span> <span class="n">qarg_params</span><span class="p">,</span> <span class="n">aux_params</span></div> |
| |
| <div class="viewcode-block" id="quantize_model_onednn"><a class="viewcode-back" href="../../../api/contrib/quantization/index.html#mxnet.contrib.quantization.quantize_model_onednn">[docs]</a><span class="nd">@wrap_ctx_to_device_func</span> |
| <span class="k">def</span> <span class="nf">quantize_model_onednn</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">aux_params</span><span class="p">,</span> <span class="n">data_names</span><span class="o">=</span><span class="p">(</span><span class="s1">'data'</span><span class="p">,),</span> |
| <span class="n">device</span><span class="o">=</span><span class="n">cpu</span><span class="p">(),</span> <span class="n">excluded_sym_names</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">excluded_op_names</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">calib_mode</span><span class="o">=</span><span class="s1">'entropy'</span><span class="p">,</span> <span class="n">calib_data</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">num_calib_batches</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">quantized_dtype</span><span class="o">=</span><span class="s1">'int8'</span><span class="p">,</span> <span class="n">quantize_mode</span><span class="o">=</span><span class="s1">'smart'</span><span class="p">,</span> |
| <span class="n">quantize_granularity</span><span class="o">=</span><span class="s1">'tensor-wise'</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""User-level API for generating a fusion + quantized model from a FP32 model</span> |
| <span class="sd"> w/ or w/o calibration with oneDNN.</span> |
| <span class="sd"> The backend quantized operators are only enabled for Linux systems. Please do not run</span> |
| <span class="sd"> inference using the quantized models on Windows for now.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> all</span> |
| <span class="sd"> :ref:`As in quantize_model<quantize_model_params>`</span> |
| |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> quantized_model: tuple</span> |
| <span class="sd"> A tuple of quantized symbol, quantized arg_params, and aux_params.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">device</span><span class="p">,</span> <span class="n">Device</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'currently only supports single device, while received </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="n">device</span><span class="p">)</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">device</span><span class="o">.</span><span class="n">device_type</span> <span class="o">!=</span> <span class="s1">'cpu'</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'quantize_model_onednn only support Intel cpu platform with oneDNN Backend'</span><span class="p">)</span> |
| |
| <span class="n">sym</span> <span class="o">=</span> <span class="n">sym</span><span class="o">.</span><span class="n">optimize_for</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="s1">'ONEDNN_QUANTIZE'</span><span class="p">)</span> |
| |
| <span class="n">qsym</span><span class="p">,</span> <span class="n">qarg_params</span><span class="p">,</span> <span class="n">aux_params</span> <span class="o">=</span> <span class="n">quantize_model</span><span class="p">(</span><span class="n">sym</span><span class="o">=</span><span class="n">sym</span><span class="p">,</span> <span class="n">arg_params</span><span class="o">=</span><span class="n">arg_params</span><span class="p">,</span> <span class="n">aux_params</span><span class="o">=</span><span class="n">aux_params</span><span class="p">,</span> |
| <span class="n">data_names</span><span class="o">=</span><span class="n">data_names</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">device</span><span class="p">,</span> |
| <span class="n">excluded_sym_names</span><span class="o">=</span><span class="n">excluded_sym_names</span><span class="p">,</span> |
| <span class="n">excluded_op_names</span><span class="o">=</span><span class="n">excluded_op_names</span><span class="p">,</span> |
| <span class="n">calib_mode</span><span class="o">=</span><span class="n">calib_mode</span><span class="p">,</span> <span class="n">calib_data</span><span class="o">=</span><span class="n">calib_data</span><span class="p">,</span> |
| <span class="n">num_calib_batches</span><span class="o">=</span><span class="n">num_calib_batches</span><span class="p">,</span> |
| <span class="n">quantized_dtype</span><span class="o">=</span><span class="n">quantized_dtype</span><span class="p">,</span> <span class="n">quantize_mode</span><span class="o">=</span><span class="n">quantize_mode</span><span class="p">,</span> |
| <span class="n">quantize_granularity</span><span class="o">=</span><span class="n">quantize_granularity</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="n">logger</span><span class="p">)</span> |
| |
| <span class="n">qsym</span> <span class="o">=</span> <span class="n">qsym</span><span class="o">.</span><span class="n">optimize_for</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="s1">'ONEDNN_QUANTIZE'</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">qsym</span><span class="p">,</span> <span class="n">qarg_params</span><span class="p">,</span> <span class="n">aux_params</span></div> |
| |
| <div class="viewcode-block" id="quantize_graph"><a class="viewcode-back" href="../../../api/contrib/quantization/index.html#mxnet.contrib.quantization.quantize_graph">[docs]</a><span class="k">def</span> <span class="nf">quantize_graph</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">aux_params</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">cpu</span><span class="p">(),</span> |
| <span class="n">excluded_sym_names</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">excluded_op_names</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">calib_mode</span><span class="o">=</span><span class="s1">'entropy'</span><span class="p">,</span> <span class="n">quantized_dtype</span><span class="o">=</span><span class="s1">'int8'</span><span class="p">,</span> |
