blob: 5b2b2c9510aa0e47f862f35da6d921a0b0010dc7 [file]
<!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="mxnet.gluon.nn.basic_layers" 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="mxnet.gluon.nn.basic_layers" property="og:description"/>
<title>mxnet.gluon.nn.basic_layers — 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("/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://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> -->
<!-- -->
<link href="../../../../genindex.html" rel="index" title="Index">
<link href="../../../../search.html" rel="search" title="Search"/>
<link href="../../../index.html" rel="up" title="Module code"/>
<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="../../../../install/index.html">Install</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 navbar-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>
<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 navbar-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/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="../../../../api/clojure/index.html">Clojure</a></li>
<li><a class="main-nav-link" href="../../../../api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="../../../../api/perl/index.html">Perl</a></li>
<li><a class="main-nav-link" href="../../../../api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="../../../../api/scala/index.html">Scala</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor-docs">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs">
<li><a class="main-nav-link" href="../../../../faq/index.html">FAQ</a></li>
<li><a class="main-nav-link" href="../../../../tutorials/index.html">Tutorials</a>
<li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/0.12.1/example">Examples</a></li>
<li><a class="main-nav-link" href="../../../../architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="../../../../api/python/gluon/model_zoo.html">Model Zoo</a></li>
<li><a class="main-nav-link" href="../../../../api/python/contrib/onnx.html">ONNX</a></li>
</li></ul>
</span>
<span id="dropdown-menu-position-anchor-community">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community <span class="caret"></span></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">Github</a></li>
<li><a class="main-nav-link" href="../../../../community/contribute.html">Contribute</a></li>
<li><a class="main-nav-link" href="../../../../community/ecosystem.html">Ecosystem</a></li>
<li><a class="main-nav-link" href="../../../../community/powered_by.html">Powered By</a></li>
</ul>
</span>
<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(0.12.1)<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/>master</a></li><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/versions/1.2.1/index.html>1.2.1</a></li><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/versions/1.1.0/index.html>1.1.0</a></li><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/versions/1.0.0/index.html>1.0.0</a></li><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</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" id="burgerMenu">
<li><a href="../../../../install/index.html">Install</a></li>
<li><a class="main-nav-link" href="../../../../tutorials/index.html">Tutorials</a></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" tabindex="-1">Github</a></li>
<li><a href="../../../../community/contribute.html" tabindex="-1">Contribute</a></li>
<li><a href="../../../../community/ecosystem.html" tabindex="-1">Ecosystem</a></li>
<li><a href="../../../../community/powered_by.html" tabindex="-1">Powered By</a></li>
</ul>
</li>
<li class="dropdown-submenu">
<a aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" role="button" tabindex="-1">API</a>
<ul class="dropdown-menu">
<li><a href="../../../../api/python/index.html" tabindex="-1">Python</a>
</li>
<li><a href="../../../../api/c++/index.html" tabindex="-1">C++</a>
</li>
<li><a href="../../../../api/clojure/index.html" tabindex="-1">Clojure</a>
</li>
<li><a href="../../../../api/julia/index.html" tabindex="-1">Julia</a>
</li>
<li><a href="../../../../api/perl/index.html" tabindex="-1">Perl</a>
</li>
<li><a href="../../../../api/r/index.html" tabindex="-1">R</a>
</li>
<li><a href="../../../../api/scala/index.html" tabindex="-1">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="../../../../tutorials/index.html" tabindex="-1">Tutorials</a></li>
<li><a href="../../../../faq/index.html" tabindex="-1">FAQ</a></li>
<li><a href="../../../../architecture/index.html" tabindex="-1">Architecture</a></li>
<li><a href="https://github.com/apache/incubator-mxnet/tree/0.12.1/example" tabindex="-1">Examples</a></li>
<li><a href="../../../../api/python/gluon/model_zoo.html" tabindex="-1">Gluon Model Zoo</a></li>
</ul>
</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(0.12.1)</a><ul class="dropdown-menu"><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/>master</a></li><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/versions/1.2.1/index.html>1.2.1</a></li><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/versions/1.1.0/index.html>1.1.0</a></li><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/versions/1.0.0/index.html>1.0.0</a></li><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</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"/>
</input></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>
<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>
<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="../../../../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/contribute.html">Community</a></li>
</ul>
</div>
</div>
<div class="content">
<div class="page-tracker"></div>
<h1>Source code for mxnet.gluon.nn.basic_layers</h1><div class="highlight"><pre>
<span></span><span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
<span class="c1"># distributed with this work for additional information</span>
<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># "License"); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="c1"># coding: utf-8</span>
<span class="c1"># pylint: disable= arguments-differ</span>
<span class="sd">"""Basic neural network layers."""</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'Sequential'</span><span class="p">,</span> <span class="s1">'HybridSequential'</span><span class="p">,</span> <span class="s1">'Dense'</span><span class="p">,</span> <span class="s1">'Dropout'</span><span class="p">,</span> <span class="s1">'Embedding'</span><span class="p">,</span>
<span class="s1">'BatchNorm'</span><span class="p">,</span> <span class="s1">'InstanceNorm'</span><span class="p">,</span> <span class="s1">'LayerNorm'</span><span class="p">,</span> <span class="s1">'Flatten'</span><span class="p">,</span> <span class="s1">'Lambda'</span><span class="p">,</span> <span class="s1">'HybridLambda'</span><span class="p">]</span>
<span class="kn">import</span> <span class="nn">warnings</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">.activations</span> <span class="k">import</span> <span class="n">Activation</span>
