Google Git
Sign in
apache / mxnet-site / refs/heads/test-revert / . / _modules / mxnet / initializer.html
blob: 868842ab0f0f3094bed0cdd4b3afa79fc205d5e1 [file] [log] [blame]
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8"/>
<meta content="IE=edge" http-equiv="X-UA-Compatible"/>
<meta content="width=device-width, initial-scale=1" name="viewport"/>
<title>mxnet.initializer — mxnet documentation</title>
<link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/>
<link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/>
<link href="../../_static/basic.css" rel="stylesheet" type="text/css">
<link href="../../_static/pygments.css" rel="stylesheet" type="text/css">
<link href="../../_static/mxnet.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../',
VERSION: '',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: ''
};
</script>
<script src="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://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> -->
<!-- -->
<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></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>
<a class="main-nav-link" href="../../tutorials/index.html">Tutorials</a>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon <span class="caret"></span></a>
<ul class="dropdown-menu 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/scala/index.html">Scala</a></li>
<li><a class="main-nav-link" href="../../api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="../../api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="../../api/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="../../api/perl/index.html">Perl</a></li>
</ul>
</span>
<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="../../architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/1.0.0/example">Examples</a></li>
<li><a class="main-nav-link" href="../../model_zoo/index.html">Model Zoo</a></li>
</ul>
</span>
<a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a>
<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="../../community/index.html">Community</a></li>
<li><a class="main-nav-link" href="../../community/contribute.html">Contribute</a></li>
<li><a class="main-nav-link" href="../../community/powered_by.html">Powered By</a></li>
</ul>
</span>
<a class="main-nav-link" href="http://discuss.mxnet.io">Discuss</a>
<span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">Versions(1.0.0)<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/>1.0.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</a></li></ul></span></nav>
<script> function getRootPath(){ return "../../" } </script>
<div class="burgerIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button">☰</a>
<ul class="dropdown-menu" 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">
<a href="#" tabindex="-1">Community</a>
<ul class="dropdown-menu">
<li><a href="../../community/index.html" tabindex="-1">Community</a></li>
<li><a href="../../community/contribute.html" tabindex="-1">Contribute</a></li>
<li><a href="../../community/powered_by.html" tabindex="-1">Powered By</a></li>
</ul>
</li>
<li class="dropdown-submenu">
<a href="#" tabindex="-1">API</a>
<ul class="dropdown-menu">
<li><a href="../../api/python/index.html" tabindex="-1">Python</a>
</li>
<li><a href="../../api/scala/index.html" tabindex="-1">Scala</a>
</li>
<li><a href="../../api/r/index.html" tabindex="-1">R</a>
</li>
<li><a href="../../api/julia/index.html" tabindex="-1">Julia</a>
</li>
<li><a href="../../api/c++/index.html" tabindex="-1">C++</a>
</li>
<li><a href="../../api/perl/index.html" tabindex="-1">Perl</a>
</li>
</ul>
</li>
<li class="dropdown-submenu">
<a 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/1.0.0/example" tabindex="-1">Examples</a></li>
<li><a href="../../model_zoo/index.html" tabindex="-1">Model Zoo</a></li>
</ul>
</li>
<li><a href="../../architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a></li>
<li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">Versions(1.0.0)</a><ul class="dropdown-menu"><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/>1.0.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</a></li></ul></li></ul>
</div>
<div class="plusIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"><span aria-hidden="true" class="glyphicon glyphicon-plus"></span></a>
<ul class="dropdown-menu dropdown-menu-right" id="plusMenu"></ul>
</div>
<div id="search-input-wrap">
<form action="../../search.html" autocomplete="off" class="" method="get" role="search">
<div class="form-group inner-addon left-addon">
<i class="glyphicon glyphicon-search"></i>
<input class="form-control" name="q" placeholder="Search" type="text"/>
</div>
<input name="check_keywords" type="hidden" value="yes">
<input name="area" type="hidden" value="default"/>
</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/index.html">Community</a></li>
</ul>
</div>
</div>
<div class="content">
<div class="page-tracker"></div>
<h1>Source code for mxnet.initializer</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="sd">"""Weight initializer."""</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">absolute_import</span><span class="p">,</span> <span class="n">print_function</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">warnings</span>
<span class="kn">import</span> <span class="nn">json</span>
<span class="kn">from</span> <span class="nn">math</span> <span class="kn">import</span> <span class="n">sqrt</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">.base</span> <span class="kn">import</span> <span class="n">string_types</span>
<span class="kn">from</span> <span class="nn">.ndarray</span> <span class="kn">import</span> <span class="n">NDArray</span><span class="p">,</span> <span class="n">load</span>
<span class="kn">from</span> <span class="nn">.</span> <span class="kn">import</span> <span class="n">random</span>
<span class="kn">from</span> <span class="nn">.</span> <span class="kn">import</span> <span class="n">registry</span>
<span class="kn">from</span> <span class="nn">.</span> <span class="kn">import</span> <span class="n">ndarray</span>
<span class="c1"># inherit str for backward compatibility</span>
<div class="viewcode-block" id="InitDesc"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.InitDesc">[docs]</a><span class="k">class</span> <span class="nc">InitDesc</span><span class="p">(</span><span class="nb">str</span><span class="p">):</span>
<span class="sd">"""Descriptor for the initialization pattern.</span>
<span class="sd"> Parameter</span>
<span class="sd"> ---------</span>
<span class="sd"> name : str</span>
<span class="sd"> Name of variable.</span>
<span class="sd"> attrs : dict of str to str</span>
<span class="sd"> Attributes of this variable taken from ``Symbol.attr_dict``.</span>
<span class="sd"> global_init : Initializer</span>
<span class="sd"> Global initializer to fallback to.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__new__</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">attrs</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">global_init</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="n">ret</span> <span class="o">=</span> <span class="nb">super</span><span class="p">(</span><span class="n">InitDesc</span><span class="p">,</span> <span class="bp">cls</span><span class="p">)</span><span class="o">.</span><span class="fm">__new__</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
<span class="n">ret</span><span class="o">.</span><span class="n">attrs</span> <span class="o">=</span> <span class="n">attrs</span> <span class="ow">or</span> <span class="p">{}</span>
<span class="n">ret</span><span class="o">.</span><span class="n">global_init</span> <span class="o">=</span> <span class="n">global_init</span>
<span class="k">return</span> <span class="n">ret</span></div>