| <span class="n">quantize_mode</span><span class="o">=</span><span class="s1">'full'</span><span class="p">,</span> <span class="n">quantize_granularity</span><span class="o">=</span><span class="s1">'tensor-wise'</span><span class="p">,</span> |
| <span class="n">LayerOutputCollector</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""User-level API for generating a quantized model from a FP32 model w/o calibration</span> |
| <span class="sd"> and a collector for naive or entropy calibration.</span> |
| <span class="sd"> The backend quantized operators are only enabled for Linux systems. Please do not run</span> |
| <span class="sd"> inference using the quantized models on Windows for now.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> sym : Symbol</span> |
| <span class="sd"> Defines the structure of a neural network for FP32 data types.</span> |
| <span class="sd"> device : Device</span> |
| <span class="sd"> Defines the device that users want to run forward propagation on the calibration</span> |
| <span class="sd"> dataset for collecting layer output statistics. Currently, only supports single device.</span> |
| <span class="sd"> arg_params : dict</span> |
| <span class="sd"> Dictionary of name to `NDArray`.</span> |
| <span class="sd"> aux_params : dict</span> |
| <span class="sd"> Dictionary of name to `NDArray`.</span> |
| <span class="sd"> excluded_sym_names : list of strings</span> |
| <span class="sd"> A list of strings representing the names of the symbols that users want to excluding</span> |
| <span class="sd"> from being quantized.</span> |
| <span class="sd"> excluded_op_names : list of strings</span> |
| <span class="sd"> A list of strings representing the names of the operators that users want to excluding</span> |
| <span class="sd"> calib_mode : str</span> |
| <span class="sd"> If calib_mode='none', no calibration will be used and the thresholds for</span> |
| <span class="sd"> requantization after the corresponding layers will be calculated at runtime by</span> |
| <span class="sd"> calling min and max operators. The quantized models generated in this</span> |
| <span class="sd"> mode are normally 10-20% slower than those with calibrations during inference.</span> |
| <span class="sd"> If calib_mode='naive', the min and max values of the layer outputs from a calibration</span> |
| <span class="sd"> dataset will be directly taken as the thresholds for quantization.</span> |
| <span class="sd"> If calib_mode='entropy' (default mode), the thresholds for quantization will be</span> |
| <span class="sd"> derived such that the KL divergence between the distributions of FP32 layer outputs and</span> |
| <span class="sd"> quantized layer outputs is minimized based upon the calibration dataset.</span> |
| <span class="sd"> quantized_dtype : str</span> |
| <span class="sd"> The quantized destination type for input data. Currently support 'int8'</span> |
| <span class="sd"> , 'uint8' and 'auto'. 'auto' means automatically select output type according to calibration result.</span> |
| <span class="sd"> Default value is 'int8'.</span> |
| <span class="sd"> quantize_mode : str</span> |
| <span class="sd"> The mode that quantization pass to apply. Support 'full' and 'smart'.</span> |
| <span class="sd"> 'full' means quantize all operator if possible.</span> |
| <span class="sd"> 'smart' means quantization pass will smartly choice which operator should be quantized.</span> |
| <span class="sd"> quantize_granularity : str</span> |
| <span class="sd"> The granularity of quantization, currently supports 'tensor-wise' and 'channel-wise'</span> |
| <span class="sd"> quantization. The default value is 'tensor-wise'.</span> |
| <span class="sd"> LayerOutputCollector : subclass of CalibrationCollector</span> |
| <span class="sd"> For custom calibration method usage.</span> |
| <span class="sd"> Passed object's include_layers attribute will be feed with names of layers which needs calibration</span> |
| <span class="sd"> logger : Object</span> |
| <span class="sd"> A logging object for printing information during the process of quantization.</span> |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> quantized_model : tuple</span> |
| <span class="sd"> A tuple of quantized symbol, quantized arg_params, aux_params and collector.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">excluded_sym_names</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">excluded_sym_names</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">excluded_sym_names</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'excluded_sym_names must be a list of strings representing'</span> |
| <span class="s1">' the names of the symbols that will not be quantized,'</span> |
| <span class="sa">f</span><span class="s1">' while received type </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">excluded_sym_names</span><span class="p">))</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">device</span><span class="p">,</span> <span class="n">Device</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'currently only supports single device, while received </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="n">device</span><span class="p">)</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'MXNET_QUANTIZATION_VERBOSE'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'1'</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Quantizing graph'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">quantized_dtype</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'int8'</span><span class="p">,</span> <span class="s1">'uint8'</span><span class="p">,</span> <span class="s1">'auto'</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'unknown quantized_dtype </span><span class="si">{</span><span class="n">quantized_dtype</span><span class="si">}</span><span class="s1"> received,'</span> |
| <span class="s1">' expected `int8`, `uint8` or `auto`'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">quantize_granularity</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'tensor-wise'</span><span class="p">,</span> <span class="s1">'channel-wise'</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'unkonwn quantize_granularity </span><span class="si">{</span><span class="n">quantize_granularity</span><span class="si">}</span><span class="s1"> received,'</span> |
