versions/1.2.1/api/python/gluon/gluon.html

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta content="IE=edge" http-equiv="X-UA-Compatible"/> <meta content="width=device-width, initial-scale=1" name="viewport"/> <meta content="Gluon Package" property="og:title"> <meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image"> <meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image:secure_url"> <meta content="Gluon Package" property="og:description"/> <title>Gluon Package — mxnet documentation</title> <link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/> <link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/> <link href="../../../_static/basic.css" rel="stylesheet" type="text/css"> <link href="../../../_static/pygments.css" rel="stylesheet" type="text/css"> <link href="../../../_static/mxnet.css" rel="stylesheet" type="text/css"/> <script type="text/javascript"> var DOCUMENTATION_OPTIONS = { URL_ROOT: '../../../', VERSION: '', COLLAPSE_INDEX: false, FILE_SUFFIX: '.html', HAS_SOURCE: true, SOURCELINK_SUFFIX: '.txt' }; </script> <script src="https://code.jquery.com/jquery-1.11.1.min.js" type="text/javascript"></script> <script src="../../../_static/underscore.js" type="text/javascript"></script> <script src="../../../_static/searchtools_custom.js" type="text/javascript"></script> <script src="../../../_static/doctools.js" type="text/javascript"></script> <script src="../../../_static/selectlang.js" type="text/javascript"></script> <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script> <script type="text/javascript"> jQuery(function() { Search.loadIndex("/versions/1.2.1/searchindex.js"); Search.init();}); </script> <script> (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); ga('create', 'UA-96378503-1', 'auto'); ga('send', 'pageview'); </script>          <link href="../../../genindex.html" rel="index" title="Index"> <link href="../../../search.html" rel="search" title="Search"/> <link href="../index.html" rel="up" title="MXNet - Python API"/> <link href="nn.html" rel="next" title="Gluon Neural Network Layers"/> <link href="../autograd/autograd.html" rel="prev" title="Autograd Package"/> <link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/> </link></link></link></meta></meta></meta></head> <body background="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-background-compressed.jpeg" role="document"> <div class="content-block"><div class="navbar navbar-fixed-top"> <div class="container" id="navContainer"> <div class="innder" id="header-inner"> <h1 id="logo-wrap"> <a href="../../../" id="logo"><img src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet_logo.png"/></a> </h1> <nav class="nav-bar" id="main-nav"> <a class="main-nav-link" href="/versions/1.2.1/install/index.html">Install</a> <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon </a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> <li><a class="main-nav-link" href="/versions/1.2.1/tutorials/gluon/gluon.html">About</a></li> <li><a class="main-nav-link" href="https://www.d2l.ai/">Dive into Deep Learning</a></li> <li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li> <li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li> </ul> <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API </a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> <li><a class="main-nav-link" href="/versions/1.2.1/api/python/index.html">Python</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/c++/index.html">C++</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/julia/index.html">Julia</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/perl/index.html">Perl</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/r/index.html">R</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/scala/index.html">Scala</a></li> </ul> <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs </a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs"> <li><a class="main-nav-link" href="/versions/1.2.1/faq/index.html">FAQ</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/tutorials/index.html">Tutorials</a> <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/1.2.1/example">Examples</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/architecture/index.html">Architecture</a></li> <li><a class="main-nav-link" href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/model_zoo/index.html">Model Zoo</a></li> <li><a class="main-nav-link" href="https://github.com/onnx/onnx-mxnet">ONNX</a></li> </li></ul> <a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community </a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-community"> <li><a class="main-nav-link" href="http://discuss.mxnet.io">Forum</a></li> <li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/1.2.1">Github</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/community/contribute.html">Contribute</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/community/powered_by.html">Powered By</a></li> </ul> <a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">1.2.1</a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a href="/">master</a></li><li><a href="/versions/1.7.0/">1.7.0</a></li><li><a href=/versions/1.6.0/>1.6.0</a></li><li><a href=/versions/1.5.0/>1.5.0</a></li><li><a href=/versions/1.4.1/>1.4.1</a></li><li><a href=/versions/1.3.1/>1.3.1</a></li><li><a href=/versions/1.2.1/>1.2.1</a></li><li><a href=/versions/1.1.0/>1.1.0</a></li><li><a href=/versions/1.0.0/>1.0.0</a></li><li><a href=/versions/0.12.1/>0.12.1</a></li><li><a href=/versions/0.11.0/>0.11.0</a></li></ul></nav> <script> function getRootPath(){ return "../../../" } </script> <div class="burgerIcon dropdown"> <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button">☰</a> <ul class="dropdown-menu" id="burgerMenu"> <li><a href="/versions/1.2.1/install/index.html">Install</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/tutorials/index.html">Tutorials</a></li> <li class="dropdown-submenu dropdown"> <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Gluon</a> <ul class="dropdown-menu navbar-menu" id="package-dropdown-menu"> <li><a class="main-nav-link" href="/versions/1.2.1/tutorials/gluon/gluon.html">About</a></li> <li><a class="main-nav-link" href="http://gluon.mxnet.io">The Straight Dope (Tutorials)</a></li> <li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li> <li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li> </ul> </li> <li class="dropdown-submenu"> <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">API</a> <ul class="dropdown-menu"> <li><a class="main-nav-link" href="/versions/1.2.1/api/python/index.html">Python</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/c++/index.html">C++</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/julia/index.html">Julia</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/perl/index.html">Perl</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/r/index.html">R</a></li> <li><a class="main-nav-link" href="/versions/1.2.1/api/scala/index.html">Scala</a></li> </ul> </li> <li class="dropdown-submenu"> <a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Docs</a> <ul class="dropdown-menu"> <li><a href="/versions/1.2.1/faq/index.html" tabindex="-1">FAQ</a></li> <li><a href="/versions/1.2.1/tutorials/index.html" tabindex="-1">Tutorials</a></li> <li><a href="https://github.com/apache/incubator-mxnet/tree/1.2.1/example" tabindex="-1">Examples</a></li> <li><a href="/versions/1.2.1/architecture/index.html" tabindex="-1">Architecture</a></li> <li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home" tabindex="-1">Developer Wiki</a></li> <li><a href="/versions/1.2.1/model_zoo/index.html" tabindex="-1">Gluon Model Zoo</a></li> <li><a href="https://github.com/onnx/onnx-mxnet" tabindex="-1">ONNX</a></li> </ul> </li> <li class="dropdown-submenu dropdown"> <a aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" role="button" tabindex="-1">Community</a> <ul class="dropdown-menu"> <li><a href="http://discuss.mxnet.io" tabindex="-1">Forum</a></li> <li><a href="https://github.com/apache/incubator-mxnet/tree/1.2.1" tabindex="-1">Github</a></li> <li><a href="/versions/1.2.1/community/contribute.html" tabindex="-1">Contribute</a></li> <li><a href="/versions/1.2.1/community/powered_by.html" tabindex="-1">Powered By</a></li> </ul> </li> <li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">1.2.1</a><ul class="dropdown-menu"><li><a tabindex="-1" href=/>master</a></li><li><a tabindex="-1" href=/versions/1.6.0/>1.6.0</a></li><li><a tabindex="-1" href=/versions/1.5.0/>1.5.0</a></li><li><a tabindex="-1" href=/versions/1.4.1/>1.4.1</a></li><li><a tabindex="-1" href=/versions/1.3.1/>1.3.1</a></li><li><a tabindex="-1" href=/versions/1.2.1/>1.2.1</a></li><li><a tabindex="-1" href=/versions/1.1.0/>1.1.0</a></li><li><a tabindex="-1" href=/versions/1.0.0/>1.0.0</a></li><li><a tabindex="-1" href=/versions/0.12.1/>0.12.1</a></li><li><a tabindex="-1" href=/versions/0.11.0/>0.11.0</a></li></ul></li></ul> </div> <div class="plusIcon dropdown"> <a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"></a> <ul class="dropdown-menu dropdown-menu-right" id="plusMenu"></ul> </div> <div id="search-input-wrap"> <form action="../../../search.html" autocomplete="off" class="" method="get" role="search"> <div class="form-group inner-addon left-addon"> <input class="form-control" name="q" placeholder="Search" type="text"/> </div> <input name="check_keywords" type="hidden" value="yes"> <input name="area" type="hidden" value="default"/> </input></form> <div id="search-preview"></div> </div> <div id="searchIcon"> </div>            </div> </div> </div> <script type="text/javascript"> $('body').css('background', 'white'); </script> <div class="container"> <div class="row"> <div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation"> <div class="sphinxsidebarwrapper"> <ul class="current"> <li class="toctree-l1 current"><a class="reference internal" href="../index.html">Python Documents</a><ul class="current"> <li class="toctree-l2"><a class="reference internal" href="../index.html#ndarray-api">NDArray API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#symbol-api">Symbol API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#module-api">Module API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#autograd-api">Autograd API</a></li> <li class="toctree-l2 current"><a