<div class="viewcode-block" id="Initializer"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Initializer">[docs]</a><span class="k">class</span> <span class="nc">Initializer</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""The base class of an initializer."""</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_kwargs</span> <span class="o">=</span> <span class="n">kwargs</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verbose</span> <span class="o">=</span> <span class="bp">False</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_print_func</span> <span class="o">=</span> <span class="bp">None</span>
<div class="viewcode-block" id="Initializer.set_verbosity"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Initializer.set_verbosity">[docs]</a> <span class="k">def</span> <span class="nf">set_verbosity</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">print_func</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""Switch on/off verbose mode</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> verbose : bool</span>
<span class="sd"> switch on/off verbose mode</span>
<span class="sd"> print_func : function</span>
<span class="sd"> A function that computes statistics of initialized arrays.</span>
<span class="sd"> Takes an `NDArray` and returns an `str`. Defaults to mean</span>
<span class="sd"> absolute value str((|x|/size(x)).asscalar()).</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verbose</span> <span class="o">=</span> <span class="n">verbose</span>
<span class="k">if</span> <span class="n">print_func</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">def</span> <span class="nf">asum_stat</span><span class="p">(</span><span class="n">x</span><span class="p">):</span>
<span class="sd">"""returns |x|/size(x), async execution."""</span>
<span class="k">return</span> <span class="nb">str</span><span class="p">((</span><span class="n">ndarray</span><span class="o">.</span><span class="n">norm</span><span class="p">(</span><span class="n">x</span><span class="p">)</span><span class="o">/</span><span class="n">sqrt</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">size</span><span class="p">))</span><span class="o">.</span><span class="n">asscalar</span><span class="p">())</span>
<span class="n">print_func</span> <span class="o">=</span> <span class="n">asum_stat</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_print_func</span> <span class="o">=</span> <span class="n">print_func</span>
<span class="k">return</span> <span class="bp">self</span></div>
<span class="k">def</span> <span class="nf">_verbose_print</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">desc</span><span class="p">,</span> <span class="n">init</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="sd">"""Internal verbose print function</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> desc : InitDesc or str</span>
<span class="sd"> name of the array</span>
<span class="sd"> init : str</span>
<span class="sd"> initializer pattern</span>
<span class="sd"> arr : NDArray</span>
<span class="sd"> initialized array</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_verbose</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_print_func</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Initialized </span><span class="si">%s</span><span class="s1"> as </span><span class="si">%s</span><span class="s1">: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">desc</span><span class="p">,</span> <span class="n">init</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_print_func</span><span class="p">(</span><span class="n">arr</span><span class="p">))</span>
<div class="viewcode-block" id="Initializer.dumps"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Initializer.dumps">[docs]</a> <span class="k">def</span> <span class="nf">dumps</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Saves the initializer to string</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> str</span>
<span class="sd"> JSON formatted string that describes the initializer.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> >>> # Create initializer and retrieve its parameters</span>
<span class="sd"> ...</span>
<span class="sd"> >>> init = mx.init.Normal(0.5)</span>
<span class="sd"> >>> init.dumps()</span>
<span class="sd"> '["normal", {"sigma": 0.5}]'</span>
<span class="sd"> >>> init = mx.init.Xavier(factor_type="in", magnitude=2.34)</span>
<span class="sd"> >>> init.dumps()</span>
<span class="sd"> '["xavier", {"rnd_type": "uniform", "magnitude": 2.34, "factor_type": "in"}]'</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">([</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="o">.</span><span class="n">lower</span><span class="p">(),</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="Initializer.__call__"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Initializer.__call__">[docs]</a> <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="sd">"""Initialize an array</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> desc : InitDesc</span>
<span class="sd"> Initialization pattern descriptor.</span>
<span class="sd"> arr : NDArray</span>
<span class="sd"> The array to be initialized.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">InitDesc</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_legacy_init</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">return</span>
<span class="k">if</span> <span class="n">desc</span><span class="o">.</span><span class="n">global_init</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">desc</span><span class="o">.</span><span class="n">global_init</span> <span class="o">=</span> <span class="bp">self</span>
<span class="n">init</span> <span class="o">=</span> <span class="n">desc</span><span class="o">.</span><span class="n">attrs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'__init__'</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
<span class="k">if</span> <span class="n">init</span><span class="p">:</span>
<span class="c1"># when calling Variable initializer</span>
<span class="n">create</span><span class="p">(</span><span class="n">init</span><span class="p">)</span><span class="o">.</span><span class="n">_init_weight</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verbose_print</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">init</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># register nnvm::FSetInputVariableAttrs in the backend for new patterns</span>
<span class="c1"># don't add new cases here.</span>
<span class="k">if</span> <span class="n">desc</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'weight'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_weight</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verbose_print</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="s1">'weight'</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">desc</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'bias'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_bias</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verbose_print</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="s1">'bias'</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">desc</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'gamma'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_gamma</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verbose_print</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="s1">'gamma'</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">desc</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'beta'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_beta</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verbose_print</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="s1">'beta'</span><span class="p">,</span> <span class="n">arr</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">_init_default</span><span class="p">(</span><span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="nf">_legacy_init</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="sd">"""Legacy initialization method.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> name : str</span>
<span class="sd"> Name of corrosponding NDArray.</span>
<span class="sd"> arr : NDArray</span>
<span class="sd"> NDArray to be initialized.</span>