| <span class="s1">' expected `tensor-wise` or `channel-wise`.'</span><span class="p">)</span> |
| <span class="n">qsym</span><span class="p">,</span> <span class="n">calib_layers</span> <span class="o">=</span> <span class="n">_quantize_symbol</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">device</span><span class="p">,</span> <span class="n">excluded_symbols</span><span class="o">=</span><span class="n">excluded_sym_names</span><span class="p">,</span> |
| <span class="n">excluded_operators</span><span class="o">=</span><span class="n">excluded_op_names</span><span class="p">,</span> |
| <span class="n">offline_params</span><span class="o">=</span><span class="nb">list</span><span class="p">(</span><span class="n">arg_params</span><span class="o">.</span><span class="n">keys</span><span class="p">()),</span> |
| <span class="n">quantized_dtype</span><span class="o">=</span><span class="n">quantized_dtype</span><span class="p">,</span> |
| <span class="n">quantize_mode</span><span class="o">=</span><span class="n">quantize_mode</span><span class="p">,</span> |
| <span class="n">quantize_granularity</span><span class="o">=</span><span class="n">quantize_granularity</span><span class="p">)</span> |
| |
| <span class="n">collector</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="n">calib_mode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">calib_mode</span> <span class="o">!=</span> <span class="s1">'none'</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">calib_mode</span> <span class="o">==</span> <span class="s1">'entropy'</span><span class="p">:</span> |
| <span class="n">collector</span> <span class="o">=</span> <span class="n">_LayerHistogramCollector</span><span class="p">(</span><span class="n">quantized_dtype</span><span class="o">=</span><span class="n">quantized_dtype</span><span class="p">,</span> |
| <span class="n">include_layers</span><span class="o">=</span><span class="n">calib_layers</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="n">logger</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'Create a layer output collector for entropy calibration.'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">calib_mode</span> <span class="o">==</span> <span class="s1">'naive'</span><span class="p">:</span> |
| <span class="n">collector</span> <span class="o">=</span> <span class="n">_LayerOutputMinMaxCollector</span><span class="p">(</span><span class="n">quantized_dtype</span><span class="o">=</span><span class="n">quantized_dtype</span><span class="p">,</span> |
| <span class="n">include_layers</span><span class="o">=</span><span class="n">calib_layers</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="n">logger</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'Create a layer output minmax collector for naive calibration'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">calib_mode</span> <span class="o">==</span> <span class="s1">'custom'</span> <span class="ow">and</span> <span class="n">LayerOutputCollector</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="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">LayerOutputCollector</span><span class="p">,</span> <span class="n">CalibrationCollector</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'LayerOutputCollecotr must be a subclass of a CalibrationCollector class,'</span> |
| <span class="sa">f</span><span class="s1">' but it is </span><span class="si">{</span><span class="n">LayerOutputCollector</span><span class="o">.</span><span class="vm">__class__</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="n">collector</span> <span class="o">=</span> <span class="n">LayerOutputCollector</span> |
| |
| <span class="c1"># Inject layer names that need calibration to collector</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">collector</span><span class="p">,</span> <span class="s2">"include_layers"</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">collector</span><span class="o">.</span><span class="n">include_layers</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Custom collector has set include_layers attribute. '</span> |
| <span class="s1">'Calibration layers not passed'</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">collector</span><span class="o">.</span><span class="n">include_layers</span> <span class="o">=</span> <span class="n">calib_layers</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span> |
| <span class="s1">'Create a custom layer output minmax collector for calibration'</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'unknown calibration mode </span><span class="si">{</span><span class="n">calib_mode</span><span class="si">}</span><span class="s1"> received,'</span> |
| <span class="s1">' expected `none`, `naive`, `entropy` or `custom`'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Collector created, please use set_monitor_callback'</span> |
| <span class="s1">' to collect calibration information.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Quantizing parameters'</span><span class="p">)</span> |
| <span class="n">qarg_params</span> <span class="o">=</span> <span class="n">_quantize_params</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">min_max_dict</span><span class="o">=</span><span class="p">{})</span> |
| |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">qsym</span> <span class="o">=</span> <span class="n">qsym</span><span class="o">.</span><span class="n">as_np_ndarray</span><span class="p">()</span> |
| |
| <span class="k">return</span> <span class="n">qsym</span><span class="p">,</span> <span class="n">qarg_params</span><span class="p">,</span> <span class="n">aux_params</span><span class="p">,</span> <span class="n">collector</span><span class="p">,</span> <span class="n">calib_layers</span></div> |
| |
| <div class="viewcode-block" id="calib_graph"><a class="viewcode-back" href="../../../api/contrib/quantization/index.html#mxnet.contrib.quantization.calib_graph">[docs]</a><span class="k">def</span> <span class="nf">calib_graph</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">aux_params</span><span class="p">,</span> <span class="n">collector</span><span class="p">,</span> |
