Google Git
Sign in
apache / mxnet-site / refs/heads/test-revert / . / versions / 0.11.0 / tutorials / gluon / gluon.html
blob: 40a50213b2ac087d5891d1e07236b50f495042cb [file] [log] [blame]
<!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"/>
<title>Gluon - Neural network building blocks — 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: ''
};
</script>
<script src="../../_static/jquery-1.11.1.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://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script>
<script type="text/javascript"> jQuery(function() { Search.loadIndex("/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>
<!-- -->
<!-- <script type="text/javascript" src="../../_static/jquery.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="../../_static/underscore.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="../../_static/doctools.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> -->
<!-- -->
<link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/>
</head>
<body role="document"><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="../../_static/mxnet.png"/></a>
</h1>
<nav class="nav-bar" id="main-nav">
<a class="main-nav-link" href="../../get_started/install.html">Install</a>
<a class="main-nav-link" href="../../tutorials/index.html">Tutorials</a>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon <span class="caret"></span></a>
<ul class="dropdown-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="../../gluon/index.html">About</a></li>
<li><a class="main-nav-link" href="http://gluon.mxnet.io/">Tutorials</a></li>
</ul>
</span>
<a class="main-nav-link" href="../../how_to/index.html">How To</a>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API <span class="caret"></span></a>
<ul class="dropdown-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="../../api/python/index.html">Python</a></li>
<li><a class="main-nav-link" href="../../api/scala/index.html">Scala</a></li>
<li><a class="main-nav-link" href="../../api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="../../api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="../../api/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="../../api/perl/index.html">Perl</a></li>
</ul>
</span>
<a class="main-nav-link" href="../../architecture/index.html">Architecture</a>
<!-- <a class="main-nav-link" href="../../community/index.html">Community</a> -->
<a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a>
<span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">Versions(0.11.0)<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/>1.0.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</a></li></ul></span></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 dropdown-menu-right" id="burgerMenu">
<li><a href="../../get_started/install.html">Install</a></li>
<li><a href="../../tutorials/index.html">Tutorials</a></li>
<li><a href="../../how_to/index.html">How To</a></li>
<li class="dropdown-submenu">
<a href="#" tabindex="-1">API</a>
<ul class="dropdown-menu">
<li><a href="../../api/python/index.html" tabindex="-1">Python</a>
</li>
<li><a href="../../api/scala/index.html" tabindex="-1">Scala</a>
</li>
<li><a href="../../api/r/index.html" tabindex="-1">R</a>
</li>
<li><a href="../../api/julia/index.html" tabindex="-1">Julia</a>
</li>
<li><a href="../../api/c++/index.html" tabindex="-1">C++</a>
</li>
<li><a href="../../api/perl/index.html" tabindex="-1">Perl</a>
</li>
</ul>
</li>
<li><a href="../../architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a></li>
<li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">Versions(0.11.0)</a><ul class="dropdown-menu"><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/>1.0.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</a></li></ul></li></ul>
</div>
<div class="plusIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"><span aria-hidden="true" class="glyphicon glyphicon-plus"></span></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">
<i class="glyphicon glyphicon-search"></i>
<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"/>
</form>
<div id="search-preview"></div>
</div>
<div id="searchIcon">
<span aria-hidden="true" class="glyphicon glyphicon-search"></span>
</div>
<!-- <div id="lang-select-wrap"> -->
<!-- <label id="lang-select-label"> -->
<!-- <\!-- <i class="fa fa-globe"></i> -\-> -->
<!-- <span></span> -->
<!-- </label> -->
<!-- <select id="lang-select"> -->
<!-- <option value="en">Eng</option> -->
<!-- <option value="zh">中文</option> -->
<!-- </select> -->
<!-- </div> -->
<!-- <a id="mobile-nav-toggle">
<span class="mobile-nav-toggle-bar"></span>
<span class="mobile-nav-toggle-bar"></span>
<span class="mobile-nav-toggle-bar"></span>
</a> -->
</div>
</div>
</div>
<div class="container">
<div class="row">
<div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../api/python/index.html">Python Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/r/index.html">R Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/julia/index.html">Julia Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/c++/index.html">C++ Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/scala/index.html">Scala Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/perl/index.html">Perl Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../how_to/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="../index.html">Tutorials</a></li>
</ul>
</div>
</div>
<div class="content">
<div class="section" id="gluon-neural-network-building-blocks">
<span id="gluon-neural-network-building-blocks"></span><h1>Gluon - Neural network building blocks<a class="headerlink" href="#gluon-neural-network-building-blocks" title="Permalink to this headline"></a></h1>
<p>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.</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="c1"># import dependencies</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">import</span> <span class="nn">mxnet</span> <span class="kn">as</span> <span class="nn">mx</span>
<span class="kn">import</span> <span class="nn">mxnet.ndarray</span> <span class="kn">as</span> <span class="nn">F</span>