<span class="sd"> """</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
<span class="s2">"</span><span class="se">\033</span><span class="s2">[91mCalling initializer with init(str, NDArray) has been deprecated."</span> \
<span class="s2">"please use init(mx.init.InitDesc(...), NDArray) instead.</span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">,</span>
<span class="ne">DeprecationWarning</span><span class="p">,</span> <span class="n">stacklevel</span><span class="o">=</span><span class="mi">3</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">string_types</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">'name must be string'</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arr</span><span class="p">,</span> <span class="n">NDArray</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">'arr must be NDArray'</span><span class="p">)</span>
<span class="k">if</span> <span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'upsampling'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_bilinear</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'stn_loc'</span><span class="p">)</span> <span class="ow">and</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'weight'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_zero</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'stn_loc'</span><span class="p">)</span> <span class="ow">and</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'bias'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_loc_bias</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'bias'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_bias</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'gamma'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_gamma</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'beta'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_beta</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'weight'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_weight</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s2">"moving_mean"</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_zero</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s2">"moving_var"</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_one</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s2">"moving_inv_var"</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_zero</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s2">"moving_avg"</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init_zero</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</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">_init_default</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_init_bilinear</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">weight</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">prod</span><span class="p">(</span><span class="n">arr</span><span class="o">.</span><span class="n">shape</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">shape</span> <span class="o">=</span> <span class="n">arr</span><span class="o">.</span><span class="n">shape</span>
<span class="n">f</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ceil</span><span class="p">(</span><span class="n">shape</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span> <span class="o">/</span> <span class="mf">2.</span><span class="p">)</span>
<span class="n">c</span> <span class="o">=</span> <span class="p">(</span><span class="mi">2</span> <span class="o">*</span> <span class="n">f</span> <span class="o">-</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">f</span> <span class="o">%</span> <span class="mi">2</span><span class="p">)</span> <span class="o">/</span> <span class="p">(</span><span class="mf">2.</span> <span class="o">*</span> <span class="n">f</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">prod</span><span class="p">(</span><span class="n">shape</span><span class="p">)):</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">i</span> <span class="o">%</span> <span class="n">shape</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span>
<span class="n">y</span> <span class="o">=</span> <span class="p">(</span><span class="n">i</span> <span class="o">/</span> <span class="n">shape</span><span class="p">[</span><span class="mi">3</span><span class="p">])</span> <span class="o">%</span> <span class="n">shape</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
<span class="n">weight</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="nb">abs</span><span class="p">(</span><span class="n">x</span> <span class="o">/</span> <span class="n">f</span> <span class="o">-</span> <span class="n">c</span><span class="p">))</span> <span class="o">*</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="nb">abs</span><span class="p">(</span><span class="n">y</span> <span class="o">/</span> <span class="n">f</span> <span class="o">-</span> <span class="n">c</span><span class="p">))</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="n">weight</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">shape</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_init_loc_bias</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">shape</span> <span class="o">=</span> <span class="n">arr</span><span class="o">.</span><span class="n">shape</span>
<span class="k">assert</span><span class="p">(</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="mi">6</span><span class="p">)</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="mf">1.0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">,</span> <span class="mi">0</span><span class="p">])</span>
<span class="k">def</span> <span class="nf">_init_zero</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="mf">0.0</span>
<span class="k">def</span> <span class="nf">_init_one</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="mf">1.0</span>
<span class="k">def</span> <span class="nf">_init_bias</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="mf">0.0</span>
<span class="k">def</span> <span class="nf">_init_gamma</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="mf">1.0</span>
<span class="k">def</span> <span class="nf">_init_beta</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="mf">0.0</span>
<span class="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="sd">"""Abstract method to Initialize weight."""</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s2">"Must override it"</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_init_default</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">_</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s1">'Unknown initialization pattern for </span><span class="si">%s</span><span class="s1">. '</span> \
<span class="s1">'Default initialization is now limited to '</span>\
<span class="s1">'"weight", "bias", "gamma" (1.0), and "beta" (0.0).'</span> \
<span class="s1">'Please use mx.sym.Variable(init=mx.init.*) to set initialization pattern'</span> <span class="o">%</span> <span class="n">name</span><span class="p">)</span></div>
<span class="c1"># pylint: disable=invalid-name</span>
<span class="n">_register</span> <span class="o">=</span> <span class="n">registry</span><span class="o">.</span><span class="n">get_register_func</span><span class="p">(</span><span class="n">Initializer</span><span class="p">,</span> <span class="s1">'initializer'</span><span class="p">)</span>
<span class="n">alias</span> <span class="o">=</span> <span class="n">registry</span><span class="o">.</span><span class="n">get_alias_func</span><span class="p">(</span><span class="n">Initializer</span><span class="p">,</span> <span class="s1">'initializer'</span><span class="p">)</span>
<span class="n">create</span> <span class="o">=</span> <span class="n">registry</span><span class="o">.</span><span class="n">get_create_func</span><span class="p">(</span><span class="n">Initializer</span><span class="p">,</span> <span class="s1">'initializer'</span><span class="p">)</span>
<span class="c1"># pylint: enable=invalid-name</span>