class="reference internal" href="../index.html#gluon-api">Gluon API</a><ul class="current"> <li class="toctree-l3 current"><a class="current reference internal" href="#">Gluon Package</a><ul> <li class="toctree-l4"><a class="reference internal" href="#overview">Overview</a></li> <li class="toctree-l4"><a class="reference internal" href="#parameter">Parameter</a></li> <li class="toctree-l4"><a class="reference internal" href="#containers">Containers</a></li> <li class="toctree-l4"><a class="reference internal" href="#trainer">Trainer</a></li> <li class="toctree-l4"><a class="reference internal" href="#utilities">Utilities</a></li> <li class="toctree-l4"><a class="reference internal" href="#api-reference">API Reference</a></li> </ul> </li> <li class="toctree-l3"><a class="reference internal" href="nn.html">Gluon Neural Network Layers</a></li> <li class="toctree-l3"><a class="reference internal" href="rnn.html">Gluon Recurrent Neural Network API</a></li> <li class="toctree-l3"><a class="reference internal" href="loss.html">Gluon Loss API</a></li> <li class="toctree-l3"><a class="reference internal" href="data.html">Gluon Data API</a></li> <li class="toctree-l3"><a class="reference internal" href="model_zoo.html">Gluon Model Zoo</a></li> <li class="toctree-l3"><a class="reference internal" href="contrib.html">Gluon Contrib API</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../index.html#kvstore-api">KVStore API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#io-api">IO API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#image-api">Image API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#optimization-api">Optimization API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#callback-api">Callback API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#metric-api">Metric API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#run-time-compilation-api">Run-Time Compilation API</a></li> <li class="toctree-l2"><a class="reference internal" href="../index.html#contrib-package">Contrib Package</a></li> </ul> </li> <li class="toctree-l1"><a class="reference internal" href="../../r/index.html">R Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../julia/index.html">Julia Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../c++/index.html">C++ Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../scala/index.html">Scala Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../perl/index.html">Perl Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../faq/index.html">HowTo Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../architecture/index.html">System Documents</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../tutorials/index.html">Tutorials</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../community/index.html">Community</a></li> </ul> </div> </div> <div class="content"> <div class="page-tracker"></div> <div class="section" id="gluon-package"> <h1>Gluon Package<a class="headerlink" href="#gluon-package" title="Permalink to this headline">¶</a></h1> <script src="../../_static/js/auto_module_index.js" type="text/javascript"></script><div class="section" id="overview"> <h2>Overview<a class="headerlink" href="#overview" title="Permalink to this headline">¶</a></h2> Gluon package is a high-level interface for MXNet designed to be easy to use while keeping most of the flexibility of low level API. Gluon supports both imperative and symbolic programming, making it easy to train complex models imperatively in Python and then deploy with symbolic graph in C++ and Scala. <div class="toctree-wrapper compound"> <ul> <li class="toctree-l1"><a class="reference internal" href="nn.html">Gluon Neural Network Layers</a></li> <li class="toctree-l1"><a class="reference internal" href="rnn.html">Gluon Recurrent Neural Network API</a></li> <li class="toctree-l1"><a class="reference internal" href="loss.html">Gluon Loss API</a></li> <li class="toctree-l1"><a class="reference internal" href="data.html">Gluon Data API</a></li> <li class="toctree-l1"><a class="reference internal" href="model_zoo.html">Gluon Model Zoo</a></li> <li class="toctree-l1"><a class="reference internal" href="contrib.html">Gluon Contrib API</a></li> </ul> </div> </div> <div class="section" id="parameter"> <h2>Parameter<a class="headerlink" href="#parameter" title="Permalink to this headline">¶</a></h2> <table border="1" class="longtable docutils"> <colgroup> <col width="10%"/> <col width="90%"/> </colgroup> <tbody valign="top"> <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.Parameter" title="mxnet.gluon.Parameter"><code class="xref py py-obj docutils literal">Parameter</code></a></td> <td>A Container holding parameters (weights) of Blocks.</td> </tr> <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.Constant" title="mxnet.gluon.Constant"><code class="xref py py-obj docutils literal">Constant</code></a></td> <td>A constant parameter for holding immutable tensors.</td> </tr> <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict"><code class="xref py py-obj docutils literal">ParameterDict</code></a></td> <td>A dictionary managing a set of parameters.</td> </tr> </tbody> </table> </div> <div class="section" id="containers"> <h2>Containers<a class="headerlink" href="#containers" title="Permalink to this headline">¶</a></h2> <table border="1" class="longtable docutils"> <colgroup> <col width="10%"/> <col width="90%"/> </colgroup> <tbody valign="top"> <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-obj docutils literal">Block</code></a></td> <td>Base class for all neural network layers and models.</td> </tr> <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.HybridBlock" title="mxnet.gluon.HybridBlock"><code class="xref py py-obj docutils literal">HybridBlock</code></a></td> <td><cite>HybridBlock</cite> supports forwarding with both Symbol and NDArray.</td> </tr> <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.SymbolBlock" title="mxnet.gluon.SymbolBlock"><code class="xref py py-obj docutils literal">SymbolBlock</code></a></td> <td>Construct block from symbol.</td> </tr> <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.nn.Sequential" title="mxnet.gluon.nn.Sequential"><code class="xref py py-obj docutils literal">nn.Sequential</code></a></td> <td>Stacks Blocks sequentially.</td> </tr> <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.nn.HybridSequential" title="mxnet.gluon.nn.HybridSequential"><code class="xref py py-obj docutils literal">nn.HybridSequential</code></a></td> <td>Stacks HybridBlocks sequentially.</td> </tr> </tbody> </table> </div> <div class="section" id="trainer"> <h2>Trainer<a class="headerlink" href="#trainer" title="Permalink to this headline">¶</a></h2> <table border="1" class="longtable docutils"> <colgroup> <col width="10%"/> <col width="90%"/> </colgroup> <tbody valign="top"> <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.Trainer" title="mxnet.gluon.Trainer"><code class="xref py py-obj docutils literal">Trainer</code></a></td> <td>Applies an <cite>Optimizer</cite> on a set of Parameters.</td> </tr> </tbody> </table> </div> <div class="section" id="utilities"> <h2>Utilities<a class="headerlink" href="#utilities" title="Permalink to this headline">¶</a></h2> <table border="1" class="longtable docutils"> <colgroup> <col width="10%"/> <col width="90%"/> </colgroup> <tbody valign="top"> <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.utils.split_data" title="mxnet.gluon.utils.split_data"><code class="xref py py-obj docutils literal">split_data</code></a></td> <td>Splits an NDArray into <cite>num_slice</cite> slices along <cite>batch_axis</cite>.</td> </tr> <tr class="row-even"><td><a class="reference internal" href="#mxnet.gluon.utils.split_and_load" title="mxnet.gluon.utils.split_and_load"><code class="xref py py-obj docutils literal">split_and_load</code></a></td> <td>Splits an NDArray into <cite>len(ctx_list)</cite> slices along <cite>batch_axis</cite> and loads each slice to one context in <cite>ctx_list</cite>.</td> </tr> <tr class="row-odd"><td><a class="reference internal" href="#mxnet.gluon.utils.clip_global_norm" title="mxnet.gluon.utils.clip_global_norm"><code class="xref py py-obj docutils literal">clip_global_norm</code></a></td> <td>Rescales NDArrays so that the sum of their 2-norm is smaller than <cite>max_norm</cite>.</td> </tr> </tbody> </table> </div> <div class="section" id="api-reference"> <h2>API Reference<a class="headerlink" href="#api-reference" title="Permalink to this headline">¶</a></h2> <script src="../../_static/js/auto_module_index.js" type="text/javascript"></script>Neural network module. <dl class="class"> <dt id="mxnet.gluon.Block"> class <code class="descclassname">mxnet.gluon.</code><code class="descname">Block</code>(prefix=None, params=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block">[source]</a><a class="headerlink" href="#mxnet.gluon.Block" title="Permalink to this definition">¶</a></dt> <dd>Base class for all neural network layers and models. Your models should subclass this class. <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a> can be nested recursively in a tree structure. You can create and assign child <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a> as regular attributes: <div class="highlight-default"><div class="highlight"><pre>from mxnet.gluon import Block, nn from mxnet import ndarray as F class Model(Block): def __init__(self, **kwargs): super(Model, self).__init__(**kwargs) # use name_scope to give child Blocks appropriate names. with self.name_scope(): self.dense0 = nn.Dense(20) self.dense1 = nn.Dense(20) def forward(self, x): x = F.relu(self.dense0(x)) return F.relu(self.dense1(x)) model = Model() model.initialize(ctx=mx.cpu(0)) model(F.zeros((10, 10), ctx=mx.cpu(0))) </pre></div> </div> Child <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a> assigned this way will be registered and <a class="reference internal" href="#mxnet.gluon.Block.collect_params" title="mxnet.gluon.Block.collect_params"><code class="xref py py-meth docutils literal">collect_params()</code></a> will collect their Parameters recursively. You can also manually register child blocks with <a class="reference internal" href="#mxnet.gluon.Block.register_child" title="mxnet.gluon.Block.register_child"><code class="xref py py-meth docutils literal">register_child()</code></a>. