Google Git
Sign in
apache / mxnet-site / 5d2e45b9c41410156d7d50982069a8e0f3991694 / . / versions / 1.1.0 / _modules / mxnet / gluon / rnn / rnn_layer.html
blob: 34804e830107ea1fe27ec6f050d0d5961353be95 [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"/>
<meta content="mxnet.gluon.rnn.rnn_layer" property="og:title">
<meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image">
<meta content="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/og-logo.png" property="og:image:secure_url">
<meta content="mxnet.gluon.rnn.rnn_layer" property="og:description"/>
<title>mxnet.gluon.rnn.rnn_layer — mxnet documentation</title>
<link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/>
<link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/>
<link href="../../../../_static/basic.css" rel="stylesheet" type="text/css">
<link href="../../../../_static/pygments.css" rel="stylesheet" type="text/css">
<link href="../../../../_static/mxnet.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../../../',
VERSION: '',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</script>
<script src="https://code.jquery.com/jquery-1.11.1.min.js" type="text/javascript"></script>
<script src="../../../../_static/underscore.js" type="text/javascript"></script>
<script src="../../../../_static/searchtools_custom.js" type="text/javascript"></script>
<script src="../../../../_static/doctools.js" type="text/javascript"></script>
<script src="../../../../_static/selectlang.js" type="text/javascript"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script>
<script type="text/javascript"> jQuery(function() { Search.loadIndex("/versions/1.1.0/searchindex.js"); Search.init();}); </script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new
Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-96378503-1', 'auto');
ga('send', 'pageview');
</script>
<!-- -->
<!-- <script type="text/javascript" src="../../../../_static/jquery.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="../../../../_static/underscore.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="../../../../_static/doctools.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> -->
<!-- -->
<link href="../../../../genindex.html" rel="index" title="Index">
<link href="../../../../search.html" rel="search" title="Search"/>
<link href="../../../index.html" rel="up" title="Module code"/>
<link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/>
</link></link></link></meta></meta></meta></head>
<body background="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-background-compressed.jpeg" role="document">
<div class="content-block"><div class="navbar navbar-fixed-top">
<div class="container" id="navContainer">
<div class="innder" id="header-inner">
<h1 id="logo-wrap">
<a href="../../../../" id="logo"><img src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet_logo.png"/></a>
</h1>
<nav class="nav-bar" id="main-nav">
<a class="main-nav-link" href="/versions/1.1.0/install/index.html">Install</a>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="/versions/1.1.0/tutorials/gluon/gluon.html">About</a></li>
<li><a class="main-nav-link" href="https://www.d2l.ai/">Dive into Deep Learning</a></li>
<li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li>
<li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li>
</ul>
</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="/versions/1.1.0/api/python/index.html">Python</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/perl/index.html">Perl</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/scala/index.html">Scala</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor-docs">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs">
<li><a class="main-nav-link" href="/versions/1.1.0/faq/index.html">FAQ</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/tutorials/index.html">Tutorials</a>
<li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/v1.1.0/example">Examples</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home">Developer Wiki</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/model_zoo/index.html">Model Zoo</a></li>
<li><a class="main-nav-link" href="https://github.com/onnx/onnx-mxnet">ONNX</a></li>
</li></ul>
</span>
<span id="dropdown-menu-position-anchor-community">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-community">
<li><a class="main-nav-link" href="http://discuss.mxnet.io">Forum</a></li>
<li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/v1.1.0">Github</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/community/contribute.html">Contribute</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/community/powered_by.html">Powered By</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">1.1.0<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a href="/">master</a></li><li><a href="/versions/1.7.0/">1.7.0</a></li><li><a href=/versions/1.6.0/>1.6.0</a></li><li><a href=/versions/1.5.0/>1.5.0</a></li><li><a href=/versions/1.4.1/>1.4.1</a></li><li><a href=/versions/1.3.1/>1.3.1</a></li><li><a href=/versions/1.2.1/>1.2.1</a></li><li><a href=/versions/1.1.0/>1.1.0</a></li><li><a href=/versions/1.0.0/>1.0.0</a></li><li><a href=/versions/0.12.1/>0.12.1</a></li><li><a href=/versions/0.11.0/>0.11.0</a></li></ul></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="/versions/1.1.0/install/index.html">Install</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/tutorials/index.html">Tutorials</a></li>