<div class="viewcode-block" id="register"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.register">[docs]</a><span class="k">def</span> <span class="nf">register</span><span class="p">(</span><span class="n">klass</span><span class="p">):</span>
<span class="sd">"""Registers a custom initializer.</span>
<span class="sd"> Custom initializers can be created by extending `mx.init.Initializer` and implementing the</span>
<span class="sd"> required functions like `_init_weight` and `_init_bias`. The created initializer must be</span>
<span class="sd"> registered using `mx.init.register` before it can be called by name.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> klass : class</span>
<span class="sd"> A subclass of `mx.init.Initializer` that needs to be registered as a custom initializer.</span>
<span class="sd"> Example</span>
<span class="sd"> -------</span>
<span class="sd"> >>> # Create and register a custom initializer that</span>
<span class="sd"> ... # initializes weights to 0.1 and biases to 1.</span>
<span class="sd"> ...</span>
<span class="sd"> >>> @mx.init.register</span>
<span class="sd"> ... @alias('myinit')</span>
<span class="sd"> ... class CustomInit(mx.init.Initializer):</span>
<span class="sd"> ... def __init__(self):</span>
<span class="sd"> ... super(CustomInit, self).__init__()</span>
<span class="sd"> ... def _init_weight(self, _, arr):</span>
<span class="sd"> ... arr[:] = 0.1</span>
<span class="sd"> ... def _init_bias(self, _, arr):</span>
<span class="sd"> ... arr[:] = 1</span>
<span class="sd"> ...</span>
<span class="sd"> >>> # Module is an instance of 'mxnet.module.Module'</span>
<span class="sd"> ...</span>
<span class="sd"> >>> module.init_params("custominit")</span>
<span class="sd"> >>> # module.init_params("myinit")</span>
<span class="sd"> >>> # module.init_params(CustomInit())</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="n">_register</span><span class="p">(</span><span class="n">klass</span><span class="p">)</span></div>
<div class="viewcode-block" id="Load"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Load">[docs]</a><span class="k">class</span> <span class="nc">Load</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""Initializes variables by loading data from file or dict.</span>
<span class="sd"> **Note** Load will drop ``arg:`` or ``aux:`` from name and</span>
<span class="sd"> initialize the variables that match with the prefix dropped.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> param: str or dict of str->`NDArray`</span>
<span class="sd"> Parameter file or dict mapping name to NDArray.</span>
<span class="sd"> default_init: Initializer</span>
<span class="sd"> Default initializer when name is not found in `param`.</span>
<span class="sd"> verbose: bool</span>
<span class="sd"> Flag for enabling logging of source when initializing.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">param</span><span class="p">,</span> <span class="n">default_init</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="bp">False</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="n">param</span> <span class="o">=</span> <span class="n">load</span><span class="p">(</span><span class="n">param</span><span class="p">)</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="nb">dict</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">param</span> <span class="o">=</span> <span class="p">{}</span>
<span class="k">for</span> <span class="n">name</span><span class="p">,</span> <span class="n">arr</span> <span class="ow">in</span> <span class="n">param</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="k">if</span> <span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'arg:'</span><span class="p">)</span> <span class="ow">or</span> <span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'aux:'</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">param</span><span class="p">[</span><span class="n">name</span><span class="p">[</span><span class="mi">4</span><span class="p">:]]</span> <span class="o">=</span> <span class="n">arr</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">param</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">arr</span>
<span class="bp">self</span><span class="o">.</span><span class="n">default_init</span> <span class="o">=</span> <span class="n">default_init</span>
<span class="bp">self</span><span class="o">.</span><span class="n">verbose</span> <span class="o">=</span> <span class="n">verbose</span>
<span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">param</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">arr</span><span class="o">.</span><span class="n">shape</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">param</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> \
<span class="s1">'Parameter </span><span class="si">%s</span><span class="s1"> cannot be initialized from loading. '</span><span class="o">%</span><span class="n">name</span> <span class="o">+</span> \
<span class="s1">'Shape mismatch, target </span><span class="si">%s</span><span class="s1"> vs loaded </span><span class="si">%s</span><span class="s1">'</span><span class="o">%</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">arr</span><span class="o">.</span><span class="n">shape</span><span class="p">),</span>
<span class="bp">self</span><span class="o">.</span><span class="n">param</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">param</span><span class="p">[</span><span class="n">name</span><span class="p">]</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">verbose</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Initialized </span><span class="si">%s</span><span class="s1"> by loading'</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">default_init</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">,</span> \
<span class="s2">"Cannot Initialize </span><span class="si">%s</span><span class="s2">. Not found in loaded param "</span><span class="o">%</span><span class="n">name</span> <span class="o">+</span> \
<span class="s2">"and no default Initializer is provided."</span>
<span class="bp">self</span><span class="o">.</span><span class="n">default_init</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">verbose</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Initialized </span><span class="si">%s</span><span class="s1"> by default'</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span></div>
<div class="viewcode-block" id="Mixed"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Mixed">[docs]</a><span class="k">class</span> <span class="nc">Mixed</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""Initialize parameters using multiple initializers.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> patterns: list of str</span>
<span class="sd"> List of regular expressions matching parameter names.</span>
<span class="sd"> initializers: list of Initializer</span>
<span class="sd"> List of initializers corresponding to `patterns`.</span>
<span class="sd"> Example</span>
<span class="sd"> -------</span>
<span class="sd"> >>> # Given 'module', an instance of 'mxnet.module.Module', initialize biases to zero</span>
<span class="sd"> ... # and every other parameter to random values with uniform distribution.</span>
<span class="sd"> ...</span>
<span class="sd"> >>> init = mx.initializer.Mixed(['bias', '.*'], [mx.init.Zero(), mx.init.Uniform(0.1)])</span>
<span class="sd"> >>> module.init_params(init)</span>
<span class="sd"> >>></span>
<span class="sd"> >>> for dictionary in module.get_params():</span>
<span class="sd"> ... for key in dictionary:</span>
<span class="sd"> ... print(key)</span>
<span class="sd"> ... print(dictionary[key].asnumpy())</span>
<span class="sd"> ...</span>
<span class="sd"> fullyconnected1_weight</span>
<span class="sd"> [[ 0.0097627 0.01856892 0.04303787]]</span>
<span class="sd"> fullyconnected1_bias</span>
<span class="sd"> [ 0.]</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">patterns</span><span class="p">,</span> <span class="n">initializers</span><span class="p">):</span>