| <span class="n">calib_mode</span><span class="o">=</span><span class="s1">'entropy'</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""User-level API for calibrating a quantized model using a filled collector.</span> |
| <span class="sd"> The backend quantized operators are only enabled for Linux systems. Please do not run</span> |
| <span class="sd"> inference using the quantized models on Windows for now.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> qsym : Symbol</span> |
| <span class="sd"> Defines the structure of a neural network for INT8 data types.</span> |
| <span class="sd"> arg_params : dict</span> |
| <span class="sd"> Dictionary of name to `NDArray`.</span> |
| <span class="sd"> aux_params : dict</span> |
| <span class="sd"> Dictionary of name to `NDArray`.</span> |
| <span class="sd"> collector : function</span> |
| <span class="sd"> layer collector for naive or entropy calibration.</span> |
| <span class="sd"> calib_mode : str</span> |
| <span class="sd"> If calib_mode='none', no calibration will be used and the thresholds for</span> |
| <span class="sd"> requantization after the corresponding layers will be calculated at runtime by</span> |
| <span class="sd"> calling min and max operators. The quantized models generated in this</span> |
| <span class="sd"> mode are normally 10-20% slower than those with calibrations during inference.</span> |
| <span class="sd"> If calib_mode='naive', the min and max values of the layer outputs from a calibration</span> |
| <span class="sd"> dataset will be directly taken as the thresholds for quantization.</span> |
| <span class="sd"> If calib_mode='entropy' (default mode), the thresholds for quantization will be</span> |
| <span class="sd"> derived such that the KL divergence between the distributions of FP32 layer outputs and</span> |
| <span class="sd"> quantized layer outputs is minimized based upon the calibration dataset.</span> |
| <span class="sd"> quantized_dtype : str</span> |
| <span class="sd"> The quantized destination type for input data. Currently support 'int8'</span> |
| <span class="sd"> , 'uint8' and 'auto'. 'auto' means automatically select output type according to calibration result.</span> |
| <span class="sd"> Default value is 'int8'.</span> |
| <span class="sd"> logger : Object</span> |
| <span class="sd"> A logging object for printing information during the process of quantization.</span> |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> quantized_model : tuple</span> |
| <span class="sd"> A tuple of calibrated symbol, quantized arg_params, aux_params.</span> |
| <span class="sd"> """</span> |
| <span class="n">min_max_dict</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">calib_mode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">calib_mode</span> <span class="o">!=</span> <span class="s1">'none'</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">calib_mode</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'entropy'</span><span class="p">,</span> <span class="s1">'naive'</span><span class="p">,</span> <span class="s1">'custom'</span><span class="p">):</span> |
| <span class="n">min_max_dict</span> <span class="o">=</span> <span class="n">collector</span><span class="o">.</span><span class="n">post_collect</span><span class="p">()</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s1">'unknown calibration mode </span><span class="si">{</span><span class="n">calib_mode</span><span class="si">}</span><span class="s1"> received,'</span> |
| <span class="s1">' expected `none`, `naive`, `entropy` or `custom`'</span><span class="p">)</span> |
| <span class="n">qsym</span> <span class="o">=</span> <span class="n">_calibrate_quantized_sym</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">min_max_dict</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Please set calibration mode to naive, entropy or custom (with custom CalibrationCollector)'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Quantizing parameters'</span><span class="p">)</span> |
| <span class="n">qarg_params</span> <span class="o">=</span> <span class="n">_quantize_params</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">arg_params</span><span class="p">,</span> <span class="n">min_max_dict</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">qsym</span> <span class="o">=</span> <span class="n">qsym</span><span class="o">.</span><span class="n">as_np_ndarray</span><span class="p">()</span> |
| |
| <span class="k">return</span> <span class="n">qsym</span><span class="p">,</span> <span class="n">qarg_params</span><span class="p">,</span> <span class="n">aux_params</span></div> |
| |
| <div class="viewcode-block" id="quantize_net"><a class="viewcode-back" href="../../../api/contrib/quantization/index.html#mxnet.contrib.quantization.quantize_net">[docs]</a><span class="nd">@wrap_ctx_to_device_func</span> |
| <span class="k">def</span> <span class="nf">quantize_net</span><span class="p">(</span><span class="n">network</span><span class="p">,</span> <span class="n">quantized_dtype</span><span class="o">=</span><span class="s1">'auto'</span><span class="p">,</span> <span class="n">quantize_mode</span><span class="o">=</span><span class="s1">'full'</span><span class="p">,</span> <span class="n">quantize_granularity</span><span class="o">=</span><span class="s1">'tensor-wise'</span><span class="p">,</span> |
| <span class="n">exclude_layers</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">exclude_layers_match</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">exclude_operators</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">calib_data</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">data_shapes</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">calib_mode</span><span class="o">=</span><span class="s1">'none'</span><span class="p">,</span> |
| <span class="n">num_calib_batches</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">cpu</span><span class="p">(),</span> <span class="n">LayerOutputCollector</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""User-level API for Gluon users to generate a quantized SymbolBlock from a FP32 HybridBlock w/ or w/o calibration.</span> |
| <span class="sd"> The backend quantized operators are only enabled for Linux systems. Please do not run</span> |