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>prefix (str) – Prefix acts like a name space. All children blocks created in parent block’s <a class="reference internal" href="#mxnet.gluon.Block.name_scope" title="mxnet.gluon.Block.name_scope"><code class="xref py py-meth docutils literal">name_scope()</code></a> will have parent block’s prefix in their name. Please refer to <a class="reference external" href="/versions/1.2.1/tutorials/basic/naming.html">naming tutorial</a> for more info on prefix and naming.</li> <li>params (<a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict">ParameterDict</a> or None) – <a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict"><code class="xref py py-class docutils literal">ParameterDict</code></a> for sharing weights with the new <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a>. For example, if you want <code class="docutils literal">dense1</code> to share <code class="docutils literal">dense0</code>‘s weights, you can do: <div class="highlight-default"><div class="highlight"><pre>dense0 = nn.Dense(20) dense1 = nn.Dense(20, params=dense0.collect_params()) </pre></div> </div> </li> </ul> </td> </tr> </tbody> </table> <dl class="method"> <dt id="mxnet.gluon.Block.__call__"> <code class="descname">__call__</code>(*args)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.__call__">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.__call__" title="Permalink to this definition">¶</a></dt> <dd>Calls forward. Only accepts positional arguments. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.__setattr__"> <code class="descname">__setattr__</code>(name, value)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.__setattr__">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.__setattr__" title="Permalink to this definition">¶</a></dt> <dd>Registers parameters. </dd></dl> <dl class="attribute"> <dt id="mxnet.gluon.Block.__weakref__"> <code class="descname">__weakref__</code><a class="headerlink" href="#mxnet.gluon.Block.__weakref__" title="Permalink to this definition">¶</a></dt> <dd>list of weak references to the object (if defined) </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.cast"> <code class="descname">cast</code>(dtype)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.cast">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.cast" title="Permalink to this definition">¶</a></dt> <dd>Cast this Block to use another data type. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">dtype (str or numpy.dtype) – The new data type.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.collect_params"> <code class="descname">collect_params</code>(select=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.collect_params">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.collect_params" title="Permalink to this definition">¶</a></dt> <dd>Returns a <a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict"><code class="xref py py-class docutils literal">ParameterDict</code></a> containing this <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a> and all of its children’s Parameters(default), also can returns the select <a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict"><code class="xref py py-class docutils literal">ParameterDict</code></a> which match some given regular expressions. For example, collect the specified parameters in [‘conv1_weight’, ‘conv1_bias’, ‘fc_weight’, ‘fc_bias’]: <div class="highlight-default"><div class="highlight"><pre>model.collect_params('conv1_weight|conv1_bias|fc_weight|fc_bias') </pre></div> </div> or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done using regular expressions: <div class="highlight-default"><div class="highlight"><pre>model.collect_params('.*weight|.*bias') </pre></div> </div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">select (str) – regular expressions</td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"></td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body">The selected <a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict"><code class="xref py py-class docutils literal">ParameterDict</code></a></td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.forward"> <code class="descname">forward</code>(*args)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.forward">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.forward" title="Permalink to this definition">¶</a></dt> <dd>Overrides to implement forward computation using <code class="xref py py-class docutils literal">NDArray</code>. Only accepts positional arguments. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">*args (list of NDArray) – Input tensors.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.hybridize"> <code class="descname">hybridize</code>(active=True, **kwargs)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.hybridize">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.hybridize" title="Permalink to this definition">¶</a></dt> <dd>Activates or deactivates <a class="reference internal" href="#mxnet.gluon.HybridBlock" title="mxnet.gluon.HybridBlock"><code class="xref py py-class docutils literal">HybridBlock</code></a> s recursively. Has no effect on non-hybrid children. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>active (bool, default True) – Whether to turn hybrid on or off.</li> <li>**kwargs (string) – Additional flags for hybridized operator.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.initialize"> <code class="descname">initialize</code>(init=<mxnet.initializer.Uniform object>, ctx=None, verbose=False, force_reinit=False)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.initialize">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.initialize" title="Permalink to this definition">¶</a></dt> <dd>Initializes <a class="reference internal" href="#mxnet.gluon.Parameter" title="mxnet.gluon.Parameter"><code class="xref py py-class docutils literal">Parameter</code></a> s of this <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a> and its children. Equivalent to <code class="docutils literal">block.collect_params().initialize(...)</code> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>init (<a class="reference internal" href="../optimization/optimization.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer">Initializer</a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal">Parameter.init()</code> is <code class="docutils literal">None</code>. Otherwise, <code class="xref py py-meth docutils literal">Parameter.init()</code> takes precedence.</li> <li>ctx (Context or list of Context) – Keeps a copy of Parameters on one or many context(s).</li> <li>verbose (bool, default False) – Whether to verbosely print out details on initialization.</li> <li>force_reinit (bool, default False) – Whether to force re-initialization if parameter is already initialized.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.load_parameters"> <code class="descname">load_parameters</code>(filename, ctx=None, allow_missing=False, ignore_extra=False)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.load_parameters">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.load_parameters" title="Permalink to this definition">¶</a></dt> <dd>Load parameters from file previously saved by <cite>save_parameters</cite>. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>filename (str) – Path to parameter file.</li> <li>ctx (Context or list of Context, default cpu()) – Context(s) to initialize loaded parameters on.</li> <li>allow_missing (bool, default False) – Whether to silently skip loading parameters not represents in the file.</li> <li>ignore_extra (bool, default False) – Whether to silently ignore parameters from the file that are not present in this Block.</li> </ul> </td> </tr> </tbody> </table> References <a class="reference external" href="/versions/1.2.1/tutorials/gluon/save_load_params.html">Saving and Loading Gluon Models</a> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.load_params"> <code class="descname">load_params</code>(filename, ctx=None, allow_missing=False, ignore_extra=False)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.load_params">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.load_params" title="Permalink to this definition">¶</a></dt> <dd>[Deprecated] Please use load_parameters. Load parameters from file. <dl class="docutils"> <dt>filename : str</dt> <dd>Path to parameter file.</dd> <dt>ctx : Context or list of Context, default cpu()</dt> <dd>Context(s) to initialize loaded parameters on.</dd> <dt>allow_missing : bool, default False</dt> <dd>Whether to silently skip loading parameters not represents in the file.</dd> <dt>ignore_extra : bool, default False</dt> <dd>Whether to silently ignore parameters from the file that are not present in this Block.</dd> </dl> </dd></dl> <dl class="attribute"> <dt id="mxnet.gluon.Block.name"> <code class="descname">name</code><a class="headerlink" href="#mxnet.gluon.Block.name" title="Permalink to this definition">¶</a></dt> <dd>Name of this <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a>, without ‘_’ in the end. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.name_scope"> <code class="descname">name_scope</code>()<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.name_scope">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.name_scope" title="Permalink to this definition">¶</a></dt> <dd>Returns a name space object managing a child <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a> and parameter names. Should be used within a <code class="docutils literal">with</code> statement: <div class="highlight-default"><div class="highlight"><pre>with self.name_scope(): self.dense = nn.Dense(20) </pre></div> </div> Please refer to <a class="reference external" href="/versions/1.2.1/tutorials/basic/naming.html">naming tutorial</a> for more info on prefix and naming. </dd></dl> <dl class="attribute"> <dt id="mxnet.gluon.Block.params"> <code class="descname">params</code><a class="headerlink" href="#mxnet.gluon.Block.params" title="Permalink to this definition">¶</a></dt> <dd>Returns this <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a>‘s parameter dictionary (does not include its children’s parameters). </dd></dl> <dl class="attribute"> <dt id="mxnet.gluon.Block.prefix"> <code class="descname">prefix</code><a class="headerlink" href="#mxnet.gluon.Block.prefix" title="Permalink to this definition">¶</a></dt> <dd>Prefix of this <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a>. