Google Git
Sign in
apache / mxnet-site / 82a1adfef83e5bbd9e128754f56a2a2e83809347 / . / versions / 1.9.1 / api / python / docs / _modules / mxnet / gluon / trainer.html
blob: 56b804b4460394f0aacda00cb4c856e55f1bf7b1 [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.trainer &#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.trainer</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.trainer</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=line-too-long</span>
<span class="sd">&quot;&quot;&quot;Parameter optimizer.&quot;&quot;&quot;</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;Trainer&#39;</span><span class="p">]</span>
<span class="kn">from</span> <span class="nn">..</span> <span class="kn">import</span> <span class="n">optimizer</span> <span class="k">as</span> <span class="n">opt</span>
<span class="kn">from</span> <span class="nn">..model</span> <span class="kn">import</span> <span class="n">_create_kvstore</span><span class="p">,</span> <span class="n">_create_sparse_kvstore</span>
<span class="kn">from</span> <span class="nn">.parameter</span> <span class="kn">import</span> <span class="n">ParameterDict</span><span class="p">,</span> <span class="n">Parameter</span>
<span class="kn">from</span> <span class="nn">..kvstore</span> <span class="kn">import</span> <span class="n">KVStore</span>
<div class="viewcode-block" id="Trainer"><a class="viewcode-back" href="../../../api/gluon/trainer.html#mxnet.gluon.Trainer">[docs]</a><span class="k">class</span> <span class="nc">Trainer</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Applies an `Optimizer` on a set of Parameters. Trainer should</span>
<span class="sd"> be used together with `autograd`.</span>
<span class="sd"> .. note::</span>
<span class="sd"> For the following cases, updates will always happen on kvstore,</span>
<span class="sd"> i.e., you cannot set update_on_kvstore=False.</span>
<span class="sd"> - dist kvstore with sparse weights or sparse gradients</span>
<span class="sd"> - dist async kvstore</span>
<span class="sd"> - `optimizer.lr_scheduler` is not None</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> params : ParameterDict</span>
<span class="sd"> The set of parameters to optimize.</span>
<span class="sd"> optimizer : str or Optimizer</span>
<span class="sd"> The optimizer to use. See</span>
<span class="sd"> `help &lt;https://mxnet.apache.org/api/python/docs/api/optimizer/index.html#mxnet.optimizer.Optimizer&gt;`_</span>
<span class="sd"> on Optimizer for a list of available optimizers.</span>
<span class="sd"> optimizer_params : dict</span>
<span class="sd"> Key-word arguments to be passed to optimizer constructor. For example,</span>
<span class="sd"> `{&#39;learning_rate&#39;: 0.1}`. All optimizers accept learning_rate, wd (weight decay),</span>
<span class="sd"> clip_gradient, and lr_scheduler. See each optimizer&#39;s</span>
<span class="sd"> constructor for a list of additional supported arguments.</span>
<span class="sd"> kvstore : str or KVStore</span>
<span class="sd"> kvstore type for multi-gpu and distributed training. See help on</span>
<span class="sd"> :any:`mxnet.kvstore.create` for more information.</span>
<span class="sd"> compression_params : dict</span>
<span class="sd"> Specifies type of gradient compression and additional arguments depending</span>
<span class="sd"> on the type of compression being used. For example, 2bit compression requires a threshold.</span>
<span class="sd"> Arguments would then be {&#39;type&#39;:&#39;2bit&#39;, &#39;threshold&#39;:0.5}</span>
<span class="sd"> See mxnet.KVStore.set_gradient_compression method for more details on gradient compression.</span>
<span class="sd"> update_on_kvstore : bool, default None</span>
<span class="sd"> Whether to perform parameter updates on kvstore. If None, then trainer will choose the more</span>
<span class="sd"> suitable option depending on the type of kvstore. If the `update_on_kvstore` argument is</span>
<span class="sd"> provided, environment variable `MXNET_UPDATE_ON_KVSTORE` will be ignored.</span>
<span class="sd"> Properties</span>
<span class="sd"> ----------</span>
<span class="sd"> learning_rate : float</span>
<span class="sd"> The current learning rate of the optimizer. Given an Optimizer object</span>
<span class="sd"> optimizer, its learning rate can be accessed as optimizer.learning_rate.</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">params</span><span class="p">,</span> <span class="n">optimizer</span><span class="p">,</span> <span class="n">optimizer_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">kvstore</span><span class="o">=</span><span class="s1">&#39;device&#39;</span><span class="p">,</span>
<span class="n">compression_params</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">update_on_kvstore</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">param_list</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="p">(</span><span class="nb">dict</span><span class="p">,</span> <span class="n">ParameterDict</span><span class="p">)):</span>
<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">params</span><span class="o">.</span><span class="n">keys</span><span class="p">())):</span>
<span class="n">param_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="n">key</span><span class="p">])</span>
<span class="n">params</span> <span class="o">=</span> <span class="n">param_list</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">&quot;First argument must be a list or dict of Parameters, &quot;</span> \
<span class="s2">&quot;got </span><span class="si">%s</span><span class="s2">.&quot;</span><span class="o">%</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">params</span><span class="p">)))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_params</span> <span class="o">=</span> <span class="p">[]</span>