<span class="kn">import</span> <span class="nn">mxnet.gluon</span> <span class="kn">as</span> <span class="nn">gluon</span>
<span class="kn">from</span> <span class="nn">mxnet.gluon</span> <span class="kn">import</span> <span class="n">nn</span>
<span class="kn">from</span> <span class="nn">mxnet</span> <span class="kn">import</span> <span class="n">autograd</span>
</pre></div>
</div>
<p>Neural networks (and other machine learning models) can be defined and trained
with <code class="docutils literal"><span class="pre">gluon.nn</span></code> and <code class="docutils literal"><span class="pre">gluon.rnn</span></code> package. A typical training script has the following
steps:</p>
<ul class="simple">
<li>Define network</li>
<li>Initialize parameters</li>
<li>Loop over inputs</li>
<li>Forward input through network to get output</li>
<li>Compute loss with output and label</li>
<li>Backprop gradient</li>
<li>Update parameters with gradient descent.</li>
</ul>
<div class="section" id="define-network">
<span id="define-network"></span><h2>Define Network<a class="headerlink" href="#define-network" title="Permalink to this headline"></a></h2>
<p><code class="docutils literal"><span class="pre">gluon.Block</span></code> is the basic building block of models. You can define networks by
composing and inheriting <code class="docutils literal"><span class="pre">Block</span></code>:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">Net</span><span class="p">(</span><span class="n">gluon</span><span class="o">.</span><span class="n">Block</span><span class="p">):</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Net</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span>
<span class="c1"># layers created in name_scope will inherit name space</span>
<span class="c1"># from parent layer.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conv1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2D</span><span class="p">(</span><span class="mi">6</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pool1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2D</span><span class="p">(</span><span class="n">pool_size</span><span class="o">=</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conv2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2D</span><span class="p">(</span><span class="mi">16</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">5</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">pool2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2D</span><span class="p">(</span><span class="n">pool_size</span><span class="o">=</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span><span class="mi">2</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fc1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">120</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fc2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">84</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fc3</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dense</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool1</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv1</span><span class="p">(</span><span class="n">x</span><span class="p">)))</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool2</span><span class="p">(</span><span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv2</span><span class="p">(</span><span class="n">x</span><span class="p">)))</span>
<span class="c1"># 0 means copy over size from corresponding dimension.</span>
<span class="c1"># -1 means infer size from the rest of dimensions.</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="mi">0</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">))</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fc1</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fc2</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc3</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
</pre></div>
</div>
</div>
<div class="section" id="initialize-parameters">
<span id="initialize-parameters"></span><h2>Initialize Parameters<a class="headerlink" href="#initialize-parameters" title="Permalink to this headline"></a></h2>
<p>A network must be created and initialized before it can be used:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">net</span> <span class="o">=</span> <span class="n">Net</span><span class="p">()</span>
<span class="c1"># Initialize on CPU. Replace with `mx.gpu(0)`, or `[mx.gpu(0), mx.gpu(1)]`,</span>
<span class="c1"># etc to use one or more GPUs.</span>
<span class="n">net</span><span class="o">.</span><span class="n">collect_params</span><span class="p">()</span><span class="o">.</span><span class="n">initialize</span><span class="p">(</span><span class="n">mx</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">Xavier</span><span class="p">(),</span> <span class="n">ctx</span><span class="o">=</span><span class="n">mx</span><span class="o">.</span><span class="n">cpu</span><span class="p">())</span>
</pre></div>
</div>
<p>Note that because we didn’t specify input size to layers in Net’s constructor,
the shape of parameters cannot be determined at this point. Actual initialization
is deferred to the first forward pass, i.e. if you access <code class="docutils literal"><span class="pre">net.fc1.weight.data()</span></code>
now an exception will be raised.</p>
<p>You can actually initialize the weights by running a forward pass:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">data</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">random_normal</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">32</span><span class="p">,</span> <span class="mi">32</span><span class="p">))</span> <span class="c1"># dummy data</span>
<span class="n">output</span> <span class="o">=</span> <span class="n">net</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
</pre></div>
</div>
<p>Or you can specify input size when creating layers, i.e. <code class="docutils literal"><span class="pre">nn.Dense(84,</span> <span class="pre">in_units=120)</span></code>