<span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">patterns</span><span class="p">)</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="n">initializers</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">map</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">zip</span><span class="p">([</span><span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">p</span><span class="p">)</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">patterns</span><span class="p">],</span> <span class="n">initializers</span><span class="p">))</span>
<span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="k">for</span> <span class="n">prog</span><span class="p">,</span> <span class="n">init</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">map</span><span class="p">:</span>
<span class="k">if</span> <span class="n">prog</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">name</span><span class="p">):</span>
<span class="n">init</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">)</span>
<span class="k">return</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Parameter name </span><span class="si">%s</span><span class="s1"> did not match any pattern. Consider'</span> <span class="o">+</span>
<span class="s1">'add a ".*" pattern at the and with default Initializer.'</span><span class="p">)</span></div>
<span class="nd">@register</span>
<span class="nd">@alias</span><span class="p">(</span><span class="s2">"zeros"</span><span class="p">)</span>
<div class="viewcode-block" id="Zero"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Zero">[docs]</a><span class="k">class</span> <span class="nc">Zero</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initializes weights to zero.</span>
<span class="sd"> Example</span>
<span class="sd"> -------</span>
<span class="sd"> >>> # Given 'module', an instance of 'mxnet.module.Module', initialize weights to zero.</span>
<span class="sd"> ...</span>
<span class="sd"> >>> init = mx.initializer.Zero()</span>
<span class="sd"> >>> module.init_params(init)</span>
<span class="sd"> >>> for dictionary in module.get_params():</span>
<span class="sd"> ... for key in dictionary:</span>
<span class="sd"> ... print(key)</span>
<span class="sd"> ... print(dictionary[key].asnumpy())</span>
<span class="sd"> ...</span>
<span class="sd"> fullyconnected0_weight</span>
<span class="sd"> [[ 0. 0. 0.]]</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Zero</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="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="mi">0</span></div>
<span class="nd">@register</span>
<span class="nd">@alias</span><span class="p">(</span><span class="s2">"ones"</span><span class="p">)</span>
<div class="viewcode-block" id="One"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.One">[docs]</a><span class="k">class</span> <span class="nc">One</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initializes weights to one.</span>
<span class="sd"> Example</span>
<span class="sd"> -------</span>
<span class="sd"> >>> # Given 'module', an instance of 'mxnet.module.Module', initialize weights to one.</span>
<span class="sd"> ...</span>
<span class="sd"> >>> init = mx.initializer.One()</span>
<span class="sd"> >>> module.init_params(init)</span>
<span class="sd"> >>> for dictionary in module.get_params():</span>
<span class="sd"> ... for key in dictionary:</span>
<span class="sd"> ... print(key)</span>
<span class="sd"> ... print(dictionary[key].asnumpy())</span>
<span class="sd"> ...</span>
<span class="sd"> fullyconnected0_weight</span>
<span class="sd"> [[ 1. 1. 1.]]</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">One</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="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="mi">1</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="Constant"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Constant">[docs]</a><span class="k">class</span> <span class="nc">Constant</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initializes the weights to a scalar value.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> value : float</span>
<span class="sd"> Fill value.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Constant</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">value</span><span class="o">=</span><span class="n">value</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="n">value</span>
<span class="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">value</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="Uniform"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Uniform">[docs]</a><span class="k">class</span> <span class="nc">Uniform</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initializes weights with random values uniformly sampled from a given range.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> scale : float, optional</span>
<span class="sd"> The bound on the range of the generated random values.</span>
<span class="sd"> Values are generated from the range [-`scale`, `scale`].</span>
<span class="sd"> Default scale is 0.07.</span>
<span class="sd"> Example</span>
<span class="sd"> -------</span>
<span class="sd"> >>> # Given 'module', an instance of 'mxnet.module.Module', initialize weights</span>
<span class="sd"> >>> # to random values uniformly sampled between -0.1 and 0.1.</span>
<span class="sd"> ...</span>
<span class="sd"> >>> init = mx.init.Uniform(0.1)</span>
<span class="sd"> >>> module.init_params(init)</span>
<span class="sd"> >>> for dictionary in module.get_params():</span>
<span class="sd"> ... for key in dictionary:</span>
<span class="sd"> ... print(key)</span>
<span class="sd"> ... print(dictionary[key].asnumpy())</span>
<span class="sd"> ...</span>
<span class="sd"> fullyconnected0_weight</span>
<span class="sd"> [[ 0.01360891 -0.02144304 0.08511933]]</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="mf">0.07</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Uniform</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">scale</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">scale</span> <span class="o">=</span> <span class="n">scale</span>
<span class="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">-</span><span class="bp">self</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">scale</span><span class="p">,</span> <span class="n">out</span><span class="o">=</span><span class="n">arr</span><span class="p">)</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="Normal"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Normal">[docs]</a><span class="k">class</span> <span class="nc">Normal</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initializes weights with random values sampled from a normal distribution</span>
<span class="sd"> with a mean of zero and standard deviation of `sigma`.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> sigma : float, optional</span>
<span class="sd"> Standard deviation of the normal distribution.</span>
<span class="sd"> Default standard deviation is 0.01.</span>
<span class="sd"> Example</span>
<span class="sd"> -------</span>
<span class="sd"> >>> # Given 'module', an instance of 'mxnet.module.Module', initialize weights</span>
<span class="sd"> >>> # to random values sampled from a normal distribution.</span>
<span class="sd"> ...</span>
<span class="sd"> >>> init = mx.init.Normal(0.5)</span>
<span class="sd"> >>> module.init_params(init)</span>
<span class="sd"> >>> for dictionary in module.get_params():</span>
<span class="sd"> ... for key in dictionary:</span>
<span class="sd"> ... print(key)</span>
<span class="sd"> ... print(dictionary[key].asnumpy())</span>
<span class="sd"> ...</span>
<span class="sd"> fullyconnected0_weight</span>
<span class="sd"> [[-0.3214761 -0.12660924 0.53789419]]</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sigma</span><span class="o">=</span><span class="mf">0.01</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Normal</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">sigma</span><span class="o">=</span><span class="n">sigma</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">sigma</span> <span class="o">=</span> <span class="n">sigma</span>