<li class="dropdown-submenu dropdown">
<a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Gluon</a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="/versions/1.1.0/tutorials/gluon/gluon.html">About</a></li>
<li><a class="main-nav-link" href="http://gluon.mxnet.io">The Straight Dope (Tutorials)</a></li>
<li><a class="main-nav-link" href="https://gluon-cv.mxnet.io">GluonCV Toolkit</a></li>
<li><a class="main-nav-link" href="https://gluon-nlp.mxnet.io/">GluonNLP Toolkit</a></li>
</ul>
</li>
<li class="dropdown-submenu">
<a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">API</a>
<ul class="dropdown-menu">
<li><a class="main-nav-link" href="/versions/1.1.0/api/python/index.html">Python</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/perl/index.html">Perl</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="/versions/1.1.0/api/scala/index.html">Scala</a></li>
</ul>
</li>
<li class="dropdown-submenu">
<a aria-expanded="true" aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" tabindex="-1">Docs</a>
<ul class="dropdown-menu">
<li><a href="/versions/1.1.0/faq/index.html" tabindex="-1">FAQ</a></li>
<li><a href="/versions/1.1.0/tutorials/index.html" tabindex="-1">Tutorials</a></li>
<li><a href="https://github.com/apache/incubator-mxnet/tree/v1.1.0/example" tabindex="-1">Examples</a></li>
<li><a href="/versions/1.1.0/architecture/index.html" tabindex="-1">Architecture</a></li>
<li><a href="https://cwiki.apache.org/confluence/display/MXNET/Apache+MXNet+Home" tabindex="-1">Developer Wiki</a></li>
<li><a href="/versions/1.1.0/model_zoo/index.html" tabindex="-1">Gluon Model Zoo</a></li>
<li><a href="https://github.com/onnx/onnx-mxnet" tabindex="-1">ONNX</a></li>
</ul>
</li>
<li class="dropdown-submenu dropdown">
<a aria-haspopup="true" class="dropdown-toggle burger-link" data-toggle="dropdown" href="#" role="button" tabindex="-1">Community</a>
<ul class="dropdown-menu">
<li><a href="http://discuss.mxnet.io" tabindex="-1">Forum</a></li>
<li><a href="https://github.com/apache/incubator-mxnet/tree/v1.1.0" tabindex="-1">Github</a></li>
<li><a href="/versions/1.1.0/community/contribute.html" tabindex="-1">Contribute</a></li>
<li><a href="/versions/1.1.0/community/powered_by.html" tabindex="-1">Powered By</a></li>
</ul>
</li>
<li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">1.1.0</a><ul class="dropdown-menu"><li><a tabindex="-1" href=/>master</a></li><li><a tabindex="-1" href=/versions/1.6.0/>1.6.0</a></li><li><a tabindex="-1" href=/versions/1.5.0/>1.5.0</a></li><li><a tabindex="-1" href=/versions/1.4.1/>1.4.1</a></li><li><a tabindex="-1" href=/versions/1.3.1/>1.3.1</a></li><li><a tabindex="-1" href=/versions/1.2.1/>1.2.1</a></li><li><a tabindex="-1" href=/versions/1.1.0/>1.1.0</a></li><li><a tabindex="-1" href=/versions/1.0.0/>1.0.0</a></li><li><a tabindex="-1" href=/versions/0.12.1/>0.12.1</a></li><li><a tabindex="-1" href=/versions/0.11.0/>0.11.0</a></li></ul></li></ul>
</div>
<div class="plusIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"><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.gluon.rnn.rnn_layer</h1><div class="highlight"><pre>
<span></span><span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
<span class="c1"># distributed with this work for additional information</span>
<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># "License"); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="c1"># coding: utf-8</span>
<span class="c1"># pylint: disable=no-member, invalid-name, protected-access, no-self-use</span>
<span class="c1"># pylint: disable=too-many-branches, too-many-arguments, no-self-use</span>
<span class="c1"># pylint: disable=too-many-lines, arguments-differ</span>
<span class="sd">"""Definition of various recurrent neural network layers."""</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">print_function</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'RNN'</span><span class="p">,</span> <span class="s1">'LSTM'</span><span class="p">,</span> <span class="s1">'GRU'</span><span class="p">]</span>
<span class="kn">from</span> <span class="nn">...</span> <span class="k">import</span> <span class="n">ndarray</span>
<span class="kn">from</span> <span class="nn">..</span> <span class="k">import</span> <span class="n">Block</span>
<span class="kn">from</span> <span class="nn">.</span> <span class="k">import</span> <span class="n">rnn_cell</span>
<span class="k">class</span> <span class="nc">_RNNLayer</span><span class="p">(</span><span class="n">Block</span><span class="p">):</span>
<span class="sd">"""Implementation of recurrent layers."""</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">num_layers</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span>
<span class="n">dropout</span><span class="p">,</span> <span class="n">bidirectional</span><span class="p">,</span> <span class="n">input_size</span><span class="p">,</span>
<span class="n">i2h_weight_initializer</span><span class="p">,</span> <span class="n">h2h_weight_initializer</span><span class="p">,</span>
<span class="n">i2h_bias_initializer</span><span class="p">,</span> <span class="n">h2h_bias_initializer</span><span class="p">,</span>