<span class="c1"># parameters to initialize on the kvstore</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_contains_sparse_weight</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_contains_sparse_grad</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_param2idx</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">param</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">params</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="n">Parameter</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">&quot;First argument must be a list or dict of Parameters, &quot;</span> \
<span class="s2">&quot;got list of </span><span class="si">%s</span><span class="s2">.&quot;</span><span class="o">%</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">param</span><span class="p">)))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_param2idx</span><span class="p">[</span><span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">i</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">param</span><span class="p">)</span>
<span class="n">param</span><span class="o">.</span><span class="n">_set_trainer</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
<span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">_stype</span> <span class="o">!=</span> <span class="s1">&#39;default&#39;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_contains_sparse_weight</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">_grad_stype</span> <span class="o">!=</span> <span class="s1">&#39;default&#39;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_contains_sparse_grad</span> <span class="o">=</span> <span class="kc">True</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_compression_params</span> <span class="o">=</span> <span class="n">compression_params</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_contexts</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_check_contexts</span><span class="p">()</span>
<span class="n">optimizer_params</span> <span class="o">=</span> <span class="n">optimizer_params</span> <span class="k">if</span> <span class="n">optimizer_params</span> <span class="k">else</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_optimizer</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">optimizer_params</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_scale</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="o">.</span><span class="n">rescale_grad</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore_params</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;kvstore&#39;</span><span class="p">:</span> <span class="n">kvstore</span><span class="p">,</span> <span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">:</span> <span class="n">update_on_kvstore</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span> <span class="o">=</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_reset_kvstore</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">_check_contexts</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">contexts</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="p">:</span>
<span class="n">ctx</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">list_ctx</span><span class="p">()</span>
<span class="k">assert</span> <span class="n">contexts</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">contexts</span> <span class="o">==</span> <span class="n">ctx</span><span class="p">,</span> \
<span class="s2">&quot;All Parameters must be initialized on the same set of contexts, &quot;</span> \
<span class="s2">&quot;but Parameter </span><span class="si">%s</span><span class="s2"> is initialized on </span><span class="si">%s</span><span class="s2"> while previous Parameters &quot;</span> \
<span class="s2">&quot;are initialized on </span><span class="si">%s</span><span class="s2">.&quot;</span><span class="o">%</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">ctx</span><span class="p">),</span> <span class="nb">str</span><span class="p">(</span><span class="n">contexts</span><span class="p">))</span>
<span class="n">contexts</span> <span class="o">=</span> <span class="n">ctx</span>
<span class="k">return</span> <span class="n">contexts</span>
<span class="k">def</span> <span class="nf">_init_optimizer</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">optimizer</span><span class="p">,</span> <span class="n">optimizer_params</span><span class="p">):</span>
<span class="n">param_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">i</span><span class="p">:</span> <span class="n">param</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">param</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="p">)}</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">opt</span><span class="o">.</span><span class="n">Optimizer</span><span class="p">):</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="n">optimizer_params</span><span class="p">,</span> \
<span class="s2">&quot;optimizer_params must be None if optimizer is an instance of &quot;</span> \
<span class="s2">&quot;Optimizer instead of str&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span> <span class="o">=</span> <span class="n">optimizer</span>
<span class="c1"># param_dict must not be deep copied, so that if user mutate the lr_mult</span>
<span class="c1"># or wd_mult of some parameters, it takes effect.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="o">.</span><span class="n">param_dict</span> <span class="o">=</span> <span class="n">param_dict</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span> <span class="o">=</span> <span class="n">opt</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">param_dict</span><span class="o">=</span><span class="n">param_dict</span><span class="p">,</span>
<span class="o">**</span><span class="n">optimizer_params</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_updaters</span> <span class="o">=</span> <span class="p">[</span><span class="n">opt</span><span class="o">.</span><span class="n">get_updater</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="p">)</span> \