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.register_child"> <code class="descname">register_child</code>(block, name=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.register_child">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.register_child" title="Permalink to this definition">¶</a></dt> <dd>Registers block as a child of self. <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a> s assigned to self as attributes will be registered automatically. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.save_parameters"> <code class="descname">save_parameters</code>(filename)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.save_parameters">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.save_parameters" title="Permalink to this definition">¶</a></dt> <dd>Save parameters to file. Saved parameters can only be loaded with <cite>load_parameters</cite>. Note that this method only saves parameters, not model structure. If you want to save model structures, please use <a class="reference internal" href="#mxnet.gluon.HybridBlock.export" title="mxnet.gluon.HybridBlock.export"><code class="xref py py-meth docutils literal">HybridBlock.export()</code></a>. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">filename (str) – Path to file.</td> </tr> </tbody> </table> References <a class="reference external" href="/versions/1.2.1/tutorials/gluon/save_load_params.html">Saving and Loading Gluon Models</a> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Block.save_params"> <code class="descname">save_params</code>(filename)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#Block.save_params">[source]</a><a class="headerlink" href="#mxnet.gluon.Block.save_params" title="Permalink to this definition">¶</a></dt> <dd>[Deprecated] Please use save_parameters. Note that if you want to load from SymbolBlock later, please use export instead. Save parameters to file. <dl class="docutils"> <dt>filename : str</dt> <dd>Path to file.</dd> </dl> </dd></dl> </dd></dl> <dl class="class"> <dt id="mxnet.gluon.Constant"> class <code class="descclassname">mxnet.gluon.</code><code class="descname">Constant</code>(name, value)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Constant">[source]</a><a class="headerlink" href="#mxnet.gluon.Constant" title="Permalink to this definition">¶</a></dt> <dd>A constant parameter for holding immutable tensors. <cite>Constant`s are ignored by `autograd</cite> and <cite>Trainer</cite>, thus their values will not change during training. But you can still update their values manually with the <cite>set_data</cite> method. <a href="#id3">`</a>Constant`s can be created with either: <div class="highlight-default"><div class="highlight"><pre>const = mx.gluon.Constant('const', [[1,2],[3,4]]) </pre></div> </div> or: <div class="highlight-default"><div class="highlight"><pre>class Block(gluon.Block): def __init__(self, **kwargs): super(Block, self).__init__(**kwargs) self.const = self.params.get_constant('const', [[1,2],[3,4]]) </pre></div> </div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>name (str) – Name of the parameter.</li> <li>value (array-like) – Initial value for the constant.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="exception"> <dt id="mxnet.gluon.DeferredInitializationError"> exception <code class="descclassname">mxnet.gluon.</code><code class="descname">DeferredInitializationError</code><a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#DeferredInitializationError">[source]</a><a class="headerlink" href="#mxnet.gluon.DeferredInitializationError" title="Permalink to this definition">¶</a></dt> <dd>Error for unfinished deferred initialization. </dd></dl> <dl class="class"> <dt id="mxnet.gluon.HybridBlock"> class <code class="descclassname">mxnet.gluon.</code><code class="descname">HybridBlock</code>(prefix=None, params=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#HybridBlock">[source]</a><a class="headerlink" href="#mxnet.gluon.HybridBlock" title="Permalink to this definition">¶</a></dt> <dd><cite>HybridBlock</cite> supports forwarding with both Symbol and NDArray. <cite>HybridBlock</cite> is similar to <cite>Block</cite>, with a few differences: <div class="highlight-default"><div class="highlight"><pre>import mxnet as mx from mxnet.gluon import HybridBlock, nn class Model(HybridBlock): def __init__(self, **kwargs): super(Model, self).__init__(**kwargs) # use name_scope to give child Blocks appropriate names. with self.name_scope(): self.dense0 = nn.Dense(20) self.dense1 = nn.Dense(20) def hybrid_forward(self, F, x): x = F.relu(self.dense0(x)) return F.relu(self.dense1(x)) model = Model() model.initialize(ctx=mx.cpu(0)) model.hybridize() model(mx.nd.zeros((10, 10), ctx=mx.cpu(0))) </pre></div> </div> Forward computation in <a class="reference internal" href="#mxnet.gluon.HybridBlock" title="mxnet.gluon.HybridBlock"><code class="xref py py-class docutils literal">HybridBlock</code></a> must be static to work with <code class="xref py py-class docutils literal">Symbol</code> s, i.e. you cannot call <code class="xref py py-meth docutils literal">NDArray.asnumpy()</code>, <code class="xref py py-attr docutils literal">NDArray.shape</code>, <code class="xref py py-attr docutils literal">NDArray.dtype</code>, <cite>NDArray</cite> indexing (<cite>x[i]</cite>) etc on tensors. Also, you cannot use branching or loop logic that bases on non-constant expressions like random numbers or intermediate results, since they change the graph structure for each iteration. Before activating with <code class="xref py py-meth docutils literal">hybridize()</code>, <a class="reference internal" href="#mxnet.gluon.HybridBlock" title="mxnet.gluon.HybridBlock"><code class="xref py py-class docutils literal">HybridBlock</code></a> works just like normal <a class="reference internal" href="#mxnet.gluon.Block" title="mxnet.gluon.Block"><code class="xref py py-class docutils literal">Block</code></a>. After activation, <a class="reference internal" href="#mxnet.gluon.HybridBlock" title="mxnet.gluon.HybridBlock"><code class="xref py py-class docutils literal">HybridBlock</code></a> will create a symbolic graph representing the forward computation and cache it. On subsequent forwards, the cached graph will be used instead of <a class="reference internal" href="#mxnet.gluon.HybridBlock.hybrid_forward" title="mxnet.gluon.HybridBlock.hybrid_forward"><code class="xref py py-meth docutils literal">hybrid_forward()</code></a>. Please see references for detailed tutorial. References <a class="reference external" href="/versions/1.2.1/tutorials/gluon/hybrid.html">Hybrid - Faster training and easy deployment</a> <dl class="method"> <dt id="mxnet.gluon.HybridBlock.__setattr__"> <code class="descname">__setattr__</code>(name, value)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#HybridBlock.__setattr__">[source]</a><a class="headerlink" href="#mxnet.gluon.HybridBlock.__setattr__" title="Permalink to this definition">¶</a></dt> <dd>Registers parameters. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.HybridBlock.export"> <code class="descname">export</code>(path, epoch=0)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#HybridBlock.export">[source]</a><a class="headerlink" href="#mxnet.gluon.HybridBlock.export" title="Permalink to this definition">¶</a></dt> <dd>Export HybridBlock to json format that can be loaded by <cite>SymbolBlock.imports</cite>, <cite>mxnet.mod.Module</cite> or the C++ interface. <div class="admonition note"> Note When there are only one input, it will have name <cite>data</cite>. When there Are more than one inputs, they will be named as <cite>data0</cite>, <cite>data1</cite>, etc. </div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>path (str) – Path to save model. Two files <cite>path-symbol.json</cite> and <cite>path-xxxx.params</cite> will be created, where xxxx is the 4 digits epoch number.</li> <li>epoch (int) – Epoch number of saved model.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.HybridBlock.forward"> <code class="descname">forward</code>(x, *args)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#HybridBlock.forward">[source]</a><a class="headerlink" href="#mxnet.gluon.HybridBlock.forward" title="Permalink to this definition">¶</a></dt> <dd>Defines the forward computation. Arguments can be either <code class="xref py py-class docutils literal">NDArray</code> or <code class="xref py py-class docutils literal">Symbol</code>. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.HybridBlock.hybrid_forward"> <code class="descname">hybrid_forward</code>(F, x, *args, **kwargs)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#HybridBlock.hybrid_forward">[source]</a><a class="headerlink" href="#mxnet.gluon.HybridBlock.hybrid_forward" title="Permalink to this definition">¶</a></dt> <dd>Overrides to construct symbolic graph for this <cite>Block</cite>. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>x (<a class="reference internal" href="../symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol">Symbol</a> or <a class="reference internal" href="../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a>) – The first input tensor.</li> <li>*args (list of Symbol or list of NDArray) – Additional input tensors.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.HybridBlock.infer_shape"> <code class="descname">infer_shape</code>(*args)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#HybridBlock.infer_shape">[source]</a><a class="headerlink" href="#mxnet.gluon.HybridBlock.infer_shape" title="Permalink to this definition">¶</a></dt> <dd>Infers shape of Parameters from inputs. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.HybridBlock.infer_type"> <code class="descname">infer_type</code>(*args)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#HybridBlock.infer_type">[source]</a><a class="headerlink" href="#mxnet.gluon.HybridBlock.infer_type" title="Permalink to this definition">¶</a></dt> <dd>Infers data type of Parameters from inputs. </dd></dl> </dd></dl> <dl class="class"> <dt id="mxnet.gluon.Parameter"> class <code class="descclassname">mxnet.gluon.