Google Git
Sign in
apache / mxnet-site / 82a1adfef83e5bbd9e128754f56a2a2e83809347 / . / versions / 1.9.1 / api / python / docs / _modules / mxnet / gluon / nn / basic_layers.html
blob: 6aacee60281bda535d8a4b30675972df44091ede [file] [log] [blame]
<!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;
}
.dropdown-caret-path {
fill: #FFFFFF;
}
</style>
<title>mxnet.gluon.nn.basic_layers &#8212; 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>
<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="/versions/1.9.1/"><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="/versions/1.9.1/get_started">Get Started</a>
<a class="page-link" href="/versions/1.9.1/features">Features</a>
<a class="page-link" href="/versions/1.9.1/ecosystem">Ecosystem</a>
<a class="page-link page-current" href="/versions/1.9.1/api">Docs & Tutorials</a>
<a class="page-link" href="/versions/1.9.1/trusted_by">Trusted By</a>
<a class="page-link" href="https://github.com/apache/incubator-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">1.9.1
<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" href="/">master</a><br>
<a class="dropdown-option-active" 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.gluon.nn.basic_layers</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>
</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/1-ndarray.html">Manipulate data with <code class="docutils literal notranslate"><span class="pre">ndarray</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/2-nn.html">Create a neural network</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/3-autograd.html">Automatic differentiation with <code class="docutils literal notranslate"><span class="pre">autograd</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/4-train.html">Train the neural network</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/5-predict.html">Predict with a pre-trained model</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/6-use_gpus.html">Use GPUs</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/getting-started/to-mxnet/index.html">Moving to MXNet from Other Frameworks</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/to-mxnet/pytorch.html">PyTorch vs Apache MXNet</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/getting-started/gluon_from_experiment_to_deployment.html">Gluon: from experiment to deployment</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/getting-started/logistic_regression_explained.html">Logistic regression explained</a></li>
<li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/image/mnist.html">MNIST</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/packages/index.html">Packages</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/packages/autograd/index.html">Automatic Differentiation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/packages/gluon/index.html">Gluon</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/index.html">Blocks</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/custom-layer.html">Custom Layers</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/custom_layer_beginners.html">Customer Layers (Beginners)</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/hybridize.html">Hybridize</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/init.html">Initialization</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/naming.html">Parameter and Block Naming</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/nn.html">Layers and Blocks</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/parameters.html">Parameter Management</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/activations/activations.html">Activation Blocks</a></li>
</ul>
</li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/index.html">Data Tutorials</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/data_augmentation.html">Image Augmentation</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/data_augmentation.html#Spatial-Augmentation">Spatial Augmentation</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/data_augmentation.html#Color-Augmentation">Color Augmentation</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/data_augmentation.html#Composed-Augmentations">Composed Augmentations</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/datasets.html">Gluon <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-custom-Datasets">Using own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/datasets.html#Appendix:-Upgrading-from-Module-DataIter-to-Gluon-DataLoader">Appendix: Upgrading from Module <code class="docutils literal notranslate"><span class="pre">DataIter</span></code> to Gluon <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li>
</ul>
</li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/gluon/image/index.html">Image Tutorials</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/image/image-augmentation.html">Image Augmentation</a></li>
<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>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/image/pretrained_models.html">Using pre-trained models in MXNet</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/ndarray/index.html">NDArray</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/01-ndarray-intro.html">An Intro: Manipulate Data the MXNet Way with NDArray</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/02-ndarray-operations.html">NDArray Operations</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/03-ndarray-contexts.html">NDArray Contexts</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/gotchas_numpy_in_mxnet.html">Gotchas using NumPy in Apache MXNet</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/index.html">Tutorials</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/csr.html">CSRNDArray - NDArray in Compressed Sparse Row Storage Format</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/row_sparse.html">RowSparseNDArray - NDArray for Sparse Gradient Updates</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/train.html">Train a Linear Regression Model with Sparse Symbols</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/train_gluon.html">Sparse NDArrays with Gluon</a></li>
</ul>
</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 internal" href="../../../../tutorials/packages/onnx/super_resolution.html">Importing an ONNX model into MXNet</a></li>
<li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html">Export ONNX Models</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/packages/optimizer/index.html">Optimizers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/packages/viz/index.html">Visualization</a><ul>
<li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/visualize_graph">Visualize networks</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/performance/index.html">Performance</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/performance/compression/index.html">Compression</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/performance/compression/int8.html">Deploy with int-8</a></li>
<li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/float16">Float16</a></li>
<li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/gradient_compression">Gradient Compression</a></li>
<li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html">GluonCV with Quantized Models</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/performance/backend/index.html">Accelerated Backend Tools</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/performance/backend/mkldnn/index.html">Intel MKL-DNN</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/performance/backend/mkldnn/mkldnn_quantization.html">Quantize with MKL-DNN backend</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/performance/backend/mkldnn/mkldnn_quantization.html#Improving-accuracy-with-Intel®-Neural-Compressor">Improving accuracy with Intel® Neural Compressor</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/performance/backend/mkldnn/mkldnn_readme.html">Install MXNet with MKL-DNN</a></li>
</ul>
</li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/performance/backend/tensorrt/index.html">TensorRT</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/performance/backend/tensorrt/tensorrt.html">Optimizing Deep Learning Computation Graphs with TensorRT</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>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/deploy/inference/scala.html">Deploy into a Java or Scala Environment</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/deploy/inference/wine_detector.html">Real-time Object Detection with MXNet On The Raspberry Pi</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/custom_layer.html">Custom Layers</a></li>
<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>
</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/ndarray/index.html">mxnet.ndarray</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/ndarray.html">ndarray</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/contrib/index.html">ndarray.contrib</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/image/index.html">ndarray.image</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/linalg/index.html">ndarray.linalg</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/op/index.html">ndarray.op</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/random/index.html">ndarray.random</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/register/index.html">ndarray.register</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/sparse/index.html">ndarray.sparse</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/utils/index.html">ndarray.utils</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/gluon/index.html">mxnet.gluon</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/block.html">gluon.Block</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/hybrid_block.html">gluon.HybridBlock</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/symbol_block.html">gluon.SymbolBlock</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/constant.html">gluon.Constant</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/parameter.html">gluon.Parameter</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/parameter_dict.html">gluon.ParameterDict</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/trainer.html">gluon.Trainer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/contrib/index.html">gluon.contrib</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/data/index.html">gluon.data</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../api/gluon/data/vision/index.html">data.vision</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../api/gluon/data/vision/datasets/index.html">vision.datasets</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../api/gluon/data/vision/transforms/index.html">vision.transforms</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/loss/index.html">gluon.loss</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/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/metric/index.html">mxnet.metric</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/kvstore/index.html">mxnet.kvstore</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/symbol/index.html">mxnet.symbol</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/symbol.html">symbol</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/contrib/index.html">symbol.contrib</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/image/index.html">symbol.image</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/linalg/index.html">symbol.linalg</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/op/index.html">symbol.op</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/random/index.html">symbol.random</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/register/index.html">symbol.register</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/sparse/index.html">symbol.sparse</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/module/index.html">mxnet.module</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/contrib/index.html">mxnet.contrib</