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_contexts</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">_init_params</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initialize parameters in the KVStore.</span>
<span class="sd"> Parameters with incomplete initialization are ignored.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span><span class="p">,</span> <span class="s2">&quot;Cannot initialize parameters in KVStore &quot;</span> \
<span class="s2">&quot;when KVStore is not initialized.&quot;</span>
<span class="n">params_to_init</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="p">:</span>
<span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span><span class="p">:</span>
<span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">_deferred_init</span><span class="p">:</span>
<span class="n">params_to_init</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">param</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">param_arrays</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">_check_and_get</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">_data</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span>
<span class="n">idx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_param2idx</span><span class="p">[</span><span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">]</span>
<span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">_stype</span> <span class="o">!=</span> <span class="s1">&#39;default&#39;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">init</span><span class="p">(</span><span class="n">idx</span><span class="p">,</span> <span class="n">param_arrays</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">broadcast</span><span class="p">(</span><span class="n">idx</span><span class="p">,</span> <span class="n">param_arrays</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">param_arrays</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span> <span class="o">=</span> <span class="n">params_to_init</span>
<span class="k">def</span> <span class="nf">_reset_kvstore</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Reset kvstore.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="ow">and</span> <span class="s1">&#39;dist&#39;</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">type</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">&quot;Cannot reset distributed KVStore.&quot;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span> <span class="o">=</span> <span class="kc">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span> <span class="o">=</span> <span class="p">[</span><span class="n">param</span> <span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">_init_kvstore</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Create kvstore.&quot;&quot;&quot;</span>
<span class="n">config</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kvstore_params</span>
<span class="c1"># configure kvstore, update_on_kvstore and self._distributed on three cases:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_contains_sparse_weight</span><span class="p">:</span>
<span class="c1"># If weight is sparse, kvstore must be present and the weight must be updated on kvstore.</span>
<span class="c1"># The training loop is the following:</span>
<span class="c1"># - row_sparse_pull(sparse_weight)</span>
<span class="c1"># - forward()</span>
<span class="c1"># - backward()</span>
<span class="c1"># - push_and_update(grad)</span>
<span class="c1"># - pull(weight)</span>
<span class="n">kvstore</span><span class="p">,</span> <span class="n">update_on_kvstore</span> <span class="o">=</span> <span class="n">_create_sparse_kvstore</span><span class="p">(</span><span class="n">config</span><span class="p">[</span><span class="s1">&#39;kvstore&#39;</span><span class="p">])</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span> <span class="o">=</span> <span class="s1">&#39;dist&#39;</span> <span class="ow">in</span> <span class="n">kvstore</span><span class="o">.</span><span class="n">type</span>
<span class="c1"># raise err if user provides unsupported configs</span>
<span class="k">if</span> <span class="n">config</span><span class="p">[</span><span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">False</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Cannot set update_on_kvstore=False when sparse weights &quot;</span>
<span class="s2">&quot;are present.&quot;</span><span class="p">)</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_contains_sparse_grad</span><span class="p">:</span>
<span class="c1"># For single node training with dense weight and sparse grad,</span>
<span class="c1"># we prefer update_on_kvstore=False because this is usually faster.</span>
<span class="c1"># This means we push and pull sparse gradients, and we do not store weight in kvstore.</span>
<span class="c1"># The training loop is the following:</span>
<span class="c1"># - forward()</span>
<span class="c1"># - backward()</span>
<span class="c1"># - push(grad)</span>
<span class="c1"># - pull(grad)</span>
<span class="c1"># - update(grad, weight)</span>
<span class="c1">#</span>
<span class="c1"># For multi-node training with dense weight and sparse grad,</span>
<span class="c1"># only update_on_kvstore=True is supported, due to the fact that</span>
<span class="c1"># kv.row_sparse_pull(grad) is not implemented.</span>
<span class="c1"># Therefore, we push sparse gradients and pull dense weights.</span>
<span class="c1"># The training loop contains:</span>
<span class="c1"># - forward()</span>
<span class="c1"># - backward()</span>
<span class="c1"># - push_and_update(grad)</span>
<span class="c1"># - pull(weight)</span>
<span class="n">arg_arrays</span> <span class="o">=</span> <span class="p">{</span><span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">:</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_contexts</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="p">}</span>