instead of <code class="docutils literal"><span class="pre">nn.Dense(84)</span></code>.</p>
</div>
<div class="section" id="loss-functions">
<span id="loss-functions"></span><h2>Loss Functions<a class="headerlink" href="#loss-functions" title="Permalink to this headline"></a></h2>
<p>Loss functions take (output, label) pairs and compute a scalar loss for each sample
in the mini-batch. The scalars measure how far each output is from the label.</p>
<p>There are many predefined loss functions in <code class="docutils literal"><span class="pre">gluon.loss</span></code>. Here we use
<code class="docutils literal"><span class="pre">softmax_cross_entropy_loss</span></code> for digit classification.</p>
<p>To compute loss and backprop for one iteration, we do:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">label</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">nd</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span> <span class="c1"># dummy label</span>
<span class="k">with</span> <span class="n">autograd</span><span class="o">.</span><span class="n">record</span><span class="p">():</span>
<span class="n">output</span> <span class="o">=</span> <span class="n">net</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="n">L</span> <span class="o">=</span> <span class="n">gluon</span><span class="o">.</span><span class="n">loss</span><span class="o">.</span><span class="n">SoftmaxCrossEntropyLoss</span><span class="p">()</span>
<span class="n">loss</span> <span class="o">=</span> <span class="n">L</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span>
<span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'loss:'</span><span class="p">,</span> <span class="n">loss</span><span class="p">)</span>
<span class="k">print</span><span class="p">(</span><span class="s1">'grad:'</span><span class="p">,</span> <span class="n">net</span><span class="o">.</span><span class="n">fc1</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">grad</span><span class="p">())</span>
</pre></div>
</div>
</div>
<div class="section" id="updating-the-weights">
<span id="updating-the-weights"></span><h2>Updating the weights<a class="headerlink" href="#updating-the-weights" title="Permalink to this headline"></a></h2>
<p>Now that gradient is computed, we just need to update the weights. This is usually
done with formulas like <code class="docutils literal"><span class="pre">weight</span> <span class="pre">=</span> <span class="pre">weight</span> <span class="pre">-</span> <span class="pre">learning_rate</span> <span class="pre">*</span> <span class="pre">grad</span> <span class="pre">/</span> <span class="pre">batch_size</span></code>.
Note we divide gradient by batch_size because gradient is aggregated over the
entire batch. For example,</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">lr</span> <span class="o">=</span> <span class="mf">0.01</span>
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">net</span><span class="o">.</span><span class="n">collect_params</span><span class="p">()</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="n">p</span><span class="o">.</span><span class="n">data</span><span class="p">()[:]</span> <span class="o">-=</span> <span class="n">lr</span> <span class="o">/</span> <span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">p</span><span class="o">.</span><span class="n">grad</span><span class="p">()</span>
</pre></div>
</div>
<p>But sometimes you want more fancy updating rules like momentum and Adam, and since
this is a commonly used functionality, gluon provide a <code class="docutils literal"><span class="pre">Trainer</span></code> class for it:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">trainer</span> <span class="o">=</span> <span class="n">gluon</span><span class="o">.</span><span class="n">Trainer</span><span class="p">(</span><span class="n">net</span><span class="o">.</span><span class="n">collect_params</span><span class="p">(),</span> <span class="s1">'sgd'</span><span class="p">,</span> <span class="p">{</span><span class="s1">'learning_rate'</span><span class="p">:</span> <span class="mf">0.01</span><span class="p">})</span>
<span class="k">with</span> <span class="n">autograd</span><span class="o">.</span><span class="n">record</span><span class="p">():</span>
<span class="n">output</span> <span class="o">=</span> <span class="n">net</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="n">L</span> <span class="o">=</span> <span class="n">gluon</span><span class="o">.</span><span class="n">loss</span><span class="o">.</span><span class="n">SoftmaxCrossEntropyLoss</span><span class="p">()</span>
<span class="n">loss</span> <span class="o">=</span> <span class="n">L</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">label</span><span class="p">)</span>
<span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span>
<span class="c1"># do the update. Trainer needs to know the batch size of data to normalize</span>
<span class="c1"># the gradient by 1/batch_size.</span>
<span class="n">trainer</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">data</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
</pre></div>
</div>
<div class="btn-group" role="group">
<div class="download_btn"><a download="gluon.ipynb" href="gluon.ipynb"><span class="glyphicon glyphicon-download-alt"></span> gluon.ipynb</a></div></div></div>
</div>
<div class="container">
<div class="footer">
<p> </p>
</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 - Neural network building blocks</a><ul>
<li><a class="reference internal" href="#define-network">Define Network</a></li>
<li><a class="reference internal" href="#initialize-parameters">Initialize Parameters</a></li>
<li><a class="reference internal" href="#loss-functions">Loss Functions</a></li>
<li><a class="reference internal" href="#updating-the-weights">Updating the weights</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div> <!-- pagename != index -->
<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 type="text/javascript">
$('body').ready(function () {
$('body').css('visibility', 'visible');
});
</script>
</div></body>
</html>