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/autograd/index.html">contrib.autograd</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/io/index.html">contrib.io</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/ndarray/index.html">contrib.ndarray</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/onnx/index.html">contrib.onnx</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/quantization/index.html">contrib.quantization</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/symbol/index.html">contrib.symbol</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/tensorboard/index.html">contrib.tensorboard</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/tensorrt/index.html">contrib.tensorrt</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/text/index.html">contrib.text</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/mxnet/index.html">mxnet</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/attribute/index.html">mxnet.attribute</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/base/index.html">mxnet.base</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/callback/index.html">mxnet.callback</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/context/index.html">mxnet.context</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/engine/index.html">mxnet.engine</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/executor/index.html">mxnet.executor</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/executor_manager/index.html">mxnet.executor_manager</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/image/index.html">mxnet.image</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/io/index.html">mxnet.io</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/kvstore_server/index.html">mxnet.kvstore_server</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/libinfo/index.html">mxnet.libinfo</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/log/index.html">mxnet.log</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/model/index.html">mxnet.model</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/monitor/index.html">mxnet.monitor</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/name/index.html">mxnet.name</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/notebook/index.html">mxnet.notebook</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/operator/index.html">mxnet.operator</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/profiler/index.html">mxnet.profiler</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/random/index.html">mxnet.random</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/recordio/index.html">mxnet.recordio</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/registry/index.html">mxnet.registry</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/rtc/index.html">mxnet.rtc</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/runtime/index.html">mxnet.runtime</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/test_utils/index.html">mxnet.test_utils</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/torch/index.html">mxnet.torch</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/util/index.html">mxnet.util</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/visualization/index.html">mxnet.visualization</a></li>
</ul>
</li>
</ul>
</li>
</ul>
</nav>
</div>
</header>
<main class="mdl-layout__content" tabIndex="0">
<script type="text/javascript" src="../../../../_static/sphinx_materialdesign_theme.js "></script>
<script type="text/javascript" src="../../../../_static/feedback.js"></script>
<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/1-ndarray.html">Manipulate data with <code class="docutils literal notranslate"><span class="pre">ndarray</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/2-nn.html">Create a neural network</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/3-autograd.html">Automatic differentiation with <code class="docutils literal notranslate"><span class="pre">autograd</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/4-train.html">Train the neural network</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/5-predict.html">Predict with a pre-trained model</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/crash-course/6-use_gpus.html">Use GPUs</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/getting-started/to-mxnet/index.html">Moving to MXNet from Other Frameworks</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/getting-started/to-mxnet/pytorch.html">PyTorch vs Apache MXNet</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/getting-started/gluon_from_experiment_to_deployment.html">Gluon: from experiment to deployment</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/getting-started/logistic_regression_explained.html">Logistic regression explained</a></li>
<li class="toctree-l3"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/packages/gluon/image/mnist.html">MNIST</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/packages/index.html">Packages</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/packages/autograd/index.html">Automatic Differentiation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/packages/gluon/index.html">Gluon</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/index.html">Blocks</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/custom-layer.html">Custom Layers</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/custom_layer_beginners.html">Customer Layers (Beginners)</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/hybridize.html">Hybridize</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/init.html">Initialization</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/naming.html">Parameter and Block Naming</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/nn.html">Layers and Blocks</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/parameters.html">Parameter Management</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/save_load_params.html">Saving and Loading Gluon Models</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/blocks/activations/activations.html">Activation Blocks</a></li>
</ul>
</li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/index.html">Data Tutorials</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/data_augmentation.html">Image Augmentation</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/data_augmentation.html#Spatial-Augmentation">Spatial Augmentation</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/data_augmentation.html#Color-Augmentation">Color Augmentation</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/data_augmentation.html#Composed-Augmentations">Composed Augmentations</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/datasets.html">Gluon <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s and <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-included-Datasets">Using own data with included <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/datasets.html#Using-own-data-with-custom-Datasets">Using own data with custom <code class="docutils literal notranslate"><span class="pre">Dataset</span></code>s</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/data/datasets.html#Appendix:-Upgrading-from-Module-DataIter-to-Gluon-DataLoader">Appendix: Upgrading from Module <code class="docutils literal notranslate"><span class="pre">DataIter</span></code> to Gluon <code class="docutils literal notranslate"><span class="pre">DataLoader</span></code></a></li>
</ul>
</li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/gluon/image/index.html">Image Tutorials</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/image/image-augmentation.html">Image Augmentation</a></li>
<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>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/gluon/image/pretrained_models.html">Using pre-trained models in MXNet</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/ndarray/index.html">NDArray</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/01-ndarray-intro.html">An Intro: Manipulate Data the MXNet Way with NDArray</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/02-ndarray-operations.html">NDArray Operations</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/03-ndarray-contexts.html">NDArray Contexts</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/gotchas_numpy_in_mxnet.html">Gotchas using NumPy in Apache MXNet</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/index.html">Tutorials</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/csr.html">CSRNDArray - NDArray in Compressed Sparse Row Storage Format</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/row_sparse.html">RowSparseNDArray - NDArray for Sparse Gradient Updates</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/train.html">Train a Linear Regression Model with Sparse Symbols</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/packages/ndarray/sparse/train_gluon.html">Sparse NDArrays with Gluon</a></li>
</ul>
</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 internal" href="../../../../tutorials/packages/onnx/super_resolution.html">Importing an ONNX model into MXNet</a></li>
<li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/python/docs/tutorials/deploy/export/onnx.html">Export ONNX Models</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/packages/optimizer/index.html">Optimizers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/packages/viz/index.html">Visualization</a><ul>
<li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/visualize_graph">Visualize networks</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../tutorials/performance/index.html">Performance</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/performance/compression/index.html">Compression</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/performance/compression/int8.html">Deploy with int-8</a></li>
<li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/float16">Float16</a></li>
<li class="toctree-l4"><a class="reference external" href="https://mxnet.apache.org/api/faq/gradient_compression">Gradient Compression</a></li>
<li class="toctree-l4"><a class="reference external" href="https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html">GluonCV with Quantized Models</a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../tutorials/performance/backend/index.html">Accelerated Backend Tools</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/performance/backend/mkldnn/index.html">Intel MKL-DNN</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/performance/backend/mkldnn/mkldnn_quantization.html">Quantize with MKL-DNN backend</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/performance/backend/mkldnn/mkldnn_quantization.html#Improving-accuracy-with-Intel®-Neural-Compressor">Improving accuracy with Intel® Neural Compressor</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/performance/backend/mkldnn/mkldnn_readme.html">Install MXNet with MKL-DNN</a></li>
</ul>
</li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/performance/backend/tensorrt/index.html">TensorRT</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../tutorials/performance/backend/tensorrt/tensorrt.html">Optimizing Deep Learning Computation Graphs with TensorRT</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>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/deploy/inference/scala.html">Deploy into a Java or Scala Environment</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../../../tutorials/deploy/inference/wine_detector.html">Real-time Object Detection with MXNet On The Raspberry Pi</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/custom_layer.html">Custom Layers</a></li>
<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>