<span class="kn">from</span> <span class="nn">..block</span> <span class="k">import</span> <span class="n">Block</span><span class="p">,</span> <span class="n">HybridBlock</span>
<span class="kn">from</span> <span class="nn">..utils</span> <span class="k">import</span> <span class="n">_indent</span>
<span class="kn">from</span> <span class="nn">...</span> <span class="k">import</span> <span class="n">nd</span><span class="p">,</span> <span class="n">sym</span>
<div class="viewcode-block" id="Sequential"><a class="viewcode-back" href="../../../../api/python/gluon/gluon.html#mxnet.gluon.nn.Sequential">[docs]</a><span class="k">class</span> <span class="nc">Sequential</span><span class="p">(</span><span class="n">Block</span><span class="p">):</span>
<span class="sd">"""Stacks Blocks sequentially.</span>
<span class="sd"> Example::</span>
<span class="sd"> net = nn.Sequential()</span>
<span class="sd"> # use net's name_scope to give child Blocks appropriate names.</span>
<span class="sd"> with net.name_scope():</span>
<span class="sd"> net.add(nn.Dense(10, activation='relu'))</span>
<span class="sd"> net.add(nn.Dense(20))</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Sequential</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<div class="viewcode-block" id="Sequential.add"><a class="viewcode-back" href="../../../../api/python/gluon/gluon.html#mxnet.gluon.nn.Sequential.add">[docs]</a> <span class="k">def</span> <span class="nf">add</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">blocks</span><span class="p">):</span>
<span class="sd">"""Adds block on top of the stack."""</span>
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="n">blocks</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">register_child</span><span class="p">(</span><span class="n">block</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">block</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="se">\n</span><span class="si">{modstr}</span><span class="se">\n</span><span class="s1">)'</span>
<span class="n">modstr</span> <span class="o">=</span> <span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">' (</span><span class="si">{key}</span><span class="s1">): </span><span class="si">{block}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">key</span><span class="p">,</span>
<span class="n">block</span><span class="o">=</span><span class="n">_indent</span><span class="p">(</span><span class="n">block</span><span class="o">.</span><span class="fm">__repr__</span><span class="p">(),</span> <span class="mi">2</span><span class="p">))</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">modstr</span><span class="o">=</span><span class="n">modstr</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">):</span>
<span class="n">layers</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">())[</span><span class="n">key</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">layers</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="n">net</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)(</span><span class="n">prefix</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_prefix</span><span class="p">)</span>
<span class="k">with</span> <span class="n">net</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span>
<span class="n">net</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="o">*</span><span class="n">layers</span><span class="p">)</span>
<span class="k">return</span> <span class="n">net</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">layers</span>
<span class="k">def</span> <span class="nf">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="p">)</span>
<div class="viewcode-block" id="Sequential.hybridize"><a class="viewcode-back" href="../../../../api/python/gluon/gluon.html#mxnet.gluon.nn.Sequential.hybridize">[docs]</a> <span class="k">def</span> <span class="nf">hybridize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">active</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">"""Activates or deactivates `HybridBlock`s recursively. Has no effect on</span>
<span class="sd"> non-hybrid children.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> active : bool, default True</span>
<span class="sd"> Whether to turn hybrid on or off.</span>
<span class="sd"> **kwargs : string</span>
<span class="sd"> Additional flags for hybridized operator.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span> <span class="ow">and</span> <span class="nb">all</span><span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">c</span><span class="p">,</span> <span class="n">HybridBlock</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">()):</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
<span class="s2">"All children of this Sequential layer '</span><span class="si">%s</span><span class="s2">' are HybridBlocks. Consider "</span>
<span class="s2">"using HybridSequential for the best performance."</span><span class="o">%</span><span class="bp">self</span><span class="o">.</span><span class="n">prefix</span><span class="p">,</span> <span class="n">stacklevel</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Sequential</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">hybridize</span><span class="p">(</span><span class="n">active</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="HybridSequential"><a class="viewcode-back" href="../../../../api/python/gluon/gluon.html#mxnet.gluon.nn.HybridSequential">[docs]</a><span class="k">class</span> <span class="nc">HybridSequential</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sd">"""Stacks HybridBlocks sequentially.</span>
<span class="sd"> Example::</span>
<span class="sd"> net = nn.HybridSequential()</span>
<span class="sd"> # use net's name_scope to give child Blocks appropriate names.</span>
<span class="sd"> with net.name_scope():</span>
<span class="sd"> net.add(nn.Dense(10, activation='relu'))</span>
<span class="sd"> net.add(nn.Dense(20))</span>
<span class="sd"> net.hybridize()</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">HybridSequential</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<div class="viewcode-block" id="HybridSequential.add"><a class="viewcode-back" href="../../../../api/python/gluon/gluon.html#mxnet.gluon.nn.HybridSequential.add">[docs]</a> <span class="k">def</span> <span class="nf">add</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">blocks</span><span class="p">):</span>
<span class="sd">"""Adds block on top of the stack."""</span>
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="n">blocks</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">register_child</span><span class="p">(</span><span class="n">block</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">block</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="se">\n</span><span class="si">{modstr}</span><span class="se">\n</span><span class="s1">)'</span>