| <span class="sd"> inference using the quantized models on Windows for now.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> network : Gluon HybridBlock</span> |
| <span class="sd"> Defines the structure of a neural network for FP32 data types.</span> |
| <span class="sd"> quantized_dtype : str</span> |
| <span class="sd"> The quantized destination type for input data. Currently support 'int8'</span> |
| <span class="sd"> , 'uint8' and 'auto'. 'auto' means automatically select output type according to calibration result.</span> |
| <span class="sd"> Default value is 'int8'.</span> |
| <span class="sd"> quantize_mode : str</span> |
| <span class="sd"> The mode that quantization pass to apply. Support 'full' and 'smart'.</span> |
| <span class="sd"> 'full' means quantize all operator if possible.</span> |
| <span class="sd"> 'smart' means quantization pass will smartly choice which operator should be quantized.</span> |
| <span class="sd"> quantize_granularity: str</span> |
| <span class="sd"> The granularity of quantization, currently supports 'tensor-wise' and 'channel-wise'</span> |
| <span class="sd"> quantization. The default value is 'tensor-wise'.</span> |
| <span class="sd"> exclude_layers : list of strings</span> |
| <span class="sd"> A list of strings representing the names of the symbols that users want to excluding</span> |
| <span class="sd"> exclude_layers_match : list of strings</span> |
| <span class="sd"> A list of strings wildcard matching the names of the symbols that users want to excluding</span> |
| <span class="sd"> from being quantized.</span> |
| <span class="sd"> exclude_operators : list of strings</span> |
| <span class="sd"> A list of strings representing the names of the operators that users want to excluding</span> |
| <span class="sd"> calib_data : gluon.DataLoader</span> |
| <span class="sd"> A iterable data loading object.</span> |
| <span class="sd"> data_shapes : list of DataDesc or list of tuple</span> |
| <span class="sd"> A list of data shapes. Required if calib_data is not provided. In case of tuples,</span> |
| <span class="sd"> the names of inputs are generated.</span> |
| <span class="sd"> calib_mode : str</span> |
| <span class="sd"> If calib_mode='none', no calibration will be used and the thresholds for</span> |
| <span class="sd"> requantization after the corresponding layers will be calculated at runtime by</span> |
| <span class="sd"> calling min and max operators. The quantized models generated in this</span> |
| <span class="sd"> mode are normally 10-20% slower than those with calibrations during inference.</span> |
| <span class="sd"> If calib_mode='naive', the min and max values of the layer outputs from a calibration</span> |
| <span class="sd"> dataset will be directly taken as the thresholds for quantization.</span> |
| <span class="sd"> If calib_mode='entropy' (default mode), the thresholds for quantization will be</span> |
| <span class="sd"> derived such that the KL divergence between the distributions of FP32 layer outputs and</span> |
| <span class="sd"> quantized layer outputs is minimized based upon the calibration dataset.</span> |
| <span class="sd"> If calib_mode='custom', the provided LayerOutputCollector will be used to determine</span> |
| <span class="sd"> the thresholds for quantization. For more information refer to CalibrationCollector</span> |
| <span class="sd"> documentation.</span> |
| <span class="sd"> num_calib_batches : int or None</span> |
| <span class="sd"> The maximum number of batches that user would like to use for calibration. If not provided,</span> |
| <span class="sd"> the whole calibration dataset will be used.</span> |
| <span class="sd"> device : Device</span> |
| <span class="sd"> Defines the device that users want to run forward propagation on the calibration</span> |
| <span class="sd"> dataset for collecting layer output statistics. Currently, only supports single device.</span> |
| <span class="sd"> LayerOutputCollector : subclass of CalibrationCollector</span> |
| <span class="sd"> For `custom` calibration method usage.</span> |
| <span class="sd"> Passed object's include_layers attribute will be feed with names of layers which needs calibration</span> |
| <span class="sd"> logger : Object</span> |
| <span class="sd"> A logging object for printing information during the process of quantization.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> network : Gluon SymbolBlock</span> |
| <span class="sd"> Defines the structure of a neural network for INT8 data types.</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">..gluon</span> <span class="kn">import</span> <span class="n">SymbolBlock</span> |
| |
| <span class="k">if</span> <span class="n">device</span> <span class="o">!=</span> <span class="n">mx</span><span class="o">.</span><span class="n">cpu</span><span class="p">():</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Quantization currently supports only CPU device'</span><span class="p">)</span> |
| <span class="n">backend</span> <span class="o">=</span> <span class="s1">'ONEDNN_QUANTIZE'</span> |
| |
| <span class="n">network</span><span class="o">.</span><span class="n">hybridize</span><span class="p">(</span><span class="n">static_alloc</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">static_shape</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> |
| <span class="n">data_types</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">if</span> <span class="n">data_shapes</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">calib_data</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'At least one of data_shapes or calib_data has to be provided.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">calib_data</span><span class="p">,</span> <span class="n">mx</span><span class="o">.</span><span class="n">gluon</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span><span class="p">):</span> |
| <span class="n">x</span> <span class="o">=</span> <span class="nb">iter</span><span class="p">(</span><span class="n">calib_data</span><span class="p">)</span> |
| <span class="n">batch</span> <span class="o">=</span> <span class="nb">next</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="n">data_shapes</span> <span class="o">=</span> <span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> |