</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/ndarray/index.html">mxnet.ndarray</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/ndarray.html">ndarray</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/contrib/index.html">ndarray.contrib</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/image/index.html">ndarray.image</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/linalg/index.html">ndarray.linalg</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/op/index.html">ndarray.op</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/random/index.html">ndarray.random</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/register/index.html">ndarray.register</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/sparse/index.html">ndarray.sparse</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/ndarray/utils/index.html">ndarray.utils</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/gluon/index.html">mxnet.gluon</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/block.html">gluon.Block</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/hybrid_block.html">gluon.HybridBlock</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/symbol_block.html">gluon.SymbolBlock</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/constant.html">gluon.Constant</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/parameter.html">gluon.Parameter</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/parameter_dict.html">gluon.ParameterDict</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/trainer.html">gluon.Trainer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/contrib/index.html">gluon.contrib</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/data/index.html">gluon.data</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../../../api/gluon/data/vision/index.html">data.vision</a><ul>
<li class="toctree-l5"><a class="reference internal" href="../../../../api/gluon/data/vision/datasets/index.html">vision.datasets</a></li>
<li class="toctree-l5"><a class="reference internal" href="../../../../api/gluon/data/vision/transforms/index.html">vision.transforms</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/loss/index.html">gluon.loss</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/gluon/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/metric/index.html">mxnet.metric</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/kvstore/index.html">mxnet.kvstore</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/symbol/index.html">mxnet.symbol</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/symbol.html">symbol</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/contrib/index.html">symbol.contrib</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/image/index.html">symbol.image</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/linalg/index.html">symbol.linalg</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/op/index.html">symbol.op</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/random/index.html">symbol.random</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/register/index.html">symbol.register</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/symbol/sparse/index.html">symbol.sparse</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/module/index.html">mxnet.module</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/contrib/index.html">mxnet.contrib</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/autograd/index.html">contrib.autograd</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/io/index.html">contrib.io</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/ndarray/index.html">contrib.ndarray</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/onnx/index.html">contrib.onnx</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/quantization/index.html">contrib.quantization</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/symbol/index.html">contrib.symbol</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/tensorboard/index.html">contrib.tensorboard</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/tensorrt/index.html">contrib.tensorrt</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/contrib/text/index.html">contrib.text</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../../api/mxnet/index.html">mxnet</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/attribute/index.html">mxnet.attribute</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/base/index.html">mxnet.base</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/callback/index.html">mxnet.callback</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/context/index.html">mxnet.context</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/engine/index.html">mxnet.engine</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/executor/index.html">mxnet.executor</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/executor_manager/index.html">mxnet.executor_manager</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/image/index.html">mxnet.image</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/io/index.html">mxnet.io</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/kvstore_server/index.html">mxnet.kvstore_server</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/libinfo/index.html">mxnet.libinfo</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/log/index.html">mxnet.log</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/model/index.html">mxnet.model</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/monitor/index.html">mxnet.monitor</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/name/index.html">mxnet.name</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/notebook/index.html">mxnet.notebook</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/operator/index.html">mxnet.operator</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/profiler/index.html">mxnet.profiler</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/random/index.html">mxnet.random</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/recordio/index.html">mxnet.recordio</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/registry/index.html">mxnet.registry</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/rtc/index.html">mxnet.rtc</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/runtime/index.html">mxnet.runtime</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/test_utils/index.html">mxnet.test_utils</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/torch/index.html">mxnet.torch</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/util/index.html">mxnet.util</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../../api/mxnet/visualization/index.html">mxnet.visualization</a></li>
</ul>
</li>
</ul>
</li>
</ul>
</nav>
</div>
</header>
<div class="document">
<div class="page-content" role="main">
<h1>Source code for mxnet.gluon.nn.basic_layers</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"># &quot;License&quot;); 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"># &quot;AS IS&quot; BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="c1"># coding: utf-8</span>
<span class="c1"># pylint: disable= arguments-differ</span>
<span class="sd">&quot;&quot;&quot;Basic neural network layers.&quot;&quot;&quot;</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;Sequential&#39;</span><span class="p">,</span> <span class="s1">&#39;HybridSequential&#39;</span><span class="p">,</span> <span class="s1">&#39;Dense&#39;</span><span class="p">,</span> <span class="s1">&#39;Dropout&#39;</span><span class="p">,</span> <span class="s1">&#39;Embedding&#39;</span><span class="p">,</span>
<span class="s1">&#39;BatchNorm&#39;</span><span class="p">,</span> <span class="s1">&#39;BatchNormReLU&#39;</span><span class="p">,</span> <span class="s1">&#39;InstanceNorm&#39;</span><span class="p">,</span> <span class="s1">&#39;LayerNorm&#39;</span><span class="p">,</span> <span class="s1">&#39;GroupNorm&#39;</span><span class="p">,</span>
<span class="s1">&#39;Flatten&#39;</span><span class="p">,</span> <span class="s1">&#39;Lambda&#39;</span><span class="p">,</span> <span class="s1">&#39;HybridLambda&#39;</span><span class="p">]</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">from</span> <span class="nn">.activations</span> <span class="kn">import</span> <span class="n">Activation</span>
<span class="kn">from</span> <span class="nn">..block</span> <span class="kn">import</span> <span class="n">Block</span><span class="p">,</span> <span class="n">HybridBlock</span>
<span class="kn">from</span> <span class="nn">..utils</span> <span class="kn">import</span> <span class="n">_indent</span>
<span class="kn">from</span> <span class="nn">...</span> <span class="kn">import</span> <span class="n">nd</span><span class="p">,</span> <span class="n">sym</span>
<span class="kn">from</span> <span class="nn">...util</span> <span class="kn">import</span> <span class="n">is_np_array</span>
<div class="viewcode-block" id="Sequential"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Sequential">[docs]</a><span class="k">class</span> <span class="nc">Sequential</span><span class="p">(</span><span class="n">Block</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Stacks Blocks sequentially.</span>
<span class="sd"> Example::</span>
<span class="sd"> net = nn.Sequential()</span>
<span class="sd"> # use net&#39;s name_scope to give child Blocks appropriate names.</span>
<span class="sd"> with net.name_scope():</span>
<span class="sd"> net.add(nn.Dense(10, activation=&#39;relu&#39;))</span>
<span class="sd"> net.add(nn.Dense(20))</span>
<span class="sd"> &quot;&quot;&quot;</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">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">params</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">Sequential</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<div class="viewcode-block" id="Sequential.add"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Sequential.add">[docs]</a> <span class="k">def</span> <span class="nf">add</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">blocks</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Adds block on top of the stack.&quot;&quot;&quot;</span>
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="n">blocks</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">register_child</span><span class="p">(</span><span class="n">block</span><span class="p">)</span></div>
<div class="viewcode-block" id="Sequential.forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Sequential.forward">[docs]</a> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">block</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="se">\n</span><span class="si">{modstr}</span><span class="se">\n</span><span class="s1">)&#39;</span>
<span class="n">modstr</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">&#39; (</span><span class="si">{key}</span><span class="s1">): </span><span class="si">{block}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">key</span><span class="p">,</span>
<span class="n">block</span><span class="o">=</span><span class="n">_indent</span><span class="p">(</span><span class="n">block</span><span class="o">.</span><span class="fm">__repr__</span><span class="p">(),</span> <span class="mi">2</span><span class="p">))</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">modstr</span><span class="o">=</span><span class="n">modstr</span><span class="p">)</span>
<span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">):</span>
<span class="n">layers</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">())[</span><span class="n">key</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">layers</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="n">net</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)(</span><span class="n">prefix</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_prefix</span><span class="p">)</span>
<span class="k">with</span> <span class="n">net</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span>
<span class="n">net</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="o">*</span><span class="n">layers</span><span class="p">)</span>
<span class="k">return</span> <span class="n">net</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">layers</span>
<span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="p">)</span>