<span class="n">modstr</span> <span class="o">=</span> <span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">' (</span><span class="si">{key}</span><span class="s1">): </span><span class="si">{block}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">key</span><span class="p">,</span>
<span class="n">block</span><span class="o">=</span><span class="n">_indent</span><span class="p">(</span><span class="n">block</span><span class="o">.</span><span class="fm">__repr__</span><span class="p">(),</span> <span class="mi">2</span><span class="p">))</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">items</span><span class="p">()])</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">modstr</span><span class="o">=</span><span class="n">modstr</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">):</span>
<span class="n">layers</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="o">.</span><span class="n">values</span><span class="p">())[</span><span class="n">key</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">layers</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="n">net</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)(</span><span class="n">prefix</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_prefix</span><span class="p">)</span>
<span class="k">with</span> <span class="n">net</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span>
<span class="n">net</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="o">*</span><span class="n">layers</span><span class="p">)</span>
<span class="k">return</span> <span class="n">net</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">layers</span>
<span class="k">def</span> <span class="nf">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_children</span><span class="p">)</span></div>
<div class="viewcode-block" id="Dense"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Dense">[docs]</a><span class="k">class</span> <span class="nc">Dense</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Just your regular densely-connected NN layer.</span>
<span class="sd"> `Dense` implements the operation:</span>
<span class="sd"> `output = activation(dot(input, weight) + bias)`</span>
<span class="sd"> where `activation` is the element-wise activation function</span>
<span class="sd"> passed as the `activation` argument, `weight` is a weights matrix</span>
<span class="sd"> created by the layer, and `bias` is a bias vector created by the layer</span>
<span class="sd"> (only applicable if `use_bias` is `True`).</span>
<span class="sd"> Note: the input must be a tensor with rank 2. Use `flatten` to convert it</span>
<span class="sd"> to rank 2 manually if necessary.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> units : int</span>
<span class="sd"> Dimensionality of the output space.</span>
<span class="sd"> activation : str</span>
<span class="sd"> Activation function to use. See help on `Activation` layer.</span>
<span class="sd"> If you don't specify anything, no activation is applied</span>
<span class="sd"> (ie. "linear" activation: `a(x) = x`).</span>
<span class="sd"> use_bias : bool</span>
<span class="sd"> Whether the layer uses a bias vector.</span>
<span class="sd"> flatten: bool</span>
<span class="sd"> Whether the input tensor should be flattened.</span>
<span class="sd"> If true, all but the first axis of input data are collapsed together.</span>
<span class="sd"> If false, all but the last axis of input data are kept the same, and the transformation</span>
<span class="sd"> applies on the last axis.</span>
<span class="sd"> dtype : str or np.dtype, default 'float32'</span>
<span class="sd"> Data type of output embeddings.</span>
<span class="sd"> weight_initializer : str or `Initializer`</span>
<span class="sd"> Initializer for the `kernel` weights matrix.</span>
<span class="sd"> bias_initializer: str or `Initializer`</span>
<span class="sd"> Initializer for the bias vector.</span>
<span class="sd"> in_units : int, optional</span>
<span class="sd"> Size of the input data. If not specified, initialization will be</span>
<span class="sd"> deferred to the first time `forward` is called and `in_units`</span>
<span class="sd"> will be inferred from the shape of input data.</span>
<span class="sd"> prefix : str or None</span>
<span class="sd"> See document of `Block`.</span>
<span class="sd"> params : ParameterDict or None</span>
<span class="sd"> See document of `Block`.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: if `flatten` is True, `data` should be a tensor with shape</span>
<span class="sd"> `(batch_size, x1, x2, ..., xn)`, where x1 * x2 * ... * xn is equal to</span>
<span class="sd"> `in_units`. If `flatten` is False, `data` should have shape</span>
<span class="sd"> `(x1, x2, ..., xn, in_units)`.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: if `flatten` is True, `out` will be a tensor with shape</span>
<span class="sd"> `(batch_size, units)`. If `flatten` is False, `out` will have shape</span>
<span class="sd"> `(x1, x2, ..., xn, units)`.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">units</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">use_bias</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">flatten</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">dtype</span><span class="o">=</span><span class="s1">'float32'</span><span class="p">,</span> <span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span>
<span class="n">in_units</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Dense</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_flatten</span> <span class="o">=</span> <span class="n">flatten</span>
<span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_units</span> <span class="o">=</span> <span class="n">units</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_in_units</span> <span class="o">=</span> <span class="n">in_units</span>
<span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'weight'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">units</span><span class="p">,</span> <span class="n">in_units</span><span class="p">),</span>
<span class="n">init</span><span class="o">=</span><span class="n">weight_initializer</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">if</span> <span class="n">use_bias</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'bias'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">units</span><span class="p">,),</span>