</code><code class="descname">Parameter</code>(name, grad_req='write', shape=None, dtype=<type 'numpy.float32'>, lr_mult=1.0, wd_mult=1.0, init=None, allow_deferred_init=False, differentiable=True)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter" title="Permalink to this definition">¶</a></dt> <dd>A Container holding parameters (weights) of Blocks. <a class="reference internal" href="#mxnet.gluon.Parameter" title="mxnet.gluon.Parameter"><code class="xref py py-class docutils literal">Parameter</code></a> holds a copy of the parameter on each <code class="xref py py-class docutils literal">Context</code> after it is initialized with <code class="docutils literal">Parameter.initialize(...)</code>. If <a class="reference internal" href="#mxnet.gluon.Parameter.grad_req" title="mxnet.gluon.Parameter.grad_req"><code class="xref py py-attr docutils literal">grad_req</code></a> is not <code class="docutils literal">'null'</code>, it will also hold a gradient array on each <code class="xref py py-class docutils literal">Context</code>: <div class="highlight-default"><div class="highlight"><pre>ctx = mx.gpu(0) x = mx.nd.zeros((16, 100), ctx=ctx) w = mx.gluon.Parameter('fc_weight', shape=(64, 100), init=mx.init.Xavier()) b = mx.gluon.Parameter('fc_bias', shape=(64,), init=mx.init.Zero()) w.initialize(ctx=ctx) b.initialize(ctx=ctx) out = mx.nd.FullyConnected(x, w.data(ctx), b.data(ctx), num_hidden=64) </pre></div> </div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>name (str) – Name of this parameter.</li> <li>grad_req ({'write', 'add', 'null'}, default 'write') – Specifies how to update gradient to grad arrays. <ul> <li><code class="docutils literal">'write'</code> means everytime gradient is written to grad <code class="xref py py-class docutils literal">NDArray</code>.</li> <li><code class="docutils literal">'add'</code> means everytime gradient is added to the grad <code class="xref py py-class docutils literal">NDArray</code>. You need to manually call <code class="docutils literal">zero_grad()</code> to clear the gradient buffer before each iteration when using this option.</li> <li>‘null’ means gradient is not requested for this parameter. gradient arrays will not be allocated.</li> </ul> </li> <li>shape (tuple of int, default None) – Shape of this parameter. By default shape is not specified. Parameter with unknown shape can be used for <code class="xref py py-class docutils literal">Symbol</code> API, but <code class="docutils literal">init</code> will throw an error when using <code class="xref py py-class docutils literal">NDArray</code> API.</li> <li>dtype (numpy.dtype or str, default 'float32') – Data type of this parameter. For example, <code class="docutils literal">numpy.float32</code> or <code class="docutils literal">'float32'</code>.</li> <li>lr_mult (float, default 1.0) – Learning rate multiplier. Learning rate will be multiplied by lr_mult when updating this parameter with optimizer.</li> <li>wd_mult (float, default 1.0) – Weight decay multiplier (L2 regularizer coefficient). Works similar to lr_mult.</li> <li>init (<a class="reference internal" href="../optimization/optimization.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer">Initializer</a>, default None) – Initializer of this parameter. Will use the global initializer by default.</li> </ul> </td> </tr> </tbody> </table> <dl class="attribute"> <dt id="mxnet.gluon.Parameter.grad_req"> <code class="descname">grad_req</code><a class="headerlink" href="#mxnet.gluon.Parameter.grad_req" title="Permalink to this definition">¶</a></dt> <dd>{‘write’, ‘add’, ‘null’} – This can be set before or after initialization. Setting <code class="docutils literal">grad_req</code> to <code class="docutils literal">'null'</code> with <code class="docutils literal">x.grad_req = 'null'</code> saves memory and computation when you don’t need gradient w.r.t x. </dd></dl> <dl class="attribute"> <dt id="mxnet.gluon.Parameter.lr_mult"> <code class="descname">lr_mult</code><a class="headerlink" href="#mxnet.gluon.Parameter.lr_mult" title="Permalink to this definition">¶</a></dt> <dd>float – Local learning rate multiplier for this Parameter. The actual learning rate is calculated with <code class="docutils literal">learning_rate * lr_mult</code>. You can set it with <code class="docutils literal">param.lr_mult = 2.0</code> </dd></dl> <dl class="attribute"> <dt id="mxnet.gluon.Parameter.wd_mult"> <code class="descname">wd_mult</code><a class="headerlink" href="#mxnet.gluon.Parameter.wd_mult" title="Permalink to this definition">¶</a></dt> <dd>float – Local weight decay multiplier for this Parameter. </dd></dl> <dl class="attribute"> <dt id="mxnet.gluon.Parameter.__weakref__"> <code class="descname">__weakref__</code><a class="headerlink" href="#mxnet.gluon.Parameter.__weakref__" title="Permalink to this definition">¶</a></dt> <dd>list of weak references to the object (if defined) </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.cast"> <code class="descname">cast</code>(dtype)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.cast">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.cast" title="Permalink to this definition">¶</a></dt> <dd>Cast data and gradient of this Parameter to a new data type. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">dtype (str or numpy.dtype) – The new data type.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.data"> <code class="descname">data</code>(ctx=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.data">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.data" title="Permalink to this definition">¶</a></dt> <dd>Returns a copy of this parameter on one context. Must have been initialized on this context before. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">ctx (Context) – Desired context.</td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"></td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body">NDArray on ctx</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.grad"> <code class="descname">grad</code>(ctx=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.grad">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.grad" title="Permalink to this definition">¶</a></dt> <dd>Returns a gradient buffer for this parameter on one context. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">ctx (Context) – Desired context.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.initialize"> <code class="descname">initialize</code>(init=None, ctx=None, default_init=<mxnet.initializer.Uniform object>, force_reinit=False)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.initialize">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.initialize" title="Permalink to this definition">¶</a></dt> <dd>Initializes parameter and gradient arrays. Only used for <code class="xref py py-class docutils literal">NDArray</code> API. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>init (<a class="reference internal" href="../optimization/optimization.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer">Initializer</a>) – The initializer to use. Overrides <code class="xref py py-meth docutils literal">Parameter.init()</code> and default_init.</li> <li>ctx (Context or list of Context, defaults to <code class="xref py py-meth docutils literal">context.current_context()</code>.) – Initialize Parameter on given context. If ctx is a list of Context, a copy will be made for each context. <div class="admonition note"> Note Copies are independent arrays. User is responsible for keeping their values consistent when updating. Normally <code class="xref py py-class docutils literal">gluon.Trainer</code> does this for you. </div> </li> <li>default_init (<a class="reference internal" href="../optimization/optimization.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer">Initializer</a>) – Default initializer is used when both <code class="xref py py-func docutils literal">init()</code> and <code class="xref py py-meth docutils literal">Parameter.init()</code> are <code class="docutils literal">None</code>.</li> <li>force_reinit (bool, default False) – Whether to force re-initialization if parameter is already initialized.</li> </ul> </td> </tr> </tbody> </table> Examples <div class="highlight-default"><div class="highlight"><pre>>>> weight = mx.gluon.Parameter('weight', shape=(2, 2)) >>> weight.initialize(ctx=mx.cpu(0)) >>> weight.data() [[-0.01068833 0.01729892] [ 0.02042518 -0.01618656]] <NDArray 2x2 @cpu(0)> >>> weight.grad() [[ 0. 0.] [ 0. 0.]] <NDArray 2x2 @cpu(0)> >>> weight.initialize(ctx=[mx.gpu(0), mx.gpu(1)]) >>> weight.data(mx.gpu(0)) [[-0.00873779 -0.02834515] [ 0.05484822 -0.06206018]] <NDArray 2x2 @gpu(0)> >>> weight.data(mx.gpu(1)) [[-0.00873779 -0.02834515] [ 0.05484822 -0.06206018]] <NDArray 2x2 @gpu(1)> </pre></div> </div> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.list_ctx"> <code class="descname">list_ctx</code>()<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.list_ctx">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.list_ctx" title="Permalink to this definition">¶</a></dt> <dd>Returns a list of contexts this parameter is initialized on. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.list_data"> <code class="descname">list_data</code>()<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.list_data">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.list_data" title="Permalink to this definition">¶</a></dt> <dd>Returns copies of this parameter on all contexts, in the same order as creation. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.list_grad"> <code class="descname">list_grad</code>()<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.list_grad">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.list_grad" title="Permalink to this definition">¶</a></dt> <dd>Returns gradient buffers on all contexts, in the same order as <code class="xref py py-meth docutils literal">values()</code>. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.reset_ctx"> <code class="descname">reset_ctx</code>(ctx)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.reset_ctx">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.reset_ctx" title="Permalink to this definition">¶</a></dt> <dd>Re-assign Parameter to other contexts. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">ctx (Context or list of Context, default <code class="docutils literal">context.current_context()</code>.) – Assign Parameter to given context. If ctx is a list of Context, a copy will be made for each context.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.set_data"> <code class="descname">set_data</code>(data)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.set_data">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.set_data" title="Permalink to this definition">¶</a></dt> <dd>Sets this parameter’s value on all contexts. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.var"> <code class="descname">var</code>()<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.var">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.var" title="Permalink to this definition">¶</a></dt> <dd>Returns a symbol representing this parameter. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Parameter.zero_grad"> <code class="descname">zero_grad</code>()<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#Parameter.zero_grad">[source]</a><a class="headerlink" href="#mxnet.gluon.Parameter.zero_grad" title="Permalink to this definition">¶</a></dt> <dd>Sets gradient buffer on all contexts to 0. No action is taken if parameter is uninitialized or doesn’t require gradient. </dd></dl> </dd></dl> <dl class="class"> <dt id="mxnet.gluon.ParameterDict"> class <code class="descclassname">mxnet.gluon.</code><code class="descname">ParameterDict</code>(prefix='', shared=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict" title="Permalink to this definition">¶</a></dt> <dd>A dictionary managing a set of parameters. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>prefix (str, default <code class="docutils literal">''</code>) – The prefix to be prepended to all Parameters’ names created by this dict.</li> <li>shared (<a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict">ParameterDict</a> or None) – If not <code class="docutils literal">None</code>, when this dict’s <a class="reference internal" href="#mxnet.gluon.ParameterDict.get" title="mxnet.gluon.ParameterDict.get"><code class="xref py py-meth docutils literal">get()</code></a> method creates a new parameter, will first try to retrieve it from “shared” dict. Usually used for sharing parameters with another Block.</li> </ul> </td> </tr> </tbody> </table> <dl class="attribute"> <dt id="mxnet.gluon.ParameterDict.__weakref__"> <code class="descname">__weakref__</code><a class="headerlink" href="#mxnet.gluon.ParameterDict.__weakref__" title="Permalink to this definition">¶</a></dt> <dd>list of weak references to the object (if defined) </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.get"> <code class="descname">get</code>(name, **kwargs)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.get">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.get" title="Permalink to this definition">¶</a></dt> <dd>Retrieves a <a class="reference internal" href="#mxnet.gluon.Parameter" title="mxnet.gluon.Parameter"><code class="xref py py-class docutils literal">Parameter</code></a> with name <code class="docutils literal">self.prefix+name</code>. If not found, <a class="reference internal" href="#mxnet.gluon.ParameterDict.get" title="mxnet.gluon.ParameterDict.get"><code class="xref py py-func docutils literal">get()</code></a> will first try to retrieve it from “shared” dict. If still not found, <a class="reference internal" href="#mxnet.gluon.ParameterDict.get" title="mxnet.gluon.ParameterDict.get"><code class="xref py py-func docutils literal">get()</code></a> will create a new <a class="reference internal" href="#mxnet.gluon.Parameter" title="mxnet.gluon.Parameter"><code class="xref py py-class docutils literal">Parameter</code></a> with key-word arguments and insert it to self. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <li>name (str) – Name of the desired Parameter. It will be prepended with this dictionary’s prefix.</li> <li>**kwargs (dict) – The rest of key-word arguments for the created <a class="reference internal" href="#mxnet.gluon.Parameter" title="mxnet.gluon.Parameter"><code class="xref py py-class docutils literal">Parameter</code></a>.</li> </ul> </td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">The created or retrieved <a class="reference internal" href="#mxnet.gluon.Parameter" title="mxnet.gluon.Parameter"><code class="xref py py-class docutils literal">Parameter</code></a>. </td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><a class="reference internal" href="#mxnet.gluon.Parameter" title="mxnet.gluon.Parameter">Parameter</a> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.get_constant"> <code class="descname">get_constant</code>(name, value=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.get_constant">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.get_constant" title="Permalink to this definition">¶</a></dt> <dd>Retrieves a <a class="reference internal" href="#mxnet.gluon.Constant" title="mxnet.gluon.Constant"><code class="xref py py-class docutils literal">Constant</code></a> with name <code class="docutils literal">self.prefix+name</code>. If not found, <a class="reference internal" href="#mxnet.gluon.ParameterDict.get" title="mxnet.gluon.ParameterDict.get"><code class="xref py py-func docutils literal">get()</code></a> will first try to retrieve it from “shared” dict. If still not found, <a class="reference internal" href="#mxnet.gluon.ParameterDict.get" title="mxnet.gluon.ParameterDict.get"><code class="xref py py-func docutils literal">get()</code></a> will create a new <a class="reference internal" href="#mxnet.gluon.Constant" title="mxnet.gluon.Constant"><code class="xref py py-class docutils literal">Constant</code></a> with key-word arguments and insert it to self. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <li>name (str) – Name of the desired Constant. It will be prepended with this dictionary’s prefix.</li> <li>value (array-like) – Initial value of constant.</li> </ul> </td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">The created or retrieved <a class="reference internal" href="#mxnet.gluon.Constant" title="mxnet.gluon.Constant"><code class="xref py py-class docutils literal">Constant</code></a>. </td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><a class="reference internal" href="#mxnet.gluon.Constant" title="mxnet.gluon.Constant">Constant</a> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.initialize"> <code class="descname">initialize</code>(init=<mxnet.initializer.Uniform object>, ctx=None, verbose=False, force_reinit=False)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.initialize">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.initialize" title="Permalink to this definition">¶</a></dt> <dd>Initializes all Parameters managed by this dictionary to be used for <code class="xref py py-class docutils literal">NDArray</code> API. It has no effect when using <code class="xref py py-class docutils literal">Symbol</code> API. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>init (<a class="reference internal" href="../optimization/optimization.html#mxnet.initializer.Initializer" title="mxnet.initializer.Initializer">Initializer</a>) – Global default Initializer to be used when <code class="xref py py-meth docutils literal">Parameter.init()</code> is <code class="docutils literal">None</code>. Otherwise, <code class="xref py py-meth docutils literal">Parameter.init()</code> takes precedence.</li> <li>ctx (Context or list of Context) – Keeps a copy of Parameters on one or many context(s).</li> <li>verbose (bool, default False) – Whether to verbosely print out details on initialization.</li> <li>force_reinit (bool, default False) – Whether to force re-initialization if parameter is already initialized.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.load"> <code class="descname">load</code>(filename, ctx=None, allow_missing=False, ignore_extra=False, restore_prefix='')<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.load">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.load" title="Permalink to this definition">¶</a></dt> <dd>Load parameters from file. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>filename (str) – Path to parameter file.</li> <li>ctx (Context or list of Context) – Context(s) initialize loaded parameters on.</li> <li>allow_missing (bool, default False) – Whether to silently skip loading parameters not represents in the file.</li> <li>ignore_extra (bool, default False) – Whether to silently ignore parameters from the file that are not present in this ParameterDict.</li> <li>restore_prefix (str, default '') – prepend prefix to names of stored parameters before loading.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="attribute"> <dt id="mxnet.gluon.ParameterDict.prefix"> <code class="descname">prefix</code><a class="headerlink" href="#mxnet.gluon.ParameterDict.prefix" title="Permalink to this definition">¶</a></dt> <dd>Prefix of this dict. It will be prepended to <code class="xref py py-class docutils literal">Parameter`s' name created with :py:func:`get</code>. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.reset_ctx"> <code class="descname">reset_ctx</code>(ctx)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.reset_ctx">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.reset_ctx" title="Permalink to this definition">¶</a></dt> <dd>Re-assign all Parameters to other contexts. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">ctx (Context or list of Context, default <code class="xref py py-meth docutils literal">context.current_context()</code>.) – Assign Parameter to given context. If ctx is a list of Context, a copy will be made for each context.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.save"> <code class="descname">save</code>(filename, strip_prefix='')<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.save">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.save" title="Permalink to this definition">¶</a></dt> <dd>Save parameters to file. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>filename (str) – Path to parameter file.</li> <li>strip_prefix (str, default '') – Strip prefix from parameter names before saving.