<div class="viewcode-block" id="Sequential.hybridize"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Sequential.hybridize">[docs]</a> <span class="k">def</span> <span class="nf">hybridize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">active</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Activates or deactivates `HybridBlock` s recursively. Has no effect on</span>
<span class="sd"> non-hybrid children.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> active : bool, default True</span>
<span class="sd"> Whether to turn hybrid on or off.</span>
<span class="sd"> **kwargs : string</span>
<span class="sd"> Additional flags for hybridized operator.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span> <span class="ow">and</span> <span class="nb">all</span><span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">c</span><span class="p">,</span> <span class="n">HybridBlock</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">()):</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
<span class="s2">&quot;All children of this Sequential layer &#39;</span><span class="si">%s</span><span class="s2">&#39; are HybridBlocks. Consider &quot;</span>
<span class="s2">&quot;using HybridSequential for the best performance.&quot;</span><span class="o">%</span><span class="bp">self</span><span class="o">.</span><span class="n">prefix</span><span class="p">,</span> <span class="n">stacklevel</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Sequential</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">hybridize</span><span class="p">(</span><span class="n">active</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="HybridSequential"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.HybridSequential">[docs]</a><span class="k">class</span> <span class="nc">HybridSequential</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Stacks HybridBlocks sequentially.</span>
<span class="sd"> Example::</span>
<span class="sd"> net = nn.HybridSequential()</span>
<span class="sd"> # use net&#39;s name_scope to give child Blocks appropriate names.</span>
<span class="sd"> with net.name_scope():</span>
<span class="sd"> net.add(nn.Dense(10, activation=&#39;relu&#39;))</span>
<span class="sd"> net.add(nn.Dense(20))</span>
<span class="sd"> net.hybridize()</span>
<span class="sd"> &quot;&quot;&quot;</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">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">params</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">HybridSequential</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<div class="viewcode-block" id="HybridSequential.add"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.HybridSequential.add">[docs]</a> <span class="k">def</span> <span class="nf">add</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">blocks</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Adds block on top of the stack.&quot;&quot;&quot;</span>
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="n">blocks</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">register_child</span><span class="p">(</span><span class="n">block</span><span class="p">)</span></div>
<div class="viewcode-block" id="HybridSequential.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.HybridSequential.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">block</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="se">\n</span><span class="si">{modstr}</span><span class="se">\n</span><span class="s1">)&#39;</span>
<span class="n">modstr</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">&#39; (</span><span class="si">{key}</span><span class="s1">): </span><span class="si">{block}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">key</span><span class="p">,</span>
<span class="n">block</span><span class="o">=</span><span class="n">_indent</span><span class="p">(</span><span class="n">block</span><span class="o">.</span><span class="fm">__repr__</span><span class="p">(),</span> <span class="mi">2</span><span class="p">))</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">modstr</span><span class="o">=</span><span class="n">modstr</span><span class="p">)</span>
<span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">):</span>
<span class="n">layers</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">())[</span><span class="n">key</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">layers</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="n">net</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)(</span><span class="n">prefix</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_prefix</span><span class="p">)</span>
<span class="k">with</span> <span class="n">net</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span>
<span class="n">net</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="o">*</span><span class="n">layers</span><span class="p">)</span>
<span class="k">return</span> <span class="n">net</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">layers</span>
<span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="p">)</span></div>
<div class="viewcode-block" id="Dense"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Dense">[docs]</a><span class="k">class</span> <span class="nc">Dense</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">&quot;&quot;&quot;Just your regular densely-connected NN layer.</span>
<span class="sd"> `Dense` implements the operation:</span>
<span class="sd"> `output = activation(dot(input, weight) + bias)`</span>
<span class="sd"> where `activation` is the element-wise activation function</span>
<span class="sd"> passed as the `activation` argument, `weight` is a weights matrix</span>
<span class="sd"> created by the layer, and `bias` is a bias vector created by the layer</span>
<span class="sd"> (only applicable if `use_bias` is `True`).</span>
<span class="sd"> .. note::</span>
<span class="sd"> the input must be a tensor with rank 2. Use `flatten` to convert it</span>
<span class="sd"> to rank 2 manually if necessary.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> units : int</span>
<span class="sd"> Dimensionality of the output space.</span>
<span class="sd"> activation : str</span>
<span class="sd"> Activation function to use. See help on `Activation` layer.</span>
<span class="sd"> If you don&#39;t specify anything, no activation is applied</span>
<span class="sd"> (ie. &quot;linear&quot; activation: `a(x) = x`).</span>
<span class="sd"> use_bias : bool, default True</span>
<span class="sd"> Whether the layer uses a bias vector.</span>
<span class="sd"> flatten: bool, default True</span>
<span class="sd"> Whether the input tensor should be flattened.</span>
<span class="sd"> If true, all but the first axis of input data are collapsed together.</span>
<span class="sd"> If false, all but the last axis of input data are kept the same, and the transformation</span>
<span class="sd"> applies on the last axis.</span>
<span class="sd"> dtype : str or np.dtype, default &#39;float32&#39;</span>
<span class="sd"> Data type of output embeddings.</span>
<span class="sd"> weight_initializer : str or `Initializer`</span>
<span class="sd"> Initializer for the `kernel` weights matrix.</span>
<span class="sd"> bias_initializer: str or `Initializer`</span>
<span class="sd"> Initializer for the bias vector.</span>
<span class="sd"> in_units : int, optional</span>
<span class="sd"> Size of the input data. If not specified, initialization will be</span>
<span class="sd"> deferred to the first time `forward` is called and `in_units`</span>
<span class="sd"> will be inferred from the shape of input data.</span>
<span class="sd"> prefix : str or None</span>
<span class="sd"> See document of `Block`.</span>
<span class="sd"> params : ParameterDict or None</span>
<span class="sd"> See document of `Block`.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: if `flatten` is True, `data` should be a tensor with shape</span>
<span class="sd"> `(batch_size, x1, x2, ..., xn)`, where x1 * x2 * ... * xn is equal to</span>
<span class="sd"> `in_units`. If `flatten` is False, `data` should have shape</span>
<span class="sd"> `(x1, x2, ..., xn, in_units)`.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: if `flatten` is True, `out` will be a tensor with shape</span>
<span class="sd"> `(batch_size, units)`. If `flatten` is False, `out` will have shape</span>
<span class="sd"> `(x1, x2, ..., xn, units)`.</span>
<span class="sd"> &quot;&quot;&quot;</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">units</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">flatten</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;float32&#39;</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span>
<span class="n">in_units</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Dense</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_flatten</span> <span class="o">=</span> <span class="n">flatten</span>
<span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_units</span> <span class="o">=</span> <span class="n">units</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_in_units</span> <span class="o">=</span> <span class="n">in_units</span>
<span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;weight&#39;</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">units</span><span class="p">,</span> <span class="n">in_units</span><span class="p">),</span>
<span class="n">init</span><span class="o">=</span><span class="n">weight_initializer</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">if</span> <span class="n">use_bias</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;bias&#39;</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">units</span><span class="p">,),</span>
<span class="n">init</span><span class="o">=</span><span class="n">bias_initializer</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">activation</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="o">=</span> <span class="n">Activation</span><span class="p">(</span><span class="n">activation</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="n">activation</span><span class="o">+</span><span class="s1">&#39;_&#39;</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">act</span> <span class="o">=</span> <span class="kc">None</span>
<div class="viewcode-block" id="Dense.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Dense.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">fc</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">fully_connected</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">FullyConnected</span>
<span class="n">act</span> <span class="o">=</span> <span class="n">fc</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">bias</span><span class="p">,</span> <span class="n">no_bias</span><span class="o">=</span><span class="n">bias</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">,</span> <span class="n">num_hidden</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_units</span><span class="p">,</span>
<span class="n">flatten</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_flatten</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;fwd&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">act</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span><span class="p">(</span><span class="n">act</span><span class="p">)</span>
<span class="k">return</span> <span class="n">act</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{layout}</span><span class="s1">, </span><span class="si">{act}</span><span class="s1">)&#39;</span>
<span class="n">shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">shape</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">act</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="k">else</span> <span class="s1">&#39;linear&#39;</span><span class="p">,</span>
<span class="n">layout</span><span class="o">=</span><span class="s1">&#39;</span><span class="si">{0}</span><span class="s1"> -&gt; </span><span class="si">{1}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">if</span> <span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span> <span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]))</span></div>