| <span class="n">data_types</span> <span class="o">=</span> <span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">data_shapes</span> <span class="o">=</span> <span class="p">[</span><span class="n">batch</span><span class="o">.</span><span class="n">shape</span><span class="p">]</span> |
| <span class="n">data_types</span> <span class="o">=</span> <span class="p">[</span><span class="n">batch</span><span class="o">.</span><span class="n">dtype</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'calib_data expects mx.gluon.data.DataLoader'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">data_types</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">data_types</span> <span class="o">=</span> <span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">data_shapes</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">mx_real_t</span><span class="p">)</span> |
| |
| <span class="n">data_descs</span> <span class="o">=</span> <span class="n">_generate_list_of_data_desc</span><span class="p">(</span><span class="n">data_shapes</span><span class="p">,</span> <span class="n">data_types</span><span class="p">)</span> |
| |
| <span class="n">num_inputs</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">data_descs</span><span class="p">)</span> |
| <span class="n">data_nd</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">arr_fn</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">np</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">mx</span><span class="o">.</span><span class="n">nd</span> |
| <span class="n">data_nd</span> <span class="o">=</span> <span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">data_descs</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">d</span><span class="p">,</span> <span class="n">F</span><span class="o">=</span><span class="n">arr_fn</span><span class="p">:</span> <span class="n">F</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="n">d</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">d</span><span class="o">.</span><span class="n">dtype</span><span class="p">))</span> |
| |
| <span class="k">while</span> <span class="kc">True</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">network</span><span class="p">(</span><span class="o">*</span><span class="n">data_nd</span><span class="p">)</span> |
| <span class="k">except</span> <span class="p">(</span><span class="ne">ValueError</span><span class="p">,</span> <span class="ne">TypeError</span><span class="p">)</span> <span class="k">as</span> <span class="n">err</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="n">err</span><span class="p">)</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">"Deduced input data descriptors failed to run forward pass."</span> |
| <span class="s2">" Trying again with one less input."</span><span class="p">)</span> |
| <span class="k">del</span> <span class="n">data_nd</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> |
| <span class="n">num_inputs</span> <span class="o">-=</span> <span class="mi">1</span> |
| <span class="n">data_shapes</span> <span class="o">=</span> <span class="p">[</span><span class="n">b</span><span class="o">.</span><span class="n">shape</span> <span class="k">for</span> <span class="n">b</span> <span class="ow">in</span> <span class="n">data_nd</span><span class="p">]</span> |
| <span class="n">data_types</span> <span class="o">=</span> <span class="p">[</span><span class="n">b</span><span class="o">.</span><span class="n">dtype</span> <span class="k">for</span> <span class="n">b</span> <span class="ow">in</span> <span class="n">data_nd</span><span class="p">]</span> |
| <span class="n">data_descs</span> <span class="o">=</span> <span class="n">_generate_list_of_data_desc</span><span class="p">(</span><span class="n">data_shapes</span><span class="p">,</span> <span class="n">data_types</span><span class="p">)</span> |
| <span class="k">continue</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">break</span> |
| |
| <span class="n">symnet</span><span class="p">,</span> <span class="n">params</span> <span class="o">=</span> <span class="n">network</span><span class="o">.</span><span class="n">export</span><span class="p">(</span><span class="kc">None</span><span class="p">)</span> |
| <span class="n">symnet</span> <span class="o">=</span> <span class="n">symnet</span><span class="o">.</span><span class="n">optimize_for</span><span class="p">(</span><span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">is_np_array</span><span class="p">():</span> |
| <span class="n">symnet</span> <span class="o">=</span> <span class="n">symnet</span><span class="o">.</span><span class="n">as_np_ndarray</span><span class="p">()</span> |
| |
| <span class="n">args</span><span class="p">,</span> <span class="n">auxs</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(),</span> <span class="nb">dict</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">params</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">ptype</span><span class="p">,</span> <span class="n">pname</span> <span class="o">=</span> <span class="n">k</span><span class="p">[:</span><span class="mi">3</span><span class="p">],</span> <span class="n">k</span><span class="p">[</span><span class="mi">4</span><span class="p">:]</span> |
| <span class="k">if</span> <span class="n">ptype</span> <span class="o">==</span> <span class="s2">"arg"</span><span class="p">:</span> |
| <span class="n">args</span><span class="p">[</span><span class="n">pname</span><span class="p">]</span> <span class="o">=</span> <span class="n">v</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">auxs</span><span class="p">[</span><span class="n">pname</span><span class="p">]</span> <span class="o">=</span> <span class="n">v</span> |
| |