<span class="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">random</span><span class="o">.</span><span class="n">normal</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">sigma</span><span class="p">,</span> <span class="n">out</span><span class="o">=</span><span class="n">arr</span><span class="p">)</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="Orthogonal"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Orthogonal">[docs]</a><span class="k">class</span> <span class="nc">Orthogonal</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initialize weight as orthogonal matrix.</span>
<span class="sd"> This initializer implements *Exact solutions to the nonlinear dynamics of</span>
<span class="sd"> learning in deep linear neural networks*, available at</span>
<span class="sd"> https://arxiv.org/abs/1312.6120.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> scale : float optional</span>
<span class="sd"> Scaling factor of weight.</span>
<span class="sd"> rand_type: string optional</span>
<span class="sd"> Use "uniform" or "normal" random number to initialize weight.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">scale</span><span class="o">=</span><span class="mf">1.414</span><span class="p">,</span> <span class="n">rand_type</span><span class="o">=</span><span class="s2">"uniform"</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Orthogonal</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">scale</span><span class="o">=</span><span class="n">scale</span><span class="p">,</span> <span class="n">rand_type</span><span class="o">=</span><span class="n">rand_type</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">scale</span> <span class="o">=</span> <span class="n">scale</span>
<span class="bp">self</span><span class="o">.</span><span class="n">rand_type</span> <span class="o">=</span> <span class="n">rand_type</span>
<span class="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">nout</span> <span class="o">=</span> <span class="n">arr</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">nin</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">prod</span><span class="p">(</span><span class="n">arr</span><span class="o">.</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="bp">self</span><span class="o">.</span><span class="n">rand_type</span> <span class="o">==</span> <span class="s2">"uniform"</span><span class="p">:</span>
<span class="n">tmp</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">-</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">,</span> <span class="p">(</span><span class="n">nout</span><span class="p">,</span> <span class="n">nin</span><span class="p">))</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">rand_type</span> <span class="o">==</span> <span class="s2">"normal"</span><span class="p">:</span>
<span class="n">tmp</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">normal</span><span class="p">(</span><span class="mf">0.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">,</span> <span class="p">(</span><span class="n">nout</span><span class="p">,</span> <span class="n">nin</span><span class="p">))</span>
<span class="n">u</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">v</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">linalg</span><span class="o">.</span><span class="n">svd</span><span class="p">(</span><span class="n">tmp</span><span class="p">,</span> <span class="n">full_matrices</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span> <span class="c1"># pylint: disable=invalid-name</span>
<span class="k">if</span> <span class="n">u</span><span class="o">.</span><span class="n">shape</span> <span class="o">==</span> <span class="n">tmp</span><span class="o">.</span><span class="n">shape</span><span class="p">:</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">u</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">v</span>
<span class="n">res</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">scale</span> <span class="o">*</span> <span class="n">res</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">arr</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="n">res</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="Xavier"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Xavier">[docs]</a><span class="k">class</span> <span class="nc">Xavier</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Returns an initializer performing "Xavier" initialization for weights.</span>
<span class="sd"> This initializer is designed to keep the scale of gradients roughly the same</span>
<span class="sd"> in all layers.</span>
<span class="sd"> By default, `rnd_type` is ``'uniform'`` and `factor_type` is ``'avg'``,</span>
<span class="sd"> the initializer fills the weights with random numbers in the range</span>
<span class="sd"> of :math:`[-c, c]`, where :math:`c = \\sqrt{\\frac{3.}{0.5 * (n_{in} + n_{out})}}`.</span>
<span class="sd"> :math:`n_{in}` is the number of neurons feeding into weights, and :math:`n_{out}` is</span>
<span class="sd"> the number of neurons the result is fed to.</span>
<span class="sd"> If `rnd_type` is ``'uniform'`` and `factor_type` is ``'in'``,</span>
<span class="sd"> the :math:`c = \\sqrt{\\frac{3.}{n_{in}}}`.</span>
<span class="sd"> Similarly when `factor_type` is ``'out'``, the :math:`c = \\sqrt{\\frac{3.}{n_{out}}}`.</span>
<span class="sd"> If `rnd_type` is ``'gaussian'`` and `factor_type` is ``'avg'``,</span>
<span class="sd"> the initializer fills the weights with numbers from normal distribution with</span>
<span class="sd"> a standard deviation of :math:`\\sqrt{\\frac{3.}{0.5 * (n_{in} + n_{out})}}`.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> rnd_type: str, optional</span>
<span class="sd"> Random generator type, can be ``'gaussian'`` or ``'uniform'``.</span>
<span class="sd"> factor_type: str, optional</span>
<span class="sd"> Can be ``'avg'``, ``'in'``, or ``'out'``.</span>
<span class="sd"> magnitude: float, optional</span>
<span class="sd"> Scale of random number.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">rnd_type</span><span class="o">=</span><span class="s2">"uniform"</span><span class="p">,</span> <span class="n">factor_type</span><span class="o">=</span><span class="s2">"avg"</span><span class="p">,</span> <span class="n">magnitude</span><span class="o">=</span><span class="mi">3</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Xavier</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">rnd_type</span><span class="o">=</span><span class="n">rnd_type</span><span class="p">,</span> <span class="n">factor_type</span><span class="o">=</span><span class="n">factor_type</span><span class="p">,</span>
<span class="n">magnitude</span><span class="o">=</span><span class="n">magnitude</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">rnd_type</span> <span class="o">=</span> <span class="n">rnd_type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">factor_type</span> <span class="o">=</span> <span class="n">factor_type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">magnitude</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">magnitude</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">shape</span> <span class="o">=</span> <span class="n">arr</span><span class="o">.</span><span class="n">shape</span>
<span class="n">hw_scale</span> <span class="o">=</span> <span class="mf">1.</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">shape</span><span class="p">)</span> <span class="o"><</span> <span class="mi">2</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Xavier initializer cannot be applied to vector {0}. It requires at'</span>
<span class="s1">' least 2D.'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="p">))</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">shape</span><span class="p">)</span> <span class="o">></span> <span class="mi">2</span><span class="p">:</span>