<div class="viewcode-block" id="Dropout"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Dropout">[docs]</a><span class="k">class</span> <span class="nc">Dropout</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Applies Dropout to the input.</span>
<span class="sd"> Dropout consists in randomly setting a fraction `rate` of input units</span>
<span class="sd"> to 0 at each update during training time, which helps prevent overfitting.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> rate : float</span>
<span class="sd"> Fraction of the input units to drop. Must be a number between 0 and 1.</span>
<span class="sd"> axes : tuple of int, default ()</span>
<span class="sd"> The axes on which dropout mask is shared. If empty, regular dropout is applied.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> References</span>
<span class="sd"> ----------</span>
<span class="sd"> `Dropout: A Simple Way to Prevent Neural Networks from Overfitting</span>
<span class="sd"> &lt;http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf&gt;`_</span>
<span class="sd"> &quot;&quot;&quot;</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">rate</span><span class="p">,</span> <span class="n">axes</span><span class="o">=</span><span class="p">(),</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Dropout</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_rate</span> <span class="o">=</span> <span class="n">rate</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_axes</span> <span class="o">=</span> <span class="n">axes</span>
<div class="viewcode-block" id="Dropout.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Dropout.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_rate</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">dropout</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">dropout</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">Dropout</span>
<span class="k">return</span> <span class="n">dropout</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">p</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_rate</span><span class="p">,</span> <span class="n">axes</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_axes</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;fwd&#39;</span><span class="p">,</span> <span class="n">cudnn_off</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">copy</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">np</span><span class="o">.</span><span class="n">copy</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">identity</span>
<span class="k">return</span> <span class="n">copy</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(p = </span><span class="si">{_rate}</span><span class="s1">, axes=</span><span class="si">{_axes}</span><span class="s1">)&#39;</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)</span></div>
<span class="k">class</span> <span class="nc">_BatchNorm</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Abstract BatchNorm layer (private, used as implementation base).</span>
<span class="sd"> Batch normalization layer (Ioffe and Szegedy, 2014).</span>
<span class="sd"> Normalizes the input at each batch, i.e. applies a transformation</span>
<span class="sd"> that maintains the mean activation close to 0 and the activation</span>
<span class="sd"> standard deviation close to 1.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> axis : int, default 1</span>
<span class="sd"> The axis that should be normalized. This is typically the channels</span>
<span class="sd"> (C) axis. For instance, after a `Conv2D` layer with `layout=&#39;NCHW&#39;`,</span>
<span class="sd"> set `axis=1` in `BatchNorm`. If `layout=&#39;NHWC&#39;`, then set `axis=3`.</span>
<span class="sd"> momentum: float, default 0.9</span>
<span class="sd"> Momentum for the moving average.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> When the next layer is linear (also e.g. `nn.relu`),</span>
<span class="sd"> this can be disabled since the scaling</span>
<span class="sd"> will be done by the next layer.</span>
<span class="sd"> use_global_stats: bool, default False</span>
<span class="sd"> If True, use global moving statistics instead of local batch-norm. This will force</span>
<span class="sd"> change batch-norm into a scale shift operator.</span>
<span class="sd"> If False, use local batch-norm.</span>
<span class="sd"> fuse_relu: bool, default False</span>
<span class="sd"> If True, this operator is equal to `BN+ReLU`.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> running_mean_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the running mean.</span>
<span class="sd"> running_variance_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the running variance.</span>
<span class="sd"> in_channels : int, default 0</span>
<span class="sd"> Number of channels (feature maps) in input data. If not specified,</span>
<span class="sd"> initialization will be deferred to the first time `forward` is called</span>
<span class="sd"> and `in_channels` will be inferred from the shape of input data.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">momentum</span><span class="o">=</span><span class="mf">0.9</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">use_global_stats</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">fuse_relu</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">running_mean_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">running_variance_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_BatchNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;axis&#39;</span><span class="p">:</span> <span class="n">axis</span><span class="p">,</span> <span class="s1">&#39;eps&#39;</span><span class="p">:</span> <span class="n">epsilon</span><span class="p">,</span> <span class="s1">&#39;momentum&#39;</span><span class="p">:</span> <span class="n">momentum</span><span class="p">,</span>
<span class="s1">&#39;fix_gamma&#39;</span><span class="p">:</span> <span class="ow">not</span> <span class="n">scale</span><span class="p">,</span> <span class="s1">&#39;use_global_stats&#39;</span><span class="p">:</span> <span class="n">use_global_stats</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fuse_relu</span> <span class="o">=</span> <span class="n">fuse_relu</span>
<span class="k">if</span> <span class="n">in_channels</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">in_channels</span> <span class="o">=</span> <span class="n">in_channels</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gamma</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;gamma&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;write&#39;</span> <span class="k">if</span> <span class="n">scale</span> <span class="k">else</span> <span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">differentiable</span><span class="o">=</span><span class="n">scale</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;beta&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;write&#39;</span> <span class="k">if</span> <span class="n">center</span> <span class="k">else</span> <span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">differentiable</span><span class="o">=</span><span class="n">center</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">running_mean</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;running_mean&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span>
<span class="n">init</span><span class="o">=</span><span class="n">running_mean_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">differentiable</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">running_var</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;running_var&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span>
<span class="n">init</span><span class="o">=</span><span class="n">running_variance_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">differentiable</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">cast</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dtype</span><span class="p">):</span>
<span class="k">if</span> <span class="n">np</span><span class="o">.</span><span class="n">dtype</span><span class="p">(</span><span class="n">dtype</span><span class="p">)</span><span class="o">.</span><span class="n">name</span> <span class="o">==</span> <span class="s1">&#39;float16&#39;</span><span class="p">:</span>
<span class="n">dtype</span> <span class="o">=</span> <span class="s1">&#39;float32&#39;</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_BatchNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">dtype</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">,</span> <span class="n">running_mean</span><span class="p">,</span> <span class="n">running_var</span><span class="p">):</span>
<span class="n">batch_norm</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">batch_norm</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">BatchNorm</span>
<span class="k">if</span> <span class="p">(</span><span class="ow">not</span> <span class="n">is_np_array</span><span class="p">())</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">fuse_relu</span><span class="p">:</span>
<span class="n">batch_norm</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">contrib</span><span class="o">.</span><span class="n">BatchNormWithReLU</span>
<span class="k">return</span> <span class="n">batch_norm</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">,</span> <span class="n">running_mean</span><span class="p">,</span> <span class="n">running_var</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;fwd&#39;</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{content}</span><span class="s1">&#39;</span>
<span class="n">in_channels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gamma</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">&#39;, in_channels=</span><span class="si">{0}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">in_channels</span> <span class="k">if</span> <span class="n">in_channels</span> <span class="k">else</span> <span class="kc">None</span><span class="p">)</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">&#39;)&#39;</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">content</span><span class="o">=</span><span class="s1">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">&#39;=&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="o">.</span><span class="fm">__repr__</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="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span>
<div class="viewcode-block" id="BatchNorm"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.BatchNorm">[docs]</a><span class="k">class</span> <span class="nc">BatchNorm</span><span class="p">(</span><span class="n">_BatchNorm</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Batch normalization layer (Ioffe and Szegedy, 2014).</span>
<span class="sd"> Normalizes the input at each batch, i.e. applies a transformation</span>
<span class="sd"> that maintains the mean activation close to 0 and the activation</span>
<span class="sd"> standard deviation close to 1.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> axis : int, default 1</span>
<span class="sd"> The axis that should be normalized. This is typically the channels</span>
<span class="sd"> (C) axis. For instance, after a `Conv2D` layer with `layout=&#39;NCHW&#39;`,</span>
<span class="sd"> set `axis=1` in `BatchNorm`. If `layout=&#39;NHWC&#39;`, then set `axis=3`.</span>
<span class="sd"> momentum: float, default 0.9</span>
<span class="sd"> Momentum for the moving average.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> When the next layer is linear (also e.g. `nn.relu`),</span>
<span class="sd"> this can be disabled since the scaling</span>
<span class="sd"> will be done by the next layer.</span>
<span class="sd"> use_global_stats: bool, default False</span>
<span class="sd"> If True, use global moving statistics instead of local batch-norm. This will force</span>