<span class="n">kvstore</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">_create_kvstore</span><span class="p">(</span><span class="n">config</span><span class="p">[</span><span class="s1">&#39;kvstore&#39;</span><span class="p">],</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_contexts</span><span class="p">),</span> <span class="n">arg_arrays</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span> <span class="o">=</span> <span class="s1">&#39;dist&#39;</span> <span class="ow">in</span> <span class="n">kvstore</span><span class="o">.</span><span class="n">type</span> <span class="k">if</span> <span class="n">kvstore</span> <span class="k">else</span> <span class="kc">False</span>
<span class="n">update_on_kvstore</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span>
<span class="c1"># raise err if user provides unsupported configs</span>
<span class="k">if</span> <span class="n">config</span><span class="p">[</span><span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">config</span><span class="p">[</span><span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">False</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Cannot set update_on_kvstore=False on dist kvstore &quot;</span>
<span class="s2">&quot;when sparse gradients are present.&quot;</span><span class="p">)</span>
<span class="n">update_on_kvstore</span> <span class="o">=</span> <span class="n">config</span><span class="p">[</span><span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">]</span>
<span class="c1"># raise err if a custom kvstore is used for sparse training</span>
<span class="k">if</span> <span class="n">kvstore</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">kvstore</span><span class="p">,</span> <span class="n">KVStore</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Cannot use </span><span class="si">{}</span><span class="s2"> for multi-device training with sparse gradients&quot;</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">kvstore</span><span class="p">)))</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># Training with dense weight and dense gradients.</span>
<span class="c1"># The only unsupported mode is async with update_on_kvstore=False</span>
<span class="n">arg_arrays</span> <span class="o">=</span> <span class="p">{</span><span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">:</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_contexts</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="p">}</span>
<span class="n">kvstore</span><span class="p">,</span> <span class="n">update_on_kvstore</span> <span class="o">=</span> <span class="n">_create_kvstore</span><span class="p">(</span><span class="n">config</span><span class="p">[</span><span class="s1">&#39;kvstore&#39;</span><span class="p">],</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_contexts</span><span class="p">),</span>
<span class="n">arg_arrays</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span> <span class="o">=</span> <span class="s1">&#39;dist&#39;</span> <span class="ow">in</span> <span class="n">kvstore</span><span class="o">.</span><span class="n">type</span> <span class="k">if</span> <span class="n">kvstore</span> <span class="k">else</span> <span class="kc">False</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span> <span class="ow">and</span> <span class="s1">&#39;async&#39;</span> <span class="ow">in</span> <span class="n">kvstore</span><span class="o">.</span><span class="n">type</span><span class="p">:</span>
<span class="n">update_on_kvstore</span> <span class="o">=</span> <span class="kc">True</span>
<span class="c1"># raise err if user provides unsupported configs</span>
<span class="k">if</span> <span class="n">config</span><span class="p">[</span><span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">]</span> <span class="ow">is</span> <span class="kc">False</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Please set update_on_kvstore=True &quot;</span>
<span class="s2">&quot;when training in async mode.&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">config</span><span class="p">[</span><span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">update_on_kvstore</span> <span class="o">=</span> <span class="n">config</span><span class="p">[</span><span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">]</span>
<span class="c1"># raise err if update_on_kvstore is set to True with kvstores that do not support optimizers</span>
<span class="k">if</span> <span class="n">update_on_kvstore</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">kvstore</span><span class="o">.</span><span class="n">is_capable</span><span class="p">(</span><span class="s1">&#39;optimizer&#39;</span><span class="p">):</span>
<span class="k">if</span> <span class="n">config</span><span class="p">[</span><span class="s1">&#39;update_on_kvstore&#39;</span><span class="p">]:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Please set update_on_kvstore=False &quot;</span>
<span class="s2">&quot;when training with </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="nb">type</span><span class="p">(</span><span class="n">kvstore</span><span class="p">)))</span>
<span class="n">update_on_kvstore</span> <span class="o">=</span> <span class="kc">False</span>
<span class="c1"># set grad compression and optimizers</span>
<span class="k">if</span> <span class="n">kvstore</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compression_params</span><span class="p">:</span>
<span class="n">kvstore</span><span class="o">.</span><span class="n">set_gradient_compression</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_compression_params</span><span class="p">)</span>
<span class="k">if</span> <span class="n">update_on_kvstore</span><span class="p">:</span>
<span class="c1"># optimizer preferably needs to be set before init for multiprecision</span>