<span class="n">hw_scale</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">prod</span><span class="p">(</span><span class="n">shape</span><span class="p">[</span><span class="mi">2</span><span class="p">:])</span>
<span class="n">fan_in</span><span class="p">,</span> <span class="n">fan_out</span> <span class="o">=</span> <span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">hw_scale</span><span class="p">,</span> <span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">hw_scale</span>
<span class="n">factor</span> <span class="o">=</span> <span class="mf">1.</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">factor_type</span> <span class="o">==</span> <span class="s2">"avg"</span><span class="p">:</span>
<span class="n">factor</span> <span class="o">=</span> <span class="p">(</span><span class="n">fan_in</span> <span class="o">+</span> <span class="n">fan_out</span><span class="p">)</span> <span class="o">/</span> <span class="mf">2.0</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">factor_type</span> <span class="o">==</span> <span class="s2">"in"</span><span class="p">:</span>
<span class="n">factor</span> <span class="o">=</span> <span class="n">fan_in</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">factor_type</span> <span class="o">==</span> <span class="s2">"out"</span><span class="p">:</span>
<span class="n">factor</span> <span class="o">=</span> <span class="n">fan_out</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">"Incorrect factor type"</span><span class="p">)</span>
<span class="n">scale</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">magnitude</span> <span class="o">/</span> <span class="n">factor</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">rnd_type</span> <span class="o">==</span> <span class="s2">"uniform"</span><span class="p">:</span>
<span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">-</span><span class="n">scale</span><span class="p">,</span> <span class="n">scale</span><span class="p">,</span> <span class="n">out</span><span class="o">=</span><span class="n">arr</span><span class="p">)</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">rnd_type</span> <span class="o">==</span> <span class="s2">"gaussian"</span><span class="p">:</span>
<span class="n">random</span><span class="o">.</span><span class="n">normal</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">scale</span><span class="p">,</span> <span class="n">out</span><span class="o">=</span><span class="n">arr</span><span class="p">)</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">"Unknown random type"</span><span class="p">)</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="MSRAPrelu"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.MSRAPrelu">[docs]</a><span class="k">class</span> <span class="nc">MSRAPrelu</span><span class="p">(</span><span class="n">Xavier</span><span class="p">):</span>
<span class="sd">"""Initialize the weight according to a MSRA paper.</span>
<span class="sd"> This initializer implements *Delving Deep into Rectifiers: Surpassing</span>
<span class="sd"> Human-Level Performance on ImageNet Classification*, available at</span>
<span class="sd"> https://arxiv.org/abs/1502.01852.</span>
<span class="sd"> This initializer is proposed for initialization related to ReLu activation,</span>
<span class="sd"> it maked some changes on top of Xavier method.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> factor_type: str, optional</span>
<span class="sd"> Can be ``'avg'``, ``'in'``, or ``'out'``.</span>
<span class="sd"> slope: float, optional</span>
<span class="sd"> initial slope of any PReLU (or similar) nonlinearities.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">factor_type</span><span class="o">=</span><span class="s2">"avg"</span><span class="p">,</span> <span class="n">slope</span><span class="o">=</span><span class="mf">0.25</span><span class="p">):</span>
<span class="n">magnitude</span> <span class="o">=</span> <span class="mf">2.</span> <span class="o">/</span> <span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="n">slope</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">MSRAPrelu</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="s2">"gaussian"</span><span class="p">,</span> <span class="n">factor_type</span><span class="p">,</span> <span class="n">magnitude</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">'factor_type'</span><span class="p">:</span> <span class="n">factor_type</span><span class="p">,</span> <span class="s1">'slope'</span><span class="p">:</span> <span class="n">slope</span><span class="p">}</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="Bilinear"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.Bilinear">[docs]</a><span class="k">class</span> <span class="nc">Bilinear</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initialize weight for upsampling layers."""</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Bilinear</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="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">weight</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">prod</span><span class="p">(</span><span class="n">arr</span><span class="o">.</span><span class="n">shape</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">shape</span> <span class="o">=</span> <span class="n">arr</span><span class="o">.</span><span class="n">shape</span>
<span class="n">f</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">ceil</span><span class="p">(</span><span class="n">shape</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span> <span class="o">/</span> <span class="mf">2.</span><span class="p">)</span>
<span class="n">c</span> <span class="o">=</span> <span class="p">(</span><span class="mi">2</span> <span class="o">*</span> <span class="n">f</span> <span class="o">-</span> <span class="mi">1</span> <span class="o">-</span> <span class="n">f</span> <span class="o">%</span> <span class="mi">2</span><span class="p">)</span> <span class="o">/</span> <span class="p">(</span><span class="mf">2.</span> <span class="o">*</span> <span class="n">f</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">prod</span><span class="p">(</span><span class="n">shape</span><span class="p">)):</span>
<span class="n">x</span> <span class="o">=</span> <span class="n">i</span> <span class="o">%</span> <span class="n">shape</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span>
<span class="n">y</span> <span class="o">=</span> <span class="p">(</span><span class="n">i</span> <span class="o">/</span> <span class="n">shape</span><span class="p">[</span><span class="mi">3</span><span class="p">])</span> <span class="o">%</span> <span class="n">shape</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
<span class="n">weight</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="nb">abs</span><span class="p">(</span><span class="n">x</span> <span class="o">/</span> <span class="n">f</span> <span class="o">-</span> <span class="n">c</span><span class="p">))</span> <span class="o">*</span> <span class="p">(</span><span class="mi">1</span> <span class="o">-</span> <span class="nb">abs</span><span class="p">(</span><span class="n">y</span> <span class="o">/</span> <span class="n">f</span> <span class="o">-</span> <span class="n">c</span><span class="p">))</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="n">weight</span><span class="o">.</span><span class="n">reshape</span><span class="p">(</span><span class="n">shape</span><span class="p">)</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="LSTMBias"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.LSTMBias">[docs]</a><span class="k">class</span> <span class="nc">LSTMBias</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initialize all bias of an LSTMCell to 0.0 except for</span>
<span class="sd"> the forget gate whose bias is set to custom value.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> forget_bias: float, default 1.0</span>
<span class="sd"> bias for the forget gate. Jozefowicz et al. 2015 recommends</span>