<span class="sd"> change batch-norm into a scale shift operator.</span>
<span class="sd"> If False, use local batch-norm.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> running_mean_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the running mean.</span>
<span class="sd"> running_variance_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the running variance.</span>
<span class="sd"> in_channels : int, default 0</span>
<span class="sd"> Number of channels (feature maps) in input data. If not specified,</span>
<span class="sd"> initialization will be deferred to the first time `forward` is called</span>
<span class="sd"> and `in_channels` will be inferred from the shape of input data.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">momentum</span><span class="o">=</span><span class="mf">0.9</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">use_global_stats</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">running_mean_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">running_variance_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">BatchNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span>
<span class="n">axis</span><span class="o">=</span><span class="n">axis</span><span class="p">,</span> <span class="n">momentum</span><span class="o">=</span><span class="n">momentum</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="n">epsilon</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="n">center</span><span class="p">,</span>
<span class="n">scale</span><span class="o">=</span><span class="n">scale</span><span class="p">,</span>
<span class="n">use_global_stats</span><span class="o">=</span><span class="n">use_global_stats</span><span class="p">,</span> <span class="n">fuse_relu</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">gamma_initializer</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">running_mean_initializer</span><span class="o">=</span><span class="n">running_mean_initializer</span><span class="p">,</span>
<span class="n">running_variance_initializer</span><span class="o">=</span><span class="n">running_variance_initializer</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="n">in_channels</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="BatchNormReLU"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.BatchNormReLU">[docs]</a><span class="k">class</span> <span class="nc">BatchNormReLU</span><span class="p">(</span><span class="n">_BatchNorm</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Batch normalization layer (Ioffe and Szegedy, 2014).</span>
<span class="sd"> Normalizes the input at each batch, i.e. applies a transformation</span>
<span class="sd"> that maintains the mean activation close to 0 and the activation</span>
<span class="sd"> standard deviation close to 1.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> axis : int, default 1</span>
<span class="sd"> The axis that should be normalized. This is typically the channels</span>
<span class="sd"> (C) axis. For instance, after a `Conv2D` layer with `layout=&#39;NCHW&#39;`,</span>
<span class="sd"> set `axis=1` in `BatchNorm`. If `layout=&#39;NHWC&#39;`, then set `axis=3`.</span>
<span class="sd"> momentum: float, default 0.9</span>
<span class="sd"> Momentum for the moving average.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> When the next layer is linear (also e.g. `nn.relu`),</span>
<span class="sd"> this can be disabled since the scaling</span>
<span class="sd"> will be done by the next layer.</span>
<span class="sd"> use_global_stats: bool, default False</span>
<span class="sd"> If True, use global moving statistics instead of local batch-norm. This will force</span>
<span class="sd"> change batch-norm into a scale shift operator.</span>
<span class="sd"> If False, use local batch-norm.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> running_mean_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the running mean.</span>
<span class="sd"> running_variance_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the running variance.</span>
<span class="sd"> in_channels : int, default 0</span>
<span class="sd"> Number of channels (feature maps) in input data. If not specified,</span>
<span class="sd"> initialization will be deferred to the first time `forward` is called</span>
<span class="sd"> and `in_channels` will be inferred from the shape of input data.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">momentum</span><span class="o">=</span><span class="mf">0.9</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">use_global_stats</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">running_mean_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">running_variance_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">BatchNormReLU</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span>
<span class="n">axis</span><span class="o">=</span><span class="n">axis</span><span class="p">,</span> <span class="n">momentum</span><span class="o">=</span><span class="n">momentum</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="n">epsilon</span><span class="p">,</span>
<span class="n">center</span><span class="o">=</span><span class="n">center</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="n">scale</span><span class="p">,</span>
<span class="n">use_global_stats</span><span class="o">=</span><span class="n">use_global_stats</span><span class="p">,</span> <span class="n">fuse_relu</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">gamma_initializer</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">running_mean_initializer</span><span class="o">=</span><span class="n">running_mean_initializer</span><span class="p">,</span>
<span class="n">running_variance_initializer</span><span class="o">=</span><span class="n">running_variance_initializer</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="n">in_channels</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="Embedding"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Embedding">[docs]</a><span class="k">class</span> <span class="nc">Embedding</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">&quot;&quot;&quot;Turns non-negative integers (indexes/tokens) into dense vectors</span>
<span class="sd"> of fixed size. eg. [4, 20] -&gt; [[0.25, 0.1], [0.6, -0.2]]</span>
<span class="sd"> .. note::</span>
<span class="sd"> if `sparse_grad` is set to True, the gradient w.r.t weight will be</span>
<span class="sd"> sparse. Only a subset of optimizers support sparse gradients, including SGD,</span>
<span class="sd"> AdaGrad and Adam. By default lazy updates is turned on, which may perform</span>
<span class="sd"> differently from standard updates. For more details, please check the</span>
<span class="sd"> Optimization API at:</span>
<span class="sd"> https://mxnet.incubator.apache.org/api/python/optimization/optimization.html</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> input_dim : int</span>
<span class="sd"> Size of the vocabulary, i.e. maximum integer index + 1.</span>
<span class="sd"> output_dim : int</span>
<span class="sd"> Dimension of the dense embedding.</span>
<span class="sd"> dtype : str or np.dtype, default &#39;float32&#39;</span>
<span class="sd"> Data type of output embeddings.</span>
<span class="sd"> weight_initializer : Initializer</span>
<span class="sd"> Initializer for the `embeddings` matrix.</span>
<span class="sd"> sparse_grad: bool</span>
<span class="sd"> If True, gradient w.r.t. weight will be a &#39;row_sparse&#39; NDArray.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: (N-1)-D tensor with shape: `(x1, x2, ..., xN-1)`.</span>
<span class="sd"> Output:</span>
<span class="sd"> - **out**: N-D tensor with shape: `(x1, x2, ..., xN-1, output_dim)`.</span>
<span class="sd"> &quot;&quot;&quot;</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">input_dim</span><span class="p">,</span> <span class="n">output_dim</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;float32&#39;</span><span class="p">,</span>
<span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">sparse_grad</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Embedding</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="n">grad_stype</span> <span class="o">=</span> <span class="s1">&#39;row_sparse&#39;</span> <span class="k">if</span> <span class="n">sparse_grad</span> <span class="k">else</span> <span class="s1">&#39;default&#39;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;input_dim&#39;</span><span class="p">:</span> <span class="n">input_dim</span><span class="p">,</span> <span class="s1">&#39;output_dim&#39;</span><span class="p">:</span> <span class="n">output_dim</span><span class="p">,</span>
<span class="s1">&#39;dtype&#39;</span><span class="p">:</span> <span class="n">dtype</span><span class="p">,</span> <span class="s1">&#39;sparse_grad&#39;</span><span class="p">:</span> <span class="n">sparse_grad</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;weight&#39;</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">input_dim</span><span class="p">,</span> <span class="n">output_dim</span><span class="p">),</span>
<span class="n">init</span><span class="o">=</span><span class="n">weight_initializer</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">grad_stype</span><span class="o">=</span><span class="n">grad_stype</span><span class="p">)</span>
<div class="viewcode-block" id="Embedding.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Embedding.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">):</span>
<span class="n">embedding</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">embedding</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">Embedding</span>
<span class="k">return</span> <span class="n">embedding</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;fwd&#39;</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{block_name}</span><span class="s1">(</span><span class="si">{input_dim}</span><span class="s1"> -&gt; </span><span class="si">{output_dim}</span><span class="s1">, </span><span class="si">{dtype}</span><span class="s1">)&#39;</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">block_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="Flatten"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Flatten">[docs]</a><span class="k">class</span> <span class="nc">Flatten</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">&quot;&quot;&quot;Flattens the input to two dimensional.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape `(N, x1, x2, ..., xn)`</span>
<span class="sd"> Output:</span>
<span class="sd"> - **out**: 2D tensor with shape: `(N, x1 \cdot x2 \cdot ... \cdot xn)`</span>
<span class="sd"> &quot;&quot;&quot;</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="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Flatten</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<div class="viewcode-block" id="Flatten.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Flatten.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="n">flatten</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">batch_flatten</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">flatten</span>
<span class="k">return</span> <span class="n">flatten</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span></div>
<div class="viewcode-block" id="InstanceNorm"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.InstanceNorm">[docs]</a><span class="k">class</span> <span class="nc">InstanceNorm</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Applies instance normalization to the n-dimensional input array.</span>
<span class="sd"> This operator takes an n-dimensional input array where (n&gt;2) and normalizes</span>
<span class="sd"> the input using the following formula:</span>
<span class="sd"> .. math::</span>
<span class="sd"> \bar{C} = \{i \mid i \neq 0, i \neq axis\}</span>
<span class="sd"> out = \frac{x - mean[data, \bar{C}]}{ \sqrt{Var[data, \bar{C}]} + \epsilon}</span>
<span class="sd"> * gamma + beta</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> axis : int, default 1</span>