<span class="n">kvstore</span><span class="o">.</span><span class="n">set_optimizer</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="o">=</span> <span class="n">kvstore</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span> <span class="o">=</span> <span class="n">update_on_kvstore</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span> <span class="o">=</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span> <span class="o">=</span> <span class="kc">True</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">learning_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="p">,</span> <span class="n">opt</span><span class="o">.</span><span class="n">Optimizer</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">UserWarning</span><span class="p">(</span><span class="s2">&quot;Optimizer has to be defined before its learning &quot;</span>
<span class="s2">&quot;rate can be accessed.&quot;</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="o">.</span><span class="n">learning_rate</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">optimizer</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="p">,</span> <span class="n">opt</span><span class="o">.</span><span class="n">Optimizer</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">UserWarning</span><span class="p">(</span><span class="s2">&quot;Optimizer has not been initialized yet&quot;</span><span class="p">)</span>
<div class="viewcode-block" id="Trainer.set_learning_rate"><a class="viewcode-back" href="../../../api/gluon/trainer.html#mxnet.gluon.Trainer.set_learning_rate">[docs]</a> <span class="k">def</span> <span class="nf">set_learning_rate</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">lr</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Sets a new learning rate of the optimizer.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> lr : float</span>
<span class="sd"> The new learning rate of the optimizer.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="p">,</span> <span class="n">opt</span><span class="o">.</span><span class="n">Optimizer</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">UserWarning</span><span class="p">(</span><span class="s2">&quot;Optimizer has to be defined before its learning &quot;</span>
<span class="s2">&quot;rate is mutated.&quot;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="o">.</span><span class="n">set_learning_rate</span><span class="p">(</span><span class="n">lr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_row_sparse_pull</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">parameter</span><span class="p">,</span> <span class="n">out</span><span class="p">,</span> <span class="n">row_id</span><span class="p">,</span> <span class="n">full_idx</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Internal method to invoke pull operations on KVStore. If `full_idx` is set to True,</span>
<span class="sd"> `kv.pull` is preferred instead of `kv.row_sparse_pull`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># initialize kv and params if not already</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_kvstore</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_params</span><span class="p">()</span>
<span class="n">idx</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_param2idx</span><span class="p">[</span><span class="n">parameter</span><span class="o">.</span><span class="n">name</span><span class="p">]</span>
<span class="k">if</span> <span class="n">full_idx</span> <span class="ow">and</span> <span class="s1">&#39;dist&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">type</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">row_id</span><span class="o">.</span><span class="n">size</span> <span class="o">==</span> <span class="n">out</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="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">pull</span><span class="p">(</span><span class="n">idx</span><span class="p">,</span> <span class="n">out</span><span class="o">=</span><span class="n">out</span><span class="p">,</span> <span class="n">priority</span><span class="o">=-</span><span class="n">idx</span><span class="p">,</span> <span class="n">ignore_sparse</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="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">row_sparse_pull</span><span class="p">(</span><span class="n">idx</span><span class="p">,</span> <span class="n">out</span><span class="o">=</span><span class="n">out</span><span class="p">,</span> <span class="n">row_ids</span><span class="o">=</span><span class="n">row_id</span><span class="p">,</span> <span class="n">priority</span><span class="o">=-</span><span class="n">idx</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_check_and_rescale_grad</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">scale</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="o">.</span><span class="n">rescale_grad</span> <span class="o">!=</span> <span class="n">scale</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">UserWarning</span><span class="p">(</span><span class="s1">&#39;Possible change in the `batch_size` from previous &#39;</span>
<span class="s1">&#39;`step` detected. Optimizer gradient normalizing &#39;</span>
<span class="s1">&#39;factor will not change w.r.t new batch_size when &#39;</span>
<span class="s1">&#39;update_on_kvstore=True and when distributed kvstore &#39;</span>
<span class="s1">&#39;is used.&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span><span class="o">.</span><span class="n">rescale_grad</span> <span class="o">=</span> <span class="n">scale</span>
<div class="viewcode-block" id="Trainer.step"><a class="viewcode-back" href="../../../api/gluon/trainer.html#mxnet.gluon.Trainer.step">[docs]</a> <span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">ignore_stale_grad</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Makes one step of parameter update. Should be called after</span>
<span class="sd"> `autograd.backward()` and outside of `record()` scope.</span>