<span class="n">init</span><span class="o">=</span><span class="n">bias_initializer</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bias</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">activation</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="o">=</span> <span class="n">Activation</span><span class="p">(</span><span class="n">activation</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="n">activation</span><span class="o">+</span><span class="s1">'_'</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">act</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">FullyConnected</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">bias</span><span class="p">,</span> <span class="n">no_bias</span><span class="o">=</span><span class="n">bias</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">,</span> <span class="n">num_hidden</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_units</span><span class="p">,</span>
<span class="n">flatten</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_flatten</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">act</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span><span class="p">(</span><span class="n">act</span><span class="p">)</span>
<span class="k">return</span> <span class="n">act</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{layout}</span><span class="s1">, </span><span class="si">{act}</span><span class="s1">)'</span>
<span class="n">shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">shape</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">act</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="k">else</span> <span class="s1">'linear'</span><span class="p">,</span>
<span class="n">layout</span><span class="o">=</span><span class="s1">'</span><span class="si">{0}</span><span class="s1"> -> </span><span class="si">{1}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">if</span> <span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span> <span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]))</span></div>
<div class="viewcode-block" id="Dropout"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Dropout">[docs]</a><span class="k">class</span> <span class="nc">Dropout</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sd">"""Applies Dropout to the input.</span>
<span class="sd"> Dropout consists in randomly setting a fraction `rate` of input units</span>
<span class="sd"> to 0 at each update during training time, which helps prevent overfitting.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> rate : float</span>
<span class="sd"> Fraction of the input units to drop. Must be a number between 0 and 1.</span>
<span class="sd"> axes : tuple of int, default ()</span>
<span class="sd"> The axes on which dropout mask is shared. If empty, regular dropout is applied.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> References</span>
<span class="sd"> ----------</span>
<span class="sd"> `Dropout: A Simple Way to Prevent Neural Networks from Overfitting</span>
<span class="sd"> <http://www.cs.toronto.edu/~rsalakhu/papers/srivastava14a.pdf>`_</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rate</span><span class="p">,</span> <span class="n">axes</span><span class="o">=</span><span class="p">(),</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Dropout</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_rate</span> <span class="o">=</span> <span class="n">rate</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_axes</span> <span class="o">=</span> <span class="n">axes</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">Dropout</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">p</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_rate</span><span class="p">,</span> <span class="n">axes</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_axes</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(p = </span><span class="si">{_rate}</span><span class="s1">, axes=</span><span class="si">{_axes}</span><span class="s1">)'</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)</span></div>
<div class="viewcode-block" id="BatchNorm"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.BatchNorm">[docs]</a><span class="k">class</span> <span class="nc">BatchNorm</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sd">"""Batch normalization layer (Ioffe and Szegedy, 2014).</span>
<span class="sd"> Normalizes the input at each batch, i.e. applies a transformation</span>
<span class="sd"> that maintains the mean activation close to 0 and the activation</span>
<span class="sd"> standard deviation close to 1.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> axis : int, default 1</span>
<span class="sd"> The axis that should be normalized. This is typically the channels</span>
<span class="sd"> (C) axis. For instance, after a `Conv2D` layer with `layout='NCHW'`,</span>
<span class="sd"> set `axis=1` in `BatchNorm`. If `layout='NHWC'`, then set `axis=3`.</span>
<span class="sd"> momentum: float, default 0.9</span>
<span class="sd"> Momentum for the moving average.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> When the next layer is linear (also e.g. `nn.relu`),</span>
<span class="sd"> this can be disabled since the scaling</span>
<span class="sd"> will be done by the next layer.</span>
<span class="sd"> use_global_stats: bool, default False</span>
<span class="sd"> If True, use global moving statistics instead of local batch-norm. This will force</span>
<span class="sd"> change batch-norm into a scale shift operator.</span>
<span class="sd"> If False, use local batch-norm.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default 'zeros'</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default 'ones'</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> moving_mean_initializer: str or `Initializer`, default 'zeros'</span>
<span class="sd"> Initializer for the moving mean.</span>
<span class="sd"> moving_variance_initializer: str or `Initializer`, default 'ones'</span>
<span class="sd"> Initializer for the moving variance.</span>
<span class="sd"> in_channels : int, default 0</span>
<span class="sd"> Number of channels (feature maps) in input data. If not specified,</span>
<span class="sd"> initialization will be deferred to the first time `forward` is called</span>
<span class="sd"> and `in_channels` will be inferred from the shape of input data.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">momentum</span><span class="o">=</span><span class="mf">0.9</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">use_global_stats</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">beta_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">'ones'</span><span class="p">,</span>
<span class="n">running_mean_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">running_variance_initializer</span><span class="o">=</span><span class="s1">'ones'</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">BatchNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'axis'</span><span class="p">:</span> <span class="n">axis</span><span class="p">,</span> <span class="s1">'eps'</span><span class="p">:</span> <span class="n">epsilon</span><span class="p">,</span> <span class="s1">'momentum'</span><span class="p">:</span> <span class="n">momentum</span><span class="p">,</span>