<span class="sd"> The axis that will be excluded in the normalization process. This is typically the channels</span>
<span class="sd"> (C) axis. For instance, after a `Conv2D` layer with `layout=&#39;NCHW&#39;`,</span>
<span class="sd"> set `axis=1` in `InstanceNorm`. If `layout=&#39;NHWC&#39;`, then set `axis=3`. Data will be</span>
<span class="sd"> normalized along axes excluding the first axis and the axis given.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> When the next layer is linear (also e.g. `nn.relu`),</span>
<span class="sd"> this can be disabled since the scaling</span>
<span class="sd"> will be done by the next layer.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> in_channels : int, default 0</span>
<span class="sd"> Number of channels (feature maps) in input data. If not specified,</span>
<span class="sd"> initialization will be deferred to the first time `forward` is called</span>
<span class="sd"> and `in_channels` will be inferred from the shape of input data.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> References</span>
<span class="sd"> ----------</span>
<span class="sd"> `Instance Normalization: The Missing Ingredient for Fast Stylization</span>
<span class="sd"> &lt;https://arxiv.org/abs/1607.08022&gt;`_</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; # Input of shape (2,1,2)</span>
<span class="sd"> &gt;&gt;&gt; x = mx.nd.array([[[ 1.1, 2.2]],</span>
<span class="sd"> ... [[ 3.3, 4.4]]])</span>
<span class="sd"> &gt;&gt;&gt; # Instance normalization is calculated with the above formula</span>
<span class="sd"> &gt;&gt;&gt; layer = InstanceNorm()</span>
<span class="sd"> &gt;&gt;&gt; layer.initialize(ctx=mx.cpu(0))</span>
<span class="sd"> &gt;&gt;&gt; layer(x)</span>
<span class="sd"> [[[-0.99998355 0.99998331]]</span>
<span class="sd"> [[-0.99998319 0.99998361]]]</span>
<span class="sd"> &lt;NDArray 2x1x2 @cpu(0)&gt;</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">InstanceNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;eps&#39;</span><span class="p">:</span> <span class="n">epsilon</span><span class="p">,</span> <span class="s1">&#39;axis&#39;</span><span class="p">:</span> <span class="n">axis</span><span class="p">,</span> <span class="s1">&#39;center&#39;</span><span class="p">:</span> <span class="n">center</span><span class="p">,</span> <span class="s1">&#39;scale&#39;</span><span class="p">:</span> <span class="n">scale</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_axis</span> <span class="o">=</span> <span class="n">axis</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span> <span class="o">=</span> <span class="n">epsilon</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gamma</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;gamma&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;write&#39;</span> <span class="k">if</span> <span class="n">scale</span> <span class="k">else</span> <span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;beta&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;write&#39;</span> <span class="k">if</span> <span class="n">center</span> <span class="k">else</span> <span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<div class="viewcode-block" id="InstanceNorm.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.InstanceNorm.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">InstanceNorm</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="s1">&#39;fwd&#39;</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">)</span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">InstanceNorm</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;fwd&#39;</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span><span class="p">)</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{content}</span><span class="s1">&#39;</span>
<span class="n">in_channels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gamma</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">&#39;, in_channels=</span><span class="si">{0}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">in_channels</span><span class="p">)</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">&#39;)&#39;</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">content</span><span class="o">=</span><span class="s1">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">&#39;=&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="o">.</span><span class="fm">__repr__</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="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span></div>
<div class="viewcode-block" id="LayerNorm"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.LayerNorm">[docs]</a><span class="k">class</span> <span class="nc">LayerNorm</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Applies layer normalization to the n-dimensional input array.</span>
<span class="sd"> This operator takes an n-dimensional input array and normalizes</span>
<span class="sd"> the input using the given axis:</span>
<span class="sd"> .. math::</span>
<span class="sd"> out = \frac{x - mean[data, axis]}{ \sqrt{Var[data, axis] + \epsilon}} * gamma + beta</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> axis : int, default -1</span>
<span class="sd"> The axis that should be normalized. This is typically the axis of the channels.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> in_channels : int, default 0</span>
<span class="sd"> Number of channels (feature maps) in input data. If not specified,</span>
<span class="sd"> initialization will be deferred to the first time `forward` is called</span>
<span class="sd"> and `in_channels` will be inferred from the shape of input data.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> References</span>
<span class="sd"> ----------</span>
<span class="sd"> `Layer Normalization</span>
<span class="sd"> &lt;https://arxiv.org/pdf/1607.06450.pdf&gt;`_</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; # Input of shape (2, 5)</span>
<span class="sd"> &gt;&gt;&gt; x = mx.nd.array([[1, 2, 3, 4, 5], [1, 1, 2, 2, 2]])</span>
<span class="sd"> &gt;&gt;&gt; # Layer normalization is calculated with the above formula</span>
<span class="sd"> &gt;&gt;&gt; layer = LayerNorm()</span>
<span class="sd"> &gt;&gt;&gt; layer.initialize(ctx=mx.cpu(0))</span>
<span class="sd"> &gt;&gt;&gt; layer(x)</span>
<span class="sd"> [[-1.41421 -0.707105 0. 0.707105 1.41421 ]</span>
<span class="sd"> [-1.2247195 -1.2247195 0.81647956 0.81647956 0.81647956]]</span>
<span class="sd"> &lt;NDArray 2x5 @cpu(0)&gt;</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">params</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">LayerNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;eps&#39;</span><span class="p">:</span> <span class="n">epsilon</span><span class="p">,</span> <span class="s1">&#39;axis&#39;</span><span class="p">:</span> <span class="n">axis</span><span class="p">,</span> <span class="s1">&#39;center&#39;</span><span class="p">:</span> <span class="n">center</span><span class="p">,</span> <span class="s1">&#39;scale&#39;</span><span class="p">:</span> <span class="n">scale</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_axis</span> <span class="o">=</span> <span class="n">axis</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span> <span class="o">=</span> <span class="n">epsilon</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_center</span> <span class="o">=</span> <span class="n">center</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_scale</span> <span class="o">=</span> <span class="n">scale</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gamma</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;gamma&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;write&#39;</span> <span class="k">if</span> <span class="n">scale</span> <span class="k">else</span> <span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;beta&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;write&#39;</span> <span class="k">if</span> <span class="n">center</span> <span class="k">else</span> <span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<div class="viewcode-block" id="LayerNorm.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.LayerNorm.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">):</span>
<span class="n">layer_norm</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">npx</span><span class="o">.</span><span class="n">layer_norm</span> <span class="k">if</span> <span class="n">is_np_array</span><span class="p">()</span> <span class="k">else</span> <span class="n">F</span><span class="o">.</span><span class="n">LayerNorm</span>
<span class="k">return</span> <span class="n">layer_norm</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">gamma</span><span class="o">=</span><span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="n">beta</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{content}</span><span class="s1">&#39;</span>
<span class="n">in_channels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gamma</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">&#39;, in_channels=</span><span class="si">{0}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">in_channels</span><span class="p">)</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">&#39;)&#39;</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">content</span><span class="o">=</span><span class="s1">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">&#39;=&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="o">.</span><span class="fm">__repr__</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="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span></div>
<div class="viewcode-block" id="GroupNorm"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.GroupNorm">[docs]</a><span class="k">class</span> <span class="nc">GroupNorm</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Applies group normalization to the n-dimensional input array.</span>
<span class="sd"> This operator takes an n-dimensional input array where the leftmost 2 axis are</span>
<span class="sd"> `batch` and `channel` respectively:</span>
<span class="sd"> .. math::</span>
<span class="sd"> x = x.reshape((N, num_groups, C // num_groups, ...))</span>
<span class="sd"> axis = (2, ...)</span>
<span class="sd"> out = \frac{x - mean[x, axis]}{ \sqrt{Var[x, axis] + \epsilon}} * gamma + beta</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> num_groups: int, default 1</span>
<span class="sd"> Number of groups to separate the channel axis into.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default &#39;zeros&#39;</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default &#39;ones&#39;</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with shape (N, C, ...).</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> References</span>
<span class="sd"> ----------</span>
<span class="sd"> `Group Normalization</span>
<span class="sd"> &lt;https://arxiv.org/pdf/1803.08494.pdf&gt;`_</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> &gt;&gt;&gt; # Input of shape (2, 3, 4)</span>
<span class="sd"> &gt;&gt;&gt; x = mx.nd.array([[[ 0, 1, 2, 3],</span>
<span class="sd"> [ 4, 5, 6, 7],</span>
<span class="sd"> [ 8, 9, 10, 11]],</span>
<span class="sd"> [[12, 13, 14, 15],</span>
<span class="sd"> [16, 17, 18, 19],</span>
<span class="sd"> [20, 21, 22, 23]]])</span>
<span class="sd"> &gt;&gt;&gt; # Group normalization is calculated with the above formula</span>
<span class="sd"> &gt;&gt;&gt; layer = GroupNorm()</span>
<span class="sd"> &gt;&gt;&gt; layer.initialize(ctx=mx.cpu(0))</span>
<span class="sd"> &gt;&gt;&gt; layer(x)</span>
<span class="sd"> [[[-1.5932543 -1.3035717 -1.0138891 -0.7242065]</span>
<span class="sd"> [-0.4345239 -0.1448413 0.1448413 0.4345239]</span>
<span class="sd"> [ 0.7242065 1.0138891 1.3035717 1.5932543]]</span>
<span class="sd"> [[-1.5932543 -1.3035717 -1.0138891 -0.7242065]</span>
<span class="sd"> [-0.4345239 -0.1448413 0.1448413 0.4345239]</span>
<span class="sd"> [ 0.7242065 1.0138891 1.3035717 1.5932543]]]</span>