<span class="sd"> For normal parameter updates, `step()` should be used, which internally calls</span>
<span class="sd"> `allreduce_grads()` and then `update()`. However, if you need to get the reduced</span>
<span class="sd"> gradients to perform certain transformation, such as in gradient clipping, then</span>
<span class="sd"> you may want to manually call `allreduce_grads()` and `update()` separately.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> batch_size : int</span>
<span class="sd"> Batch size of data processed. Gradient will be normalized by `1/batch_size`.</span>
<span class="sd"> Set this to 1 if you normalized loss manually with `loss = mean(loss)`.</span>
<span class="sd"> ignore_stale_grad : bool, optional, default=False</span>
<span class="sd"> If true, ignores Parameters with stale gradient (gradient that has not</span>
<span class="sd"> been updated by `backward` after last step) and skip update.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">rescale_grad</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scale</span> <span class="o">/</span> <span class="n">batch_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_check_and_rescale_grad</span><span class="p">(</span><span class="n">rescale_grad</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_kvstore</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_params</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_allreduce_grads</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_update</span><span class="p">(</span><span class="n">ignore_stale_grad</span><span class="p">)</span></div>
<div class="viewcode-block" id="Trainer.allreduce_grads"><a class="viewcode-back" href="../../../api/gluon/trainer.html#mxnet.gluon.Trainer.allreduce_grads">[docs]</a> <span class="k">def</span> <span class="nf">allreduce_grads</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;For each parameter, reduce the gradients from different contexts.</span>
<span class="sd"> Should be called after `autograd.backward()`, outside of `record()` scope,</span>
<span class="sd"> and before `trainer.update()`.</span>
<span class="sd"> For normal parameter updates, `step()` should be used, which internally calls</span>
<span class="sd"> `allreduce_grads()` and then `update()`. However, if you need to get the reduced</span>
<span class="sd"> gradients to perform certain transformation, such as in gradient clipping, then</span>
<span class="sd"> you may want to manually call `allreduce_grads()` and `update()` separately.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_kvstore</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_params</span><span class="p">()</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span><span class="p">),</span> \
<span class="s1">&#39;allreduce_grads() when parameters are updated on kvstore &#39;</span> \
<span class="s1">&#39;is not supported. Try setting `update_on_kvstore` &#39;</span> \
<span class="s1">&#39;to False when creating trainer.&#39;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_allreduce_grads</span><span class="p">()</span></div>
<span class="k">def</span> <span class="nf">_allreduce_grads</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># nothing to reduce</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="p">:</span>
<span class="k">return</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">param</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="p">):</span>
<span class="k">if</span> <span class="n">param</span><span class="o">.</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">grad_list</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">list_grad</span><span class="p">()</span>
<span class="c1"># sparse gradients, call push and pull separately</span>
<span class="k">if</span> <span class="n">grad_list</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">stype</span> <span class="o">!=</span> <span class="s1">&#39;default&#39;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">push</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">grad_list</span><span class="p">,</span> <span class="n">priority</span><span class="o">=-</span><span class="n">i</span><span class="p">)</span>
<span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">_stype</span> <span class="o">==</span> <span class="s1">&#39;default&#39;</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span><span class="p">:</span>
<span class="n">pull_list</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">list_data</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">pull_list</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">list_grad</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">pull</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">pull_list</span><span class="p">,</span> <span class="n">priority</span><span class="o">=-</span><span class="n">i</span><span class="p">,</span>
<span class="n">ignore_sparse</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_distributed</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># allreduce dense gradients if not update_on_kvstore,</span>
<span class="c1"># otherwise push dense gradients, pull dense weights</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">pushpull</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">grad_list</span><span class="p">,</span> <span class="n">out</span><span class="o">=</span><span class="n">param</span><span class="o">.</span><span class="n">list_data</span><span class="p">(),</span> <span class="n">priority</span><span class="o">=-</span><span class="n">i</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">_kvstore</span><span class="o">.</span><span class="n">pushpull</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">grad_list</span><span class="p">,</span> <span class="n">priority</span><span class="o">=-</span><span class="n">i</span><span class="p">)</span>