| <span class="k">if</span> <span class="n">exclude_layers</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">exclude_layers</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="n">exclude_layers_match</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">exclude_layers_match</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">if</span> <span class="n">exclude_operators</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">exclude_operators</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">name_match</span> <span class="ow">in</span> <span class="n">exclude_layers_match</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">layers</span> <span class="ow">in</span> <span class="nb">list</span><span class="p">(</span><span class="n">symnet</span><span class="o">.</span><span class="n">get_internals</span><span class="p">()):</span> |
| <span class="k">if</span> <span class="n">layers</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="n">name_match</span><span class="p">)</span> <span class="o">!=</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span> |
| <span class="n">exclude_layers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">layers</span><span class="o">.</span><span class="n">name</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s1">'These layers have been excluded </span><span class="si">{</span><span class="n">exclude_layers</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| |
| <span class="n">qsym</span><span class="p">,</span> <span class="n">qarg_params</span><span class="p">,</span> <span class="n">aux_params</span><span class="p">,</span> <span class="n">collector</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">quantize_graph</span><span class="p">(</span> |
| <span class="n">sym</span><span class="o">=</span><span class="n">symnet</span><span class="p">,</span> <span class="n">arg_params</span><span class="o">=</span><span class="n">args</span><span class="p">,</span> <span class="n">aux_params</span><span class="o">=</span><span class="n">auxs</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">device</span><span class="p">,</span> |
| <span class="n">excluded_sym_names</span><span class="o">=</span><span class="n">exclude_layers</span><span class="p">,</span> <span class="n">excluded_op_names</span><span class="o">=</span><span class="n">exclude_operators</span><span class="p">,</span> |
| <span class="n">calib_mode</span><span class="o">=</span><span class="n">calib_mode</span><span class="p">,</span> <span class="n">quantized_dtype</span><span class="o">=</span><span class="n">quantized_dtype</span><span class="p">,</span> <span class="n">quantize_mode</span><span class="o">=</span><span class="n">quantize_mode</span><span class="p">,</span> |
| <span class="n">quantize_granularity</span><span class="o">=</span><span class="n">quantize_granularity</span><span class="p">,</span> <span class="n">LayerOutputCollector</span><span class="o">=</span><span class="n">LayerOutputCollector</span><span class="p">,</span> |
| <span class="n">logger</span><span class="o">=</span><span class="n">logger</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">calib_mode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">calib_mode</span> <span class="o">!=</span> <span class="s1">'none'</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">device</span><span class="p">,</span> <span class="n">Device</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="sa">f</span><span class="s1">'currently only supports single device, while received </span><span class="si">{</span><span class="nb">str</span><span class="p">(</span><span class="n">device</span><span class="p">)</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">calib_data</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="sa">f</span><span class="s1">'calib_data must be provided when calib_mode=</span><span class="si">{</span><span class="n">calib_mode</span><span class="si">}</span><span class="s1">'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">calib_mode</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'naive'</span><span class="p">,</span> <span class="s1">'entropy'</span><span class="p">,</span> <span class="s1">'custom'</span><span class="p">]:</span> |
| <span class="n">inputs</span> <span class="o">=</span> <span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">data_descs</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">dd</span><span class="p">:</span> <span class="n">mx</span><span class="o">.</span><span class="n">sym</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="n">dd</span><span class="o">.</span><span class="n">name</span><span class="p">))</span> |
| <span class="n">calib_net</span> <span class="o">=</span> <span class="n">SymbolBlock</span><span class="p">(</span><span class="n">symnet</span><span class="p">,</span> <span class="n">inputs</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">calib_net</span><span class="o">.</span><span class="n">collect_params</span><span class="p">()</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">v</span><span class="o">.</span><span class="n">grad_req</span> <span class="o">=</span> <span class="s1">'null'</span> |
| |
| <span class="n">calib_net</span><span class="o">.</span><span class="n">load_dict</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">cast_dtype</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">dtype_source</span><span class="o">=</span><span class="s1">'saved'</span><span class="p">)</span> |
| <span class="n">calib_net</span><span class="o">.</span><span class="n">hybridize</span><span class="p">(</span><span class="n">static_alloc</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">static_shape</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> |
| <span class="n">num_batches</span> <span class="o">=</span> <span class="n">_collect_layer_statistics</span><span class="p">(</span><span class="n">calib_net</span><span class="p">,</span> <span class="n">calib_data</span><span class="p">,</span> <span class="n">collector</span><span class="p">,</span> <span class="n">num_inputs</span><span class="p">,</span> |
| <span class="n">num_calib_batches</span><span class="p">,</span> <span class="n">logger</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">logger</span><span class="p">:</span> |
| <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="sa">f</span><span class="s1">'Collected layer output values from FP32 model using </span><span class="si">{</span><span class="n">num_batches</span><span class="si">}</span><span class="s1"> batches'</span><span class="p">)</span> |
| |