<span class="s1">'fix_gamma'</span><span class="p">:</span> <span class="ow">not</span> <span class="n">scale</span><span class="p">,</span> <span class="s1">'use_global_stats'</span><span class="p">:</span> <span class="n">use_global_stats</span><span class="p">}</span>
<span class="k">if</span> <span class="n">in_channels</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">in_channels</span> <span class="o">=</span> <span class="n">in_channels</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gamma</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'gamma'</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">'write'</span> <span class="k">if</span> <span class="n">scale</span> <span class="k">else</span> <span class="s1">'null'</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">differentiable</span><span class="o">=</span><span class="n">scale</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'beta'</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">'write'</span> <span class="k">if</span> <span class="n">center</span> <span class="k">else</span> <span class="s1">'null'</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">differentiable</span><span class="o">=</span><span class="n">center</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">running_mean</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'running_mean'</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">'null'</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span>
<span class="n">init</span><span class="o">=</span><span class="n">running_mean_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">differentiable</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">running_var</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'running_var'</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">'null'</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span>
<span class="n">init</span><span class="o">=</span><span class="n">running_variance_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">differentiable</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">cast</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dtype</span><span class="p">):</span>
<span class="k">if</span> <span class="n">np</span><span class="o">.</span><span class="n">dtype</span><span class="p">(</span><span class="n">dtype</span><span class="p">)</span><span class="o">.</span><span class="n">name</span> <span class="o">==</span> <span class="s1">'float16'</span><span class="p">:</span>
<span class="n">dtype</span> <span class="o">=</span> <span class="s1">'float32'</span>
<span class="nb">super</span><span class="p">(</span><span class="n">BatchNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="n">cast</span><span class="p">(</span><span class="n">dtype</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">,</span> <span class="n">running_mean</span><span class="p">,</span> <span class="n">running_var</span><span class="p">):</span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">BatchNorm</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">,</span> <span class="n">running_mean</span><span class="p">,</span> <span class="n">running_var</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{content}</span><span class="s1">'</span>
<span class="n">in_channels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gamma</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">', in_channels=</span><span class="si">{0}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">in_channels</span> <span class="k">if</span> <span class="n">in_channels</span> <span class="k">else</span> <span class="kc">None</span><span class="p">)</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">')'</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">content</span><span class="o">=</span><span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">'='</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="o">.</span><span class="fm">__repr__</span><span class="p">()])</span>
<span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span></div>
<div class="viewcode-block" id="Embedding"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Embedding">[docs]</a><span class="k">class</span> <span class="nc">Embedding</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Turns non-negative integers (indexes/tokens) into dense vectors</span>
<span class="sd"> of fixed size. eg. [4, 20] -> [[0.25, 0.1], [0.6, -0.2]]</span>
<span class="sd"> Note: if `sparse_grad` is set to True, the gradient w.r.t weight will be</span>
<span class="sd"> sparse. Only a subset of optimizers support sparse gradients, including SGD, AdaGrad</span>
<span class="sd"> and Adam. By default lazy updates is turned on, which may perform differently</span>
<span class="sd"> from standard updates. For more details, please check the Optimization API at:</span>
<span class="sd"> https://mxnet.incubator.apache.org/api/python/optimization/optimization.html</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> input_dim : int</span>
<span class="sd"> Size of the vocabulary, i.e. maximum integer index + 1.</span>
<span class="sd"> output_dim : int</span>
<span class="sd"> Dimension of the dense embedding.</span>
<span class="sd"> dtype : str or np.dtype, default 'float32'</span>
<span class="sd"> Data type of output embeddings.</span>
<span class="sd"> weight_initializer : Initializer</span>
<span class="sd"> Initializer for the `embeddings` matrix.</span>
<span class="sd"> sparse_grad: bool</span>
<span class="sd"> If True, gradient w.r.t. weight will be a 'row_sparse' NDArray.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: (N-1)-D tensor with shape: `(x1, x2, ..., xN-1)`.</span>
<span class="sd"> Output:</span>
<span class="sd"> - **out**: N-D tensor with shape: `(x1, x2, ..., xN-1, output_dim)`.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_dim</span><span class="p">,</span> <span class="n">output_dim</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="s1">'float32'</span><span class="p">,</span>
<span class="n">weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">sparse_grad</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Embedding</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="n">grad_stype</span> <span class="o">=</span> <span class="s1">'row_sparse'</span> <span class="k">if</span> <span class="n">sparse_grad</span> <span class="k">else</span> <span class="s1">'default'</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'input_dim'</span><span class="p">:</span> <span class="n">input_dim</span><span class="p">,</span> <span class="s1">'output_dim'</span><span class="p">:</span> <span class="n">output_dim</span><span class="p">,</span>
<span class="s1">'dtype'</span><span class="p">:</span> <span class="n">dtype</span><span class="p">,</span> <span class="s1">'sparse_grad'</span><span class="p">:</span> <span class="n">sparse_grad</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'weight'</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">input_dim</span><span class="p">,</span> <span class="n">output_dim</span><span class="p">),</span>