<div class="viewcode-block" id="Trainer.update"><a class="viewcode-back" href="../../../api/gluon/trainer.html#mxnet.gluon.Trainer.update">[docs]</a> <span class="k">def</span> <span class="nf">update</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">ignore_stale_grad</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Makes one step of parameter update.</span>
<span class="sd"> Should be called after `autograd.backward()` and outside of `record()` scope,</span>
<span class="sd"> and after `trainer.update()`.</span>
<span class="sd"> For normal parameter updates, `step()` should be used, which internally calls</span>
<span class="sd"> `allreduce_grads()` and then `update()`. However, if you need to get the reduced</span>
<span class="sd"> gradients to perform certain transformation, such as in gradient clipping, then</span>
<span class="sd"> you may want to manually call `allreduce_grads()` and `update()` separately.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> batch_size : int</span>
<span class="sd"> Batch size of data processed. Gradient will be normalized by `1/batch_size`.</span>
<span class="sd"> Set this to 1 if you normalized loss manually with `loss = mean(loss)`.</span>
<span class="sd"> ignore_stale_grad : bool, optional, default=False</span>
<span class="sd"> If true, ignores Parameters with stale gradient (gradient that has not</span>
<span class="sd"> been updated by `backward` after last step) and skip update.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_kvstore</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_params</span><span class="p">()</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span><span class="p">),</span> \
<span class="s1">&#39;update() when parameters are updated on kvstore &#39;</span> \
<span class="s1">&#39;is not supported. Try setting `update_on_kvstore` &#39;</span> \
<span class="s1">&#39;to False when creating trainer.&#39;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_check_and_rescale_grad</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_scale</span> <span class="o">/</span> <span class="n">batch_size</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_update</span><span class="p">(</span><span class="n">ignore_stale_grad</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_update</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">ignore_stale_grad</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="n">loss_scaler</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="s1">&#39;_amp_loss_scaler&#39;</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">if</span> <span class="n">loss_scaler</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">loss_scaler</span><span class="o">.</span><span class="n">has_overflow</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="p">):</span>
<span class="k">return</span> <span class="c1"># skip on overflow</span>
<span class="n">updates</span> <span class="o">=</span> <span class="p">[[]</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_updaters</span><span class="p">]</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">param</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_params</span><span class="p">):</span>
<span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">grad_req</span> <span class="o">==</span> <span class="s1">&#39;null&#39;</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">ignore_stale_grad</span><span class="p">:</span>
<span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">param</span><span class="o">.</span><span class="n">_check_and_get</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">_data</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">data</span><span class="o">.</span><span class="n">_fresh_grad</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">UserWarning</span><span class="p">(</span>
<span class="s2">&quot;Gradient of Parameter `</span><span class="si">%s</span><span class="s2">` on context </span><span class="si">%s</span><span class="s2"> has not been updated &quot;</span>
<span class="s2">&quot;by backward since last `step`. This could mean a bug in your &quot;</span>
<span class="s2">&quot;model that made it only use a subset of the Parameters (Blocks) &quot;</span>
<span class="s2">&quot;for this iteration. If you are intentionally only using a subset, &quot;</span>
<span class="s2">&quot;call step with ignore_stale_grad=True to suppress this &quot;</span>
<span class="s2">&quot;warning and skip updating of Parameters with stale gradient&quot;</span> \
<span class="o">%</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">context</span><span class="p">)))</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span><span class="p">:</span>
<span class="k">continue</span>
<span class="k">for</span> <span class="n">upd</span><span class="p">,</span> <span class="n">arr</span><span class="p">,</span> <span class="n">grad</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">updates</span><span class="p">,</span> <span class="n">param</span><span class="o">.</span><span class="n">list_data</span><span class="p">(),</span> <span class="n">param</span><span class="o">.</span><span class="n">list_grad</span><span class="p">()):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">ignore_stale_grad</span> <span class="ow">or</span> <span class="n">arr</span><span class="o">.</span><span class="n">_fresh_grad</span><span class="p">:</span>
<span class="n">upd</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">i</span><span class="p">,</span> <span class="n">grad</span><span class="p">,</span> <span class="n">arr</span><span class="p">))</span>
<span class="n">arr</span><span class="o">.</span><span class="n">_fresh_grad</span> <span class="o">=</span> <span class="kc">False</span>
<span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span><span class="p">):</span>
<span class="k">for</span> <span class="n">updater</span><span class="p">,</span> <span class="n">upd</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_updaters</span><span class="p">,</span> <span class="n">updates</span><span class="p">):</span>