| <span class="n">qsym</span><span class="p">,</span> <span class="n">qarg_params</span><span class="p">,</span> <span class="n">aux_params</span> <span class="o">=</span> <span class="n">calib_graph</span><span class="p">(</span> |
| <span class="n">qsym</span><span class="o">=</span><span class="n">qsym</span><span class="p">,</span> <span class="n">arg_params</span><span class="o">=</span><span class="n">args</span><span class="p">,</span> <span class="n">aux_params</span><span class="o">=</span><span class="n">auxs</span><span class="p">,</span> <span class="n">collector</span><span class="o">=</span><span class="n">collector</span><span class="p">,</span> |
| <span class="n">calib_mode</span><span class="o">=</span><span class="n">calib_mode</span><span class="p">,</span> <span class="n">logger</span><span class="o">=</span><span class="n">logger</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'calib_mode has to be one of: naive, entropy, custom'</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="n">calib_mode</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">calib_mode</span> <span class="o">==</span> <span class="s1">'none'</span><span class="p">:</span> |
| <span class="n">inputs</span> <span class="o">=</span> <span class="n">_multilist_iterator</span><span class="p">(</span><span class="n">data_descs</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">dd</span><span class="p">:</span> <span class="n">mx</span><span class="o">.</span><span class="n">sym</span><span class="o">.</span><span class="n">var</span><span class="p">(</span><span class="n">dd</span><span class="o">.</span><span class="n">name</span><span class="p">))</span> |
| |
| <span class="n">net</span> <span class="o">=</span> <span class="n">SymbolBlock</span><span class="p">(</span><span class="n">qsym</span><span class="p">,</span> <span class="n">inputs</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">net</span><span class="o">.</span><span class="n">collect_params</span><span class="p">()</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">v</span><span class="o">.</span><span class="n">grad_req</span> <span class="o">=</span> <span class="s1">'null'</span> |
| |
| <span class="n">all_params</span> <span class="o">=</span> <span class="p">{(</span><span class="sa">f</span><span class="s1">'arg:</span><span class="si">{</span><span class="n">k</span><span class="si">}</span><span class="s1">'</span><span class="p">):</span> <span class="n">v</span><span class="o">.</span><span class="n">as_in_context</span><span class="p">(</span><span class="n">cpu</span><span class="p">())</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">qarg_params</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span> |
| <span class="n">all_params</span><span class="o">.</span><span class="n">update</span><span class="p">({(</span><span class="sa">f</span><span class="s1">'aux:</span><span class="si">{</span><span class="n">k</span><span class="si">}</span><span class="s1">'</span><span class="p">):</span> <span class="n">v</span><span class="o">.</span><span class="n">as_in_context</span><span class="p">(</span><span class="n">cpu</span><span class="p">())</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">aux_params</span><span class="o">.</span><span class="n">items</span><span class="p">()})</span> |
| <span class="n">net</span><span class="o">.</span><span class="n">load_dict</span><span class="p">(</span><span class="n">all_params</span><span class="p">,</span> <span class="n">cast_dtype</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">dtype_source</span><span class="o">=</span><span class="s1">'saved'</span><span class="p">)</span> |
| <span class="n">net</span><span class="o">.</span><span class="n">optimize_for</span><span class="p">(</span><span class="n">data_nd</span><span class="p">,</span> <span class="n">backend</span><span class="o">=</span><span class="n">backend</span><span class="p">,</span> <span class="n">skip_infer</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">net</span></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/mxnet/issues">Github Issues</a></li> |
| <li><a href="https://github.com/apache/mxnet/projects">Projects</a></li> |
| <li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li> |
| <li><a href="/community">Contribute To MXNet</a></li> |
| </ul> |
| </div> |
| |
| <div class="col-4"><ul class="social-media-list"><li><a href="https://github.com/apache/mxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#github"></use></svg> <span class="username">apache/mxnet</span></a></li><li><a href="https://www.twitter.com/apachemxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#twitter"></use></svg> <span class="username">apachemxnet</span></a></li><li><a href="https://youtube.com/apachemxnet"><svg class="svg-icon"><use xlink:href="../../../_static/minima-social-icons.svg#youtube"></use></svg> <span class="username">apachemxnet</span></a></li></ul> |
| </div> |
| |
| <div class="col-4 footer-text"> |
| <p>A flexible and efficient library for deep learning.</p> |
| </div> |
| </div> |
| </div> |
| </footer> |
| |
| <footer class="site-footer2"> |
| <div class="wrapper"> |
| <div class="row"> |
| <div class="col-3"> |
| <img src="../../../_static/apache_incubator_logo.png" class="footer-logo col-2"> |
| </div> |
| <div class="footer-bottom-warning col-9"> |
| <p>Apache MXNet is an effort undergoing incubation at <a href="http://www.apache.org/">The Apache Software Foundation</a> (ASF), <span style="font-weight:bold">sponsored by the <i>Apache Incubator</i></span>. Incubation is required |
| of all newly accepted projects until a further review indicates that the infrastructure, |
| communications, and decision making process have stabilized in a manner consistent with other |
| successful ASF projects. While incubation status is not necessarily a reflection of the completeness |
| or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF. |
| </p><p>"Copyright © 2017-2018, The Apache Software Foundation Apache MXNet, MXNet, Apache, the Apache |
| feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the |
| Apache Software Foundation."</p> |
| </div> |
| </div> |
| </div> |
| </footer> |
| |
| </body> |
| </html> |