<span class="sd"> &lt;NDArray 2x3x4 @cpu(0)&gt;</span>
<span class="sd"> &quot;&quot;&quot;</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">num_groups</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="s1">&#39;zeros&#39;</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">&#39;ones&#39;</span><span class="p">,</span>
<span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">params</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">GroupNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;eps&#39;</span><span class="p">:</span> <span class="n">epsilon</span><span class="p">,</span> <span class="s1">&#39;num_groups&#39;</span><span class="p">:</span> <span class="n">num_groups</span><span class="p">,</span> <span class="s1">&#39;center&#39;</span><span class="p">:</span> <span class="n">center</span><span class="p">,</span> <span class="s1">&#39;scale&#39;</span><span class="p">:</span> <span class="n">scale</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_groups</span> <span class="o">=</span> <span class="n">num_groups</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span> <span class="o">=</span> <span class="n">epsilon</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_center</span> <span class="o">=</span> <span class="n">center</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_scale</span> <span class="o">=</span> <span class="n">scale</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gamma</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;gamma&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;write&#39;</span> <span class="k">if</span> <span class="n">scale</span> <span class="k">else</span> <span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">num_groups</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;beta&#39;</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">&#39;write&#39;</span> <span class="k">if</span> <span class="n">center</span> <span class="k">else</span> <span class="s1">&#39;null&#39;</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">num_groups</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<div class="viewcode-block" id="GroupNorm.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.GroupNorm.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">):</span>
<span class="n">norm_data</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">GroupNorm</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">gamma</span><span class="o">=</span><span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="n">beta</span><span class="p">,</span> <span class="n">num_groups</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_groups</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span><span class="p">)</span>
<span class="k">return</span> <span class="n">norm_data</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{content}</span><span class="s1">)&#39;</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">content</span><span class="o">=</span><span class="s1">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">&#39;=&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="o">.</span><span class="fm">__repr__</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="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span></div>
<div class="viewcode-block" id="Lambda"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Lambda">[docs]</a><span class="k">class</span> <span class="nc">Lambda</span><span class="p">(</span><span class="n">Block</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">&quot;&quot;&quot;Wraps an operator or an expression as a Block object.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> function : str or function</span>
<span class="sd"> Function used in lambda must be one of the following:</span>
<span class="sd"> 1) the name of an operator that is available in ndarray. For example::</span>
<span class="sd"> block = Lambda(&#39;tanh&#39;)</span>
<span class="sd"> 2) a function that conforms to ``def function(*args)``. For example::</span>
<span class="sd"> block = Lambda(lambda x: nd.LeakyReLU(x, slope=0.1))</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - ** *args **: one or more input data. Their shapes depend on the function.</span>
<span class="sd"> Output:</span>
<span class="sd"> - ** *outputs **: one or more output data. Their shapes depend on the function.</span>
<span class="sd"> &quot;&quot;&quot;</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">function</span><span class="p">,</span> <span class="n">prefix</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">Lambda</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">function</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="k">assert</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">nd</span><span class="p">,</span> <span class="n">function</span><span class="p">),</span> \
<span class="s2">&quot;Function name </span><span class="si">%s</span><span class="s2"> is not found in ndarray.&quot;</span> <span class="o">%</span> <span class="n">function</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func_impl</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">nd</span><span class="p">,</span> <span class="n">function</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">callable</span><span class="p">(</span><span class="n">function</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func_impl</span> <span class="o">=</span> <span class="n">function</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="s2">&quot;Unrecognized function in lambda: </span><span class="si">{}</span><span class="s2"> of type </span><span class="si">{}</span><span class="s2">&quot;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">function</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">function</span><span class="p">)))</span>
<div class="viewcode-block" id="Lambda.forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.Lambda.forward">[docs]</a> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_func_impl</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{function}</span><span class="s1">)&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">function</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_func_impl</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span></div>
<div class="viewcode-block" id="HybridLambda"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.HybridLambda">[docs]</a><span class="k">class</span> <span class="nc">HybridLambda</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">&quot;&quot;&quot;Wraps an operator or an expression as a HybridBlock object.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> function : str or function</span>
<span class="sd"> Function used in lambda must be one of the following:</span>
<span class="sd"> 1) The name of an operator that is available in both symbol and ndarray. For example::</span>
<span class="sd"> block = HybridLambda(&#39;tanh&#39;)</span>
<span class="sd"> 2) A function that conforms to ``def function(F, data, *args)``. For example::</span>
<span class="sd"> block = HybridLambda(lambda F, x: F.LeakyReLU(x, slope=0.1))</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - ** *args **: one or more input data. First argument must be symbol or ndarray. Their \</span>
<span class="sd"> shapes depend on the function.</span>
<span class="sd"> Output:</span>
<span class="sd"> - ** *outputs **: one or more output data. Their shapes depend on the function.</span>
<span class="sd"> &quot;&quot;&quot;</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">function</span><span class="p">,</span> <span class="n">prefix</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">HybridLambda</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">function</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="k">assert</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">nd</span><span class="p">,</span> <span class="n">function</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">function</span><span class="p">),</span> \
<span class="s2">&quot;Function name </span><span class="si">%s</span><span class="s2"> is not found in symbol/ndarray.&quot;</span> <span class="o">%</span> <span class="n">function</span>
<span class="n">func_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">sym</span><span class="p">:</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">function</span><span class="p">),</span> <span class="n">nd</span><span class="p">:</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">nd</span><span class="p">,</span> <span class="n">function</span><span class="p">)}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">F</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">func_dict</span><span class="p">[</span><span class="n">F</span><span class="p">](</span><span class="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func_name</span> <span class="o">=</span> <span class="n">function</span>
<span class="k">elif</span> <span class="n">callable</span><span class="p">(</span><span class="n">function</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func</span> <span class="o">=</span> <span class="n">function</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func_name</span> <span class="o">=</span> <span class="n">function</span><span class="o">.</span><span class="vm">__name__</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="s2">&quot;Unrecognized function in lambda: </span><span class="si">{}</span><span class="s2"> of type </span><span class="si">{}</span><span class="s2">&quot;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">function</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">function</span><span class="p">)))</span>
<div class="viewcode-block" id="HybridLambda.hybrid_forward"><a class="viewcode-back" href="../../../../api/gluon/nn/index.html#mxnet.gluon.nn.HybridLambda.hybrid_forward">[docs]</a> <span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_func</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="s1">&#39;</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{function}</span><span class="s1">)&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">function</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_func_name</span><span class="p">)</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 class="u-email" href="mailto:dev@mxnet.apache.org">Dev list</a></li>
<li><a class="u-email" href="mailto:user@mxnet.apache.org">User mailing list</a></li>
<li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li>
<li><a href="https://issues.apache.org/jira/projects/MXNET/issues">Jira Tracker</a></li>
<li><a href="https://github.com/apache/incubator-mxnet/labels/Roadmap">Github Roadmap</a></li>
<li><a href="https://medium.com/apache-mxnet">Blog</a></li>
<li><a href="https://discuss.mxnet.io">Forum</a></li>
<li><a href="/community/contribute">Contribute</a></li>
</ul>
</div>
<div class="col-4"><ul class="social-media-list"><li><a href="https://github.com/apache/incubator-mxnet"><svg class="svg-icon"><use xlink:href="../../../../_static/minima-social-icons.svg#github"></use></svg> <span class="username">apache/incubator-mxnet</span></a></li><li><a href="https://www.twitter.com/apachemxnet"><svg class="svg-icon"><use xlink:href="../../../../_static/minima-social-icons.svg#twitter"></use></svg> <span class="username">apachemxnet</span></a></li><li><a href="https://youtube.com/apachemxnet"><svg class="svg-icon"><use xlink:href="../../../../_static/minima-social-icons.svg#youtube"></use></svg> <span class="username">apachemxnet</span></a></li></ul>
</div>
<div class="col-4 footer-text">
<p>A flexible and efficient library for deep learning.</p>
</div>
</div>
</div>
</footer>
<footer class="site-footer2">
<div class="wrapper">
<div class="row">
<div class="col-3">
<img src="../../../../_static/apache_incubator_logo.png" class="footer-logo col-2">
</div>
<div class="footer-bottom-warning col-9">
<p>Apache MXNet is an effort undergoing incubation at <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>