<span class="k">if</span> <span class="n">upd</span><span class="p">:</span>
<span class="n">i</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">g</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="n">upd</span><span class="p">)</span>
<span class="n">updater</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">g</span><span class="p">)</span>
<div class="viewcode-block" id="Trainer.save_states"><a class="viewcode-back" href="../../../api/gluon/trainer.html#mxnet.gluon.Trainer.save_states">[docs]</a> <span class="k">def</span> <span class="nf">save_states</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fname</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Saves trainer states (e.g. optimizer, momentum) to a file.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> fname : str</span>
<span class="sd"> Path to output states file.</span>
<span class="sd"> Note</span>
<span class="sd"> ----</span>
<span class="sd"> `optimizer.param_dict`, which contains Parameter information (such as</span>
<span class="sd"> `lr_mult` and `wd_mult`) will not be saved.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_kvstore</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_params</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span><span class="p">:</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span><span class="p">,</span> <span class="s2">&quot;Cannot save trainer states when some &quot;</span> \
<span class="s2">&quot;parameters are not yet initialized in kvstore.&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">save_optimizer_states</span><span class="p">(</span><span class="n">fname</span><span class="p">,</span> <span class="n">dump_optimizer</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="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">fname</span><span class="p">,</span> <span class="s1">&#39;wb&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">fout</span><span class="p">:</span>
<span class="n">fout</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_updaters</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">get_states</span><span class="p">(</span><span class="n">dump_optimizer</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span></div>
<div class="viewcode-block" id="Trainer.load_states"><a class="viewcode-back" href="../../../api/gluon/trainer.html#mxnet.gluon.Trainer.load_states">[docs]</a> <span class="k">def</span> <span class="nf">load_states</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fname</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Loads trainer states (e.g. optimizer, momentum) from a file.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> fname : str</span>
<span class="sd"> Path to input states file.</span>
<span class="sd"> Note</span>
<span class="sd"> ----</span>
<span class="sd"> `optimizer.param_dict`, which contains Parameter information (such as</span>
<span class="sd"> `lr_mult` and `wd_mult`) will not be loaded from the file, but rather set</span>
<span class="sd"> based on current Trainer&#39;s parameters.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kv_initialized</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_kvstore</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_params_to_init</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_params</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_update_on_kvstore</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">load_optimizer_states</span><span class="p">(</span><span class="n">fname</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kvstore</span><span class="o">.</span><span class="n">_updater</span><span class="o">.</span><span class="n">optimizer</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">fname</span><span class="p">,</span> <span class="s1">&#39;rb&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="n">states</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">()</span>
<span class="k">for</span> <span class="n">updater</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_updaters</span><span class="p">:</span>
<span class="n">updater</span><span class="o">.</span><span class="n">set_states</span><span class="p">(</span><span class="n">states</span><span class="p">)</span>
<span class="n">updater</span><span class="o">.</span><span class="n">optimizer</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_updaters</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">optimizer</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_optimizer</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_updaters</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">optimizer</span>
<span class="n">param_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">i</span><span class="p">:</span> <span class="n">param</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">param</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</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">_optimizer</span><span class="o">.</span><span class="n">param_dict</span> <span class="o">=</span> <span class="n">param_dict</span></div></div>
</pre></div>
<hr class="feedback-hr-top" />
<div class="feedback-container">
<div class="feedback-question">Did this page help you?</div>
<div class="feedback-answer-container">
<div class="feedback-answer yes-link" data-response="yes">Yes</div>
<div class="feedback-answer no-link" data-response="no">No</div>
</div>
<div class="feedback-thank-you">Thanks for your feedback!</div>
</div>
<hr class="feedback-hr-bottom" />
</div>
<div class="side-doc-outline">
<div class="side-doc-outline--content">
</div>
</div>
<div class="clearer"></div>
</div><div class="pagenation">
</div>
<footer class="site-footer h-card">
<div class="wrapper">
<div class="row">
<div class="col-4">
<h4 class="footer-category-title">Resources</h4>
<ul class="contact-list">
<li><a 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>