<span class="n">init</span><span class="o">=</span><span class="n">weight_initializer</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">grad_stype</span><span class="o">=</span><span class="n">grad_stype</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">):</span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">Embedding</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">weight</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{block_name}</span><span class="s1">(</span><span class="si">{input_dim}</span><span class="s1"> -> </span><span class="si">{output_dim}</span><span class="s1">, </span><span class="si">{dtype}</span><span class="s1">)'</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">block_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="Flatten"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Flatten">[docs]</a><span class="k">class</span> <span class="nc">Flatten</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Flattens the input to two dimensional.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape `(N, x1, x2, ..., xn)`</span>
<span class="sd"> Output:</span>
<span class="sd"> - **out**: 2D tensor with shape: `(N, x1 \cdot x2 \cdot ... \cdot xn)`</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Flatten</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">Flatten</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span></div>
<div class="viewcode-block" id="InstanceNorm"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.InstanceNorm">[docs]</a><span class="k">class</span> <span class="nc">InstanceNorm</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""</span>
<span class="sd"> Applies instance normalization to the n-dimensional input array.</span>
<span class="sd"> This operator takes an n-dimensional input array where (n>2) and normalizes</span>
<span class="sd"> the input using the following formula:</span>
<span class="sd"> .. math::</span>
<span class="sd"> \bar{C} = \{i \mid i \neq 0, i \neq axis\}</span>
<span class="sd"> out = \frac{x - mean[data, \bar{C}]}{ \sqrt{Var[data, \bar{C}]} + \epsilon}</span>
<span class="sd"> * gamma + beta</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> axis : int, default 1</span>
<span class="sd"> The axis that will be excluded in the normalization process. This is typically the channels</span>
<span class="sd"> (C) axis. For instance, after a `Conv2D` layer with `layout='NCHW'`,</span>
<span class="sd"> set `axis=1` in `InstanceNorm`. If `layout='NHWC'`, then set `axis=3`. Data will be</span>
<span class="sd"> normalized along axes excluding the first axis and the axis given.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> When the next layer is linear (also e.g. `nn.relu`),</span>
<span class="sd"> this can be disabled since the scaling</span>
<span class="sd"> will be done by the next layer.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default 'zeros'</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default 'ones'</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> in_channels : int, default 0</span>
<span class="sd"> Number of channels (feature maps) in input data. If not specified,</span>
<span class="sd"> initialization will be deferred to the first time `forward` is called</span>
<span class="sd"> and `in_channels` will be inferred from the shape of input data.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> References</span>
<span class="sd"> ----------</span>
<span class="sd"> `Instance Normalization: The Missing Ingredient for Fast Stylization</span>
<span class="sd"> <https://arxiv.org/abs/1607.08022>`_</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> >>> # Input of shape (2,1,2)</span>
<span class="sd"> >>> x = mx.nd.array([[[ 1.1, 2.2]],</span>
<span class="sd"> ... [[ 3.3, 4.4]]])</span>
<span class="sd"> >>> # Instance normalization is calculated with the above formula</span>
<span class="sd"> >>> layer = InstanceNorm()</span>
<span class="sd"> >>> layer.initialize(ctx=mx.cpu(0))</span>
<span class="sd"> >>> layer(x)</span>
<span class="sd"> [[[-0.99998355 0.99998331]]</span>
<span class="sd"> [[-0.99998319 0.99998361]]]</span>
<span class="sd"> <NDArray 2x1x2 @cpu(0)></span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">'ones'</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">InstanceNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'eps'</span><span class="p">:</span> <span class="n">epsilon</span><span class="p">,</span> <span class="s1">'axis'</span><span class="p">:</span> <span class="n">axis</span><span class="p">,</span> <span class="s1">'center'</span><span class="p">:</span> <span class="n">center</span><span class="p">,</span> <span class="s1">'scale'</span><span class="p">:</span> <span class="n">scale</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_axis</span> <span class="o">=</span> <span class="n">axis</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span> <span class="o">=</span> <span class="n">epsilon</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gamma</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'gamma'</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">'write'</span> <span class="k">if</span> <span class="n">scale</span> <span class="k">else</span> <span class="s1">'null'</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'beta'</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">'write'</span> <span class="k">if</span> <span class="n">center</span> <span class="k">else</span> <span class="s1">'null'</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">InstanceNorm</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">,</span>
<span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span><span class="p">)</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">)</span>
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">InstanceNorm</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">'fwd'</span><span class="p">,</span>
<span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span><span class="p">)</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{content}</span><span class="s1">'</span>
<span class="n">in_channels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gamma</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">', in_channels=</span><span class="si">{0}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">in_channels</span><span class="p">)</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">')'</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">content</span><span class="o">=</span><span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">'='</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="o">.</span><span class="fm">__repr__</span><span class="p">()])</span>