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.setattr"> <code class="descname">setattr</code>(name, value)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.setattr">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.setattr" title="Permalink to this definition">¶</a></dt> <dd>Set an attribute to a new value for all Parameters. For example, set grad_req to null if you don’t need gradient w.r.t a model’s Parameters: <div class="highlight-default"><div class="highlight"><pre>model.collect_params().setattr('grad_req', 'null') </pre></div> </div> or change the learning rate multiplier: <div class="highlight-default"><div class="highlight"><pre>model.collect_params().setattr('lr_mult', 0.5) </pre></div> </div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>name (str) – Name of the attribute.</li> <li>value (valid type for attribute name) – The new value for the attribute.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.update"> <code class="descname">update</code>(other)<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.update">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.update" title="Permalink to this definition">¶</a></dt> <dd>Copies all Parameters in <code class="docutils literal">other</code> to self. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.ParameterDict.zero_grad"> <code class="descname">zero_grad</code>()<a class="reference internal" href="../../../_modules/mxnet/gluon/parameter.html#ParameterDict.zero_grad">[source]</a><a class="headerlink" href="#mxnet.gluon.ParameterDict.zero_grad" title="Permalink to this definition">¶</a></dt> <dd>Sets all Parameters’ gradient buffer to 0. </dd></dl> </dd></dl> <dl class="class"> <dt id="mxnet.gluon.SymbolBlock"> class <code class="descclassname">mxnet.gluon.</code><code class="descname">SymbolBlock</code>(outputs, inputs, params=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#SymbolBlock">[source]</a><a class="headerlink" href="#mxnet.gluon.SymbolBlock" title="Permalink to this definition">¶</a></dt> <dd>Construct block from symbol. This is useful for using pre-trained models as feature extractors. For example, you may want to extract the output from fc2 layer in AlexNet. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>outputs (<a class="reference internal" href="../symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol">Symbol</a> or list of Symbol) – The desired output for SymbolBlock.</li> <li>inputs (<a class="reference internal" href="../symbol/symbol.html#mxnet.symbol.Symbol" title="mxnet.symbol.Symbol">Symbol</a> or list of Symbol) – The Variables in output’s argument that should be used as inputs.</li> <li>params (<a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict">ParameterDict</a>) – Parameter dictionary for arguments and auxililary states of outputs that are not inputs.</li> </ul> </td> </tr> </tbody> </table> Examples <div class="highlight-default"><div class="highlight"><pre>>>> # To extract the feature from fc1 and fc2 layers of AlexNet: >>> alexnet = gluon.model_zoo.vision.alexnet(pretrained=True, ctx=mx.cpu(), prefix='model_') >>> inputs = mx.sym.var('data') >>> out = alexnet(inputs) >>> internals = out.get_internals() >>> print(internals.list_outputs()) ['data', ..., 'model_dense0_relu_fwd_output', ..., 'model_dense1_relu_fwd_output', ...] >>> outputs = [internals['model_dense0_relu_fwd_output'], internals['model_dense1_relu_fwd_output']] >>> # Create SymbolBlock that shares parameters with alexnet >>> feat_model = gluon.SymbolBlock(outputs, inputs, params=alexnet.collect_params()) >>> x = mx.nd.random.normal(shape=(16, 3, 224, 224)) >>> print(feat_model(x)) </pre></div> </div> <dl class="staticmethod"> <dt id="mxnet.gluon.SymbolBlock.imports"> static <code class="descname">imports</code>(symbol_file, input_names, param_file=None, ctx=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/block.html#SymbolBlock.imports">[source]</a><a class="headerlink" href="#mxnet.gluon.SymbolBlock.imports" title="Permalink to this definition">¶</a></dt> <dd>Import model previously saved by <cite>HybridBlock.export</cite> or <cite>Module.save_checkpoint</cite> as a SymbolBlock for use in Gluon. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <li>symbol_file (str) – Path to symbol file.</li> <li>input_names (list of str) – List of input variable names</li> <li>param_file (str, optional) – Path to parameter file.</li> <li>ctx (Context, default None) – The context to initialize SymbolBlock on.</li> </ul> </td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">SymbolBlock loaded from symbol and parameter files. </td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><a class="reference internal" href="#mxnet.gluon.SymbolBlock" title="mxnet.gluon.SymbolBlock">SymbolBlock</a> </td> </tr> </tbody> </table> Examples <div class="highlight-default"><div class="highlight"><pre>>>> net1 = gluon.model_zoo.vision.resnet18_v1( ... prefix='resnet', pretrained=True) >>> net1.hybridize() >>> x = mx.nd.random.normal(shape=(1, 3, 32, 32)) >>> out1 = net1(x) >>> net1.export('net1', epoch=1) >>> >>> net2 = gluon.SymbolBlock.imports( ... 'net1-symbol.json', ['data'], 'net1-0001.params') >>> out2 = net2(x) </pre></div> </div> </dd></dl> </dd></dl> <dl class="class"> <dt id="mxnet.gluon.Trainer"> class <code class="descclassname">mxnet.gluon.</code><code class="descname">Trainer</code>(params, optimizer, optimizer_params=None, kvstore='device', compression_params=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/trainer.html#Trainer">[source]</a><a class="headerlink" href="#mxnet.gluon.Trainer" title="Permalink to this definition">¶</a></dt> <dd>Applies an <cite>Optimizer</cite> on a set of Parameters. Trainer should be used together with <cite>autograd</cite>. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>params (<a class="reference internal" href="#mxnet.gluon.ParameterDict" title="mxnet.gluon.ParameterDict">ParameterDict</a>) – The set of parameters to optimize.</li> <li>optimizer (str or <a class="reference internal" href="../optimization/optimization.html#mxnet.optimizer.Optimizer" title="mxnet.optimizer.Optimizer">Optimizer</a>) – The optimizer to use. See <a class="reference external" href="/versions/1.2.1/api/python/optimization/optimization.html#the-mxnet-optimizer-package">help</a> on Optimizer for a list of available optimizers.</li> <li>optimizer_params (dict) – Key-word arguments to be passed to optimizer constructor. For example, <cite>{‘learning_rate’: 0.1}</cite>. All optimizers accept learning_rate, wd (weight decay), clip_gradient, and lr_scheduler. See each optimizer’s constructor for a list of additional supported arguments.</li> <li>kvstore (str or <a class="reference internal" href="../kvstore/kvstore.html#mxnet.kvstore.KVStore" title="mxnet.kvstore.KVStore">KVStore</a>) – kvstore type for multi-gpu and distributed training. See help on <a class="reference internal" href="../kvstore/kvstore.html#mxnet.kvstore.create" title="mxnet.kvstore.create"><code class="xref any py py-func docutils literal">mxnet.kvstore.create</code></a> for more information.</li> <li>compression_params (dict) – Specifies type of gradient compression and additional arguments depending on the type of compression being used. For example, 2bit compression requires a threshold. Arguments would then be {‘type’:‘2bit’, ‘threshold’:0.5} See mxnet.KVStore.set_gradient_compression method for more details on gradient compression.</li> <li>Properties – </li> <li>---------- – </li> <li>learning_rate (float) – The current learning rate of the optimizer. Given an Optimizer object optimizer, its learning rate can be accessed as optimizer.learning_rate.</li> </ul> </td> </tr> </tbody> </table> <dl class="attribute"> <dt id="mxnet.gluon.Trainer.__weakref__"> <code class="descname">__weakref__</code><a class="headerlink" href="#mxnet.gluon.Trainer.__weakref__" title="Permalink to this definition">¶</a></dt> <dd>list of weak references to the object (if defined) </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Trainer.load_states"> <code class="descname">load_states</code>(fname)<a class="reference internal" href="../../../_modules/mxnet/gluon/trainer.html#Trainer.load_states">[source]</a><a class="headerlink" href="#mxnet.gluon.Trainer.load_states" title="Permalink to this definition">¶</a></dt> <dd>Loads trainer states (e.g. optimizer, momentum) from a file. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">fname (str) – Path to input states file.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Trainer.save_states"> <code class="descname">save_states</code>(fname)<a class="reference internal" href="../../../_modules/mxnet/gluon/trainer.html#Trainer.save_states">[source]</a><a class="headerlink" href="#mxnet.gluon.Trainer.save_states" title="Permalink to this definition">¶</a></dt> <dd>Saves trainer states (e.g. optimizer, momentum) to a file. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">fname (str) – Path to output states file.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Trainer.set_learning_rate"> <code class="descname">set_learning_rate</code>(lr)<a class="reference internal" href="../../../_modules/mxnet/gluon/trainer.html#Trainer.set_learning_rate">[source]</a><a class="headerlink" href="#mxnet.gluon.Trainer.set_learning_rate" title="Permalink to this definition">¶</a></dt> <dd>Sets a new learning rate of the optimizer. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body">lr (float) – The new learning rate of the optimizer.</td> </tr> </tbody> </table> </dd></dl> <dl class="method"> <dt id="mxnet.gluon.Trainer.step"> <code class="descname">step</code>(batch_size, ignore_stale_grad=False)<a class="reference internal" href="../../../_modules/mxnet/gluon/trainer.html#Trainer.step">[source]</a><a class="headerlink" href="#mxnet.gluon.Trainer.step" title="Permalink to this definition">¶</a></dt> <dd>Makes one step of parameter update. Should be called after <cite>autograd.compute_gradient</cite> and outside of <cite>record()</cite> scope. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>batch_size (int) – Batch size of data processed. Gradient will be normalized by <cite>1/batch_size</cite>. Set this to 1 if you normalized loss manually with <cite>loss = mean(loss)</cite>.</li> <li>ignore_stale_grad (bool, optional, default=False) – If true, ignores Parameters with stale gradient (gradient that has not been updated by <cite>backward</cite> after last step) and skip update.