<span class="sd"> setting this to 1.0.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">forget_bias</span><span class="o">=</span><span class="mf">1.0</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">LSTMBias</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">forget_bias</span><span class="o">=</span><span class="n">forget_bias</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">forget_bias</span> <span class="o">=</span> <span class="n">forget_bias</span>
<span class="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="mf">0.0</span>
<span class="c1"># in the case of LSTMCell the forget gate is the second</span>
<span class="c1"># gate of the 4 LSTM gates, we modify the according values.</span>
<span class="n">num_hidden</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">arr</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">/</span> <span class="mi">4</span><span class="p">)</span>
<span class="n">arr</span><span class="p">[</span><span class="n">num_hidden</span><span class="p">:</span><span class="mi">2</span><span class="o">*</span><span class="n">num_hidden</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">forget_bias</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="FusedRNN"><a class="viewcode-back" href="../../api/python/optimization/optimization.html#mxnet.initializer.FusedRNN">[docs]</a><span class="k">class</span> <span class="nc">FusedRNN</span><span class="p">(</span><span class="n">Initializer</span><span class="p">):</span>
<span class="sd">"""Initialize parameters for fused rnn layers.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> init : Initializer</span>
<span class="sd"> initializer applied to unpacked weights. Fall back to global</span>
<span class="sd"> initializer if None.</span>
<span class="sd"> num_hidden : int</span>
<span class="sd"> should be the same with arguments passed to FusedRNNCell.</span>
<span class="sd"> num_layers : int</span>
<span class="sd"> should be the same with arguments passed to FusedRNNCell.</span>
<span class="sd"> mode : str</span>
<span class="sd"> should be the same with arguments passed to FusedRNNCell.</span>
<span class="sd"> bidirectional : bool</span>
<span class="sd"> should be the same with arguments passed to FusedRNNCell.</span>
<span class="sd"> forget_bias : float</span>
<span class="sd"> should be the same with arguments passed to FusedRNNCell.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">init</span><span class="p">,</span> <span class="n">num_hidden</span><span class="p">,</span> <span class="n">num_layers</span><span class="p">,</span> <span class="n">mode</span><span class="p">,</span> <span class="n">bidirectional</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">forget_bias</span><span class="o">=</span><span class="mf">1.0</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">init</span><span class="p">,</span> <span class="n">string_types</span><span class="p">):</span>
<span class="n">klass</span><span class="p">,</span> <span class="n">kwargs</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">init</span><span class="p">)</span>
<span class="n">init</span> <span class="o">=</span> <span class="n">_INITIALIZER_REGISTRY</span><span class="p">[</span><span class="n">klass</span><span class="o">.</span><span class="n">lower</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">FusedRNN</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">init</span><span class="o">=</span><span class="n">init</span><span class="o">.</span><span class="n">dumps</span><span class="p">()</span> <span class="k">if</span> <span class="n">init</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span> <span class="k">else</span> <span class="bp">None</span><span class="p">,</span>
<span class="n">num_hidden</span><span class="o">=</span><span class="n">num_hidden</span><span class="p">,</span> <span class="n">num_layers</span><span class="o">=</span><span class="n">num_layers</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="n">mode</span><span class="p">,</span>
<span class="n">bidirectional</span><span class="o">=</span><span class="n">bidirectional</span><span class="p">,</span> <span class="n">forget_bias</span><span class="o">=</span><span class="n">forget_bias</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_init</span> <span class="o">=</span> <span class="n">init</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_hidden</span> <span class="o">=</span> <span class="n">num_hidden</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span> <span class="o">=</span> <span class="n">num_layers</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mode</span> <span class="o">=</span> <span class="n">mode</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bidirectional</span> <span class="o">=</span> <span class="n">bidirectional</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_forget_bias</span> <span class="o">=</span> <span class="n">forget_bias</span>
<span class="k">def</span> <span class="nf">_init_weight</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">desc</span><span class="p">,</span> <span class="n">arr</span><span class="p">):</span> <span class="c1"># pylint: disable=arguments-differ</span>
<span class="kn">from</span> <span class="nn">.rnn</span> <span class="kn">import</span> <span class="n">rnn_cell</span>
<span class="n">cell</span> <span class="o">=</span> <span class="n">rnn_cell</span><span class="o">.</span><span class="n">FusedRNNCell</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_hidden</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_mode</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bidirectional</span><span class="p">,</span>
<span class="n">forget_bias</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_forget_bias</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="s1">''</span><span class="p">)</span>
<span class="n">args</span> <span class="o">=</span> <span class="n">cell</span><span class="o">.</span><span class="n">unpack_weights</span><span class="p">({</span><span class="s1">'parameters'</span><span class="p">:</span> <span class="n">arr</span><span class="p">})</span>
<span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">args</span><span class="p">:</span>
<span class="n">arg_desc</span> <span class="o">=</span> <span class="n">InitDesc</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">global_init</span><span class="o">=</span><span class="n">desc</span><span class="o">.</span><span class="n">global_init</span><span class="p">)</span>
<span class="c1"># for lstm bias, we use a custom initializer</span>
<span class="c1"># which adds a bias to the forget gate</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mode</span> <span class="o">==</span> <span class="s1">'lstm'</span> <span class="ow">and</span> <span class="n">name</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s2">"_f_bias"</span><span class="p">):</span>
<span class="n">args</span><span class="p">[</span><span class="n">name</span><span class="p">][:]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_forget_bias</span>
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_init</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">desc</span><span class="o">.</span><span class="n">global_init</span><span class="p">(</span><span class="n">arg_desc</span><span class="p">,</span> <span class="n">args</span><span class="p">[</span><span class="n">name</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">_init</span><span class="p">(</span><span class="n">arg_desc</span><span class="p">,</span> <span class="n">args</span><span class="p">[</span><span class="n">name</span><span class="p">])</span>
<span class="n">arr</span><span class="p">[:]</span> <span class="o">=</span> <span class="n">cell</span><span class="o">.</span><span class="n">pack_weights</span><span class="p">(</span><span class="n">args</span><span class="p">)[</span><span class="s1">'parameters'</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, 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>