<span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span></div>
<div class="viewcode-block" id="LayerNorm"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.LayerNorm">[docs]</a><span class="k">class</span> <span class="nc">LayerNorm</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""</span>
<span class="sd"> Applies layer normalization to the n-dimensional input array.</span>
<span class="sd"> This operator takes an n-dimensional input array and normalizes</span>
<span class="sd"> the input using the given axis:</span>
<span class="sd"> .. math::</span>
<span class="sd"> out = \frac{x - mean[data, axis]}{ \sqrt{Var[data, axis]} + \epsilon} * gamma + beta</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> axis : int, default -1</span>
<span class="sd"> The axis that should be normalized. This is typically the axis of the channels.</span>
<span class="sd"> epsilon: float, default 1e-5</span>
<span class="sd"> Small float added to variance to avoid dividing by zero.</span>
<span class="sd"> center: bool, default True</span>
<span class="sd"> If True, add offset of `beta` to normalized tensor.</span>
<span class="sd"> If False, `beta` is ignored.</span>
<span class="sd"> scale: bool, default True</span>
<span class="sd"> If True, multiply by `gamma`. If False, `gamma` is not used.</span>
<span class="sd"> beta_initializer: str or `Initializer`, default 'zeros'</span>
<span class="sd"> Initializer for the beta weight.</span>
<span class="sd"> gamma_initializer: str or `Initializer`, default 'ones'</span>
<span class="sd"> Initializer for the gamma weight.</span>
<span class="sd"> in_channels : int, default 0</span>
<span class="sd"> Number of channels (feature maps) in input data. If not specified,</span>
<span class="sd"> initialization will be deferred to the first time `forward` is called</span>
<span class="sd"> and `in_channels` will be inferred from the shape of input data.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with arbitrary shape.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with the same shape as `data`.</span>
<span class="sd"> References</span>
<span class="sd"> ----------</span>
<span class="sd"> `Layer Normalization</span>
<span class="sd"> <https://arxiv.org/pdf/1607.06450.pdf>`_</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> >>> # Input of shape (2, 5)</span>
<span class="sd"> >>> x = mx.nd.array([[1, 2, 3, 4, 5], [1, 1, 2, 2, 2]])</span>
<span class="sd"> >>> # Layer normalization is calculated with the above formula</span>
<span class="sd"> >>> layer = LayerNorm()</span>
<span class="sd"> >>> layer.initialize(ctx=mx.cpu(0))</span>
<span class="sd"> >>> layer(x)</span>
<span class="sd"> [[-1.41421 -0.707105 0. 0.707105 1.41421 ]</span>
<span class="sd"> [-1.2247195 -1.2247195 0.81647956 0.81647956 0.81647956]]</span>
<span class="sd"> <NDArray 2x5 @cpu(0)></span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">axis</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">epsilon</span><span class="o">=</span><span class="mf">1e-5</span><span class="p">,</span> <span class="n">center</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
<span class="n">beta_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">gamma_initializer</span><span class="o">=</span><span class="s1">'ones'</span><span class="p">,</span>
<span class="n">in_channels</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">LayerNorm</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="n">params</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'eps'</span><span class="p">:</span> <span class="n">epsilon</span><span class="p">,</span> <span class="s1">'axis'</span><span class="p">:</span> <span class="n">axis</span><span class="p">,</span> <span class="s1">'center'</span><span class="p">:</span> <span class="n">center</span><span class="p">,</span> <span class="s1">'scale'</span><span class="p">:</span> <span class="n">scale</span><span class="p">}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_axis</span> <span class="o">=</span> <span class="n">axis</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span> <span class="o">=</span> <span class="n">epsilon</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_center</span> <span class="o">=</span> <span class="n">center</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_scale</span> <span class="o">=</span> <span class="n">scale</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gamma</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'gamma'</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">'write'</span> <span class="k">if</span> <span class="n">scale</span> <span class="k">else</span> <span class="s1">'null'</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">gamma_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'beta'</span><span class="p">,</span> <span class="n">grad_req</span><span class="o">=</span><span class="s1">'write'</span> <span class="k">if</span> <span class="n">center</span> <span class="k">else</span> <span class="s1">'null'</span><span class="p">,</span>
<span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,),</span> <span class="n">init</span><span class="o">=</span><span class="n">beta_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="p">):</span>
<span class="n">norm_data</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">gamma</span><span class="o">=</span><span class="n">gamma</span><span class="p">,</span> <span class="n">beta</span><span class="o">=</span><span class="n">beta</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_axis</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_epsilon</span><span class="p">)</span>
<span class="k">return</span> <span class="n">norm_data</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{content}</span><span class="s1">'</span>
<span class="n">in_channels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gamma</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">', in_channels=</span><span class="si">{0}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">in_channels</span><span class="p">)</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">')'</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">content</span><span class="o">=</span><span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="s1">'='</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">k</span><span class="p">,</span> <span class="n">v</span><span class="o">.</span><span class="fm">__repr__</span><span class="p">()])</span>
<span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">()]))</span></div>
<div class="viewcode-block" id="Lambda"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.Lambda">[docs]</a><span class="k">class</span> <span class="nc">Lambda</span><span class="p">(</span><span class="n">Block</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Wraps an operator or an expression as a Block object.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> function : str or function</span>