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> </dd></dl> <dl class="class"> <dt id="mxnet.gluon.nn.Sequential"> class <code class="descclassname">mxnet.gluon.nn.</code><code class="descname">Sequential</code>(prefix=None, params=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/nn/basic_layers.html#Sequential">[source]</a><a class="headerlink" href="#mxnet.gluon.nn.Sequential" title="Permalink to this definition">¶</a></dt> <dd>Stacks Blocks sequentially. Example: <div class="highlight-default"><div class="highlight"><pre>net = nn.Sequential() # use net's name_scope to give child Blocks appropriate names. with net.name_scope(): net.add(nn.Dense(10, activation='relu')) net.add(nn.Dense(20)) </pre></div> </div> <dl class="method"> <dt id="mxnet.gluon.nn.Sequential.add"> <code class="descname">add</code>(*blocks)<a class="reference internal" href="../../../_modules/mxnet/gluon/nn/basic_layers.html#Sequential.add">[source]</a><a class="headerlink" href="#mxnet.gluon.nn.Sequential.add" title="Permalink to this definition">¶</a></dt> <dd>Adds block on top of the stack. </dd></dl> <dl class="method"> <dt id="mxnet.gluon.nn.Sequential.hybridize"> <code class="descname">hybridize</code>(active=True, **kwargs)<a class="reference internal" href="../../../_modules/mxnet/gluon/nn/basic_layers.html#Sequential.hybridize">[source]</a><a class="headerlink" href="#mxnet.gluon.nn.Sequential.hybridize" title="Permalink to this definition">¶</a></dt> <dd>Activates or deactivates <a href="#id5">`</a>HybridBlock`s recursively. Has no effect on non-hybrid children. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> <li>active (bool, default True) – Whether to turn hybrid on or off.</li> <li>**kwargs (string) – Additional flags for hybridized operator.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> </dd></dl> <dl class="class"> <dt id="mxnet.gluon.nn.HybridSequential"> class <code class="descclassname">mxnet.gluon.nn.</code><code class="descname">HybridSequential</code>(prefix=None, params=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/nn/basic_layers.html#HybridSequential">[source]</a><a class="headerlink" href="#mxnet.gluon.nn.HybridSequential" title="Permalink to this definition">¶</a></dt> <dd>Stacks HybridBlocks sequentially. Example: <div class="highlight-default"><div class="highlight"><pre>net = nn.HybridSequential() # use net's name_scope to give child Blocks appropriate names. with net.name_scope(): net.add(nn.Dense(10, activation='relu')) net.add(nn.Dense(20)) net.hybridize() </pre></div> </div> <dl class="method"> <dt id="mxnet.gluon.nn.HybridSequential.add"> <code class="descname">add</code>(*blocks)<a class="reference internal" href="../../../_modules/mxnet/gluon/nn/basic_layers.html#HybridSequential.add">[source]</a><a class="headerlink" href="#mxnet.gluon.nn.HybridSequential.add" title="Permalink to this definition">¶</a></dt> <dd>Adds block on top of the stack. </dd></dl> </dd></dl> Parallelization utility optimizer. <dl class="function"> <dt id="mxnet.gluon.utils.split_data"> <code class="descclassname">mxnet.gluon.utils.</code><code class="descname">split_data</code>(data, num_slice, batch_axis=0, even_split=True)<a class="reference internal" href="../../../_modules/mxnet/gluon/utils.html#split_data">[source]</a><a class="headerlink" href="#mxnet.gluon.utils.split_data" title="Permalink to this definition">¶</a></dt> <dd>Splits an NDArray into <cite>num_slice</cite> slices along <cite>batch_axis</cite>. Usually used for data parallelism where each slices is sent to one device (i.e. GPU). <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <li>data (<a class="reference internal" href="../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a>) – A batch of data.</li> <li>num_slice (int) – Number of desired slices.</li> <li>batch_axis (int, default 0) – The axis along which to slice.</li> <li>even_split (bool, default True) – Whether to force all slices to have the same number of elements. If <cite>True</cite>, an error will be raised when <cite>num_slice</cite> does not evenly divide <cite>data.shape[batch_axis]</cite>.</li> </ul> </td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">Return value is a list even if <cite>num_slice</cite> is 1. </td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body">list of NDArray </td> </tr> </tbody> </table> </dd></dl> <dl class="function"> <dt id="mxnet.gluon.utils.split_and_load"> <code class="descclassname">mxnet.gluon.utils.</code><code class="descname">split_and_load</code>(data, ctx_list, batch_axis=0, even_split=True)<a class="reference internal" href="../../../_modules/mxnet/gluon/utils.html#split_and_load">[source]</a><a class="headerlink" href="#mxnet.gluon.utils.split_and_load" title="Permalink to this definition">¶</a></dt> <dd>Splits an NDArray into <cite>len(ctx_list)</cite> slices along <cite>batch_axis</cite> and loads each slice to one context in <cite>ctx_list</cite>. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <li>data (<a class="reference internal" href="../ndarray/ndarray.html#mxnet.ndarray.NDArray" title="mxnet.ndarray.NDArray">NDArray</a>) – A batch of data.</li> <li>ctx_list (list of Context) – A list of Contexts.</li> <li>batch_axis (int, default 0) – The axis along which to slice.</li> <li>even_split (bool, default True) – Whether to force all slices to have the same number of elements.</li> </ul> </td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">Each corresponds to a context in <cite>ctx_list</cite>. </td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body">list of NDArray </td> </tr> </tbody> </table> </dd></dl> <dl class="function"> <dt id="mxnet.gluon.utils.clip_global_norm"> <code class="descclassname">mxnet.gluon.utils.</code><code class="descname">clip_global_norm</code>(arrays, max_norm)<a class="reference internal" href="../../../_modules/mxnet/gluon/utils.html#clip_global_norm">[source]</a><a class="headerlink" href="#mxnet.gluon.utils.clip_global_norm" title="Permalink to this definition">¶</a></dt> <dd>Rescales NDArrays so that the sum of their 2-norm is smaller than <cite>max_norm</cite>. </dd></dl> <dl class="function"> <dt id="mxnet.gluon.utils.check_sha1"> <code class="descclassname">mxnet.gluon.utils.</code><code class="descname">check_sha1</code>(filename, sha1_hash)<a class="reference internal" href="../../../_modules/mxnet/gluon/utils.html#check_sha1">[source]</a><a class="headerlink" href="#mxnet.gluon.utils.check_sha1" title="Permalink to this definition">¶</a></dt> <dd>Check whether the sha1 hash of the file content matches the expected hash. <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <li>filename (str) – Path to the file.</li> <li>sha1_hash (str) – Expected sha1 hash in hexadecimal digits.</li> </ul> </td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">Whether the file content matches the expected hash. </td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body">bool </td> </tr> </tbody> </table> </dd></dl> <dl class="function"> <dt id="mxnet.gluon.utils.download"> <code class="descclassname">mxnet.gluon.utils.</code><code class="descname">download</code>(url, path=None, overwrite=False, sha1_hash=None)<a class="reference internal" href="../../../_modules/mxnet/gluon/utils.html#download">[source]</a><a class="headerlink" href="#mxnet.gluon.utils.download" title="Permalink to this definition">¶</a></dt> <dd>Download an given URL <table class="docutils field-list" frame="void" rules="none"> <col class="field-name"/> <col class="field-body"/> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple"> <li>url (str) – URL to download</li> <li>path (str, optional) – Destination path to store downloaded file. By default stores to the current directory with same name as in url.</li> <li>overwrite (bool, optional) – Whether to overwrite destination file if already exists.</li> <li>sha1_hash (str, optional) – Expected sha1 hash in hexadecimal digits. Will ignore existing file when hash is specified but doesn’t match.</li> </ul> </td> </tr> <tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">The file path of the downloaded file. </td> </tr> <tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body">str </td> </tr> </tbody> </table> </dd></dl> <script>auto_index("api-reference");</script></div> </div> </div> </div> <div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation"> <div class="sphinxsidebarwrapper"> <h3><a href="../../../index.html">Table Of Contents</a></h3> <ul> <li><a class="reference internal" href="#">Gluon Package</a><ul> <li><a class="reference internal" href="#overview">Overview</a></li> <li><a class="reference internal" href="#parameter">Parameter</a></li> <li><a class="reference internal" href="#containers">Containers</a></li> <li><a class="reference internal" href="#trainer">Trainer</a></li> <li><a class="reference internal" href="#utilities">Utilities</a></li> <li><a class="reference internal" href="#api-reference">API Reference</a></li> </ul> </li> </ul> </div> </div> </div><div class="footer"> <div class="section-disclaimer"> <div class="container"> <div> <img height="60" src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/apache_incubator_logo.png"/> Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), sponsored by the Apache Incubator. 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. "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." </div> </div> </div> </div>  </div> <script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script> <script src="../../../_static/js/sidebar.js" type="text/javascript"></script> <script src="../../../_static/js/search.js" type="text/javascript"></script> <script src="../../../_static/js/navbar.js" type="text/javascript"></script> <script src="../../../_static/js/clipboard.min.js" type="text/javascript"></script> <script src="../../../_static/js/copycode.js" type="text/javascript"></script> <script src="../../../_static/js/page.js" type="text/javascript"></script> <script src="../../../_static/js/docversion.js" type="text/javascript"></script> <script type="text/javascript"> $('body').ready(function () { $('body').css('visibility', 'visible'); }); </script> </body> </html>

versions/1.2.1/api/python/gluon/gluon.html (1,522 lines of code) (raw):