<span class="sd"> Function used in lambda must be one of the following:</span>
<span class="sd"> 1) the name of an operator that is available in ndarray. For example::</span>
<span class="sd"> block = Lambda('tanh')</span>
<span class="sd"> 2) a function that conforms to "def function(*args)". For example::</span>
<span class="sd"> block = Lambda(lambda x: nd.LeakyReLU(x, slope=0.1))</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - ** *args **: one or more input data. Their shapes depend on the function.</span>
<span class="sd"> Output:</span>
<span class="sd"> - ** *outputs **: one or more output data. Their shapes depend on the function.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">function</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Lambda</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">function</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="k">assert</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">nd</span><span class="p">,</span> <span class="n">function</span><span class="p">),</span> \
<span class="s2">"Function name </span><span class="si">%s</span><span class="s2"> is not found in ndarray."</span> <span class="o">%</span> <span class="n">function</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func_impl</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">nd</span><span class="p">,</span> <span class="n">function</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">callable</span><span class="p">(</span><span class="n">function</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func_impl</span> <span class="o">=</span> <span class="n">function</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"Unrecognized function in lambda: </span><span class="si">{}</span><span class="s2"> of type </span><span class="si">{}</span><span class="s2">"</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">function</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">function</span><span class="p">)))</span>
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_func_impl</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{function}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">function</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_func_impl</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)</span></div>
<div class="viewcode-block" id="HybridLambda"><a class="viewcode-back" href="../../../../api/python/gluon/nn.html#mxnet.gluon.nn.HybridLambda">[docs]</a><span class="k">class</span> <span class="nc">HybridLambda</span><span class="p">(</span><span class="n">HybridBlock</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Wraps an operator or an expression as a HybridBlock object.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> function : str or function</span>
<span class="sd"> Function used in lambda must be one of the following:</span>
<span class="sd"> 1) the name of an operator that is available in both symbol and ndarray. For example::</span>
<span class="sd"> block = HybridLambda('tanh')</span>
<span class="sd"> 2) a function that conforms to "def function(F, data, *args)". For example::</span>
<span class="sd"> block = HybridLambda(lambda F, x: F.LeakyReLU(x, slope=0.1))</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - ** *args **: one or more input data. First argument must be symbol or ndarray.</span>
<span class="sd"> Their shapes depend on the function.</span>
<span class="sd"> Output:</span>
<span class="sd"> - ** *outputs **: one or more output data. Their shapes depend on the function.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">function</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">HybridLambda</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">function</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="k">assert</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">nd</span><span class="p">,</span> <span class="n">function</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">function</span><span class="p">),</span> \
<span class="s2">"Function name </span><span class="si">%s</span><span class="s2"> is not found in symbol/ndarray."</span> <span class="o">%</span> <span class="n">function</span>
<span class="n">func_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">sym</span><span class="p">:</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">sym</span><span class="p">,</span> <span class="n">function</span><span class="p">),</span> <span class="n">nd</span><span class="p">:</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">nd</span><span class="p">,</span> <span class="n">function</span><span class="p">)}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">F</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">:</span> <span class="n">func_dict</span><span class="p">[</span><span class="n">F</span><span class="p">](</span><span class="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func_name</span> <span class="o">=</span> <span class="n">function</span>
<span class="k">elif</span> <span class="n">callable</span><span class="p">(</span><span class="n">function</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func</span> <span class="o">=</span> <span class="n">function</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func_name</span> <span class="o">=</span> <span class="n">function</span><span class="o">.</span><span class="vm">__name__</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"Unrecognized function in lambda: </span><span class="si">{}</span><span class="s2"> of type </span><span class="si">{}</span><span class="s2">"</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">function</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">function</span><span class="p">)))</span>
<span class="k">def</span> <span class="nf">hybrid_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_func</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">x</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{function}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">function</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_func_name</span><span class="p">)</span></div>
</pre></div>
</div>
</div>
<div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
</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"/>
<p>
Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), <strong>sponsored by the <i>Apache Incubator</i></strong>. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
</p>
<p>
"Copyright © 2017-2018, The Apache Software Foundation
Apache MXNet, MXNet, Apache, the Apache feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the Apache Software Foundation."
</p>
</div>
</div>
</div>
</div> <!-- pagename != index -->
</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 type="text/javascript">
$('body').ready(function () {
$('body').css('visibility', 'visible');
});
</script>
</body>
</html>