<span class="n">mode</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">_RNNLayer</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'TNC'</span> <span class="ow">or</span> <span class="n">layout</span> <span class="o">==</span> <span class="s1">'NTC'</span><span class="p">,</span> \
<span class="s2">"Invalid layout </span><span class="si">%s</span><span class="s2">; must be one of ['TNC' or 'NTC']"</span><span class="o">%</span><span class="n">layout</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</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">_layout</span> <span class="o">=</span> <span class="n">layout</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_dropout</span> <span class="o">=</span> <span class="n">dropout</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_dir</span> <span class="o">=</span> <span class="mi">2</span> <span class="k">if</span> <span class="n">bidirectional</span> <span class="k">else</span> <span class="mi">1</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_input_size</span> <span class="o">=</span> <span class="n">input_size</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_i2h_weight_initializer</span> <span class="o">=</span> <span class="n">i2h_weight_initializer</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_h2h_weight_initializer</span> <span class="o">=</span> <span class="n">h2h_weight_initializer</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_i2h_bias_initializer</span> <span class="o">=</span> <span class="n">i2h_bias_initializer</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_h2h_bias_initializer</span> <span class="o">=</span> <span class="n">h2h_bias_initializer</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_gates</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'rnn_relu'</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> <span class="s1">'rnn_tanh'</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> <span class="s1">'lstm'</span><span class="p">:</span> <span class="mi">4</span><span class="p">,</span> <span class="s1">'gru'</span><span class="p">:</span> <span class="mi">3</span><span class="p">}[</span><span class="n">mode</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">i2h_weight</span> <span class="o">=</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">h2h_weight</span> <span class="o">=</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">i2h_bias</span> <span class="o">=</span> <span class="p">[]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">h2h_bias</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">ng</span><span class="p">,</span> <span class="n">ni</span><span class="p">,</span> <span class="n">nh</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_gates</span><span class="p">,</span> <span class="n">input_size</span><span class="p">,</span> <span class="n">hidden_size</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">num_layers</span><span class="p">):</span>
<span class="k">for</span> <span class="n">j</span> <span class="ow">in</span> <span class="p">([</span><span class="s1">'l'</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">]</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span> <span class="o">==</span> <span class="mi">2</span> <span class="k">else</span> <span class="p">[</span><span class="s1">'l'</span><span class="p">]):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">i2h_weight</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'</span><span class="si">%s%d</span><span class="s1">_i2h_weight'</span><span class="o">%</span><span class="p">(</span><span class="n">j</span><span class="p">,</span> <span class="n">i</span><span class="p">),</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">ng</span><span class="o">*</span><span class="n">nh</span><span class="p">,</span> <span class="n">ni</span><span class="p">),</span>
<span class="n">init</span><span class="o">=</span><span class="n">i2h_weight_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">h2h_weight</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'</span><span class="si">%s%d</span><span class="s1">_h2h_weight'</span><span class="o">%</span><span class="p">(</span><span class="n">j</span><span class="p">,</span> <span class="n">i</span><span class="p">),</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">ng</span><span class="o">*</span><span class="n">nh</span><span class="p">,</span> <span class="n">nh</span><span class="p">),</span>
<span class="n">init</span><span class="o">=</span><span class="n">h2h_weight_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">i2h_bias</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'</span><span class="si">%s%d</span><span class="s1">_i2h_bias'</span><span class="o">%</span><span class="p">(</span><span class="n">j</span><span class="p">,</span> <span class="n">i</span><span class="p">),</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">ng</span><span class="o">*</span><span class="n">nh</span><span class="p">,),</span>
<span class="n">init</span><span class="o">=</span><span class="n">i2h_bias_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">h2h_bias</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'</span><span class="si">%s%d</span><span class="s1">_h2h_bias'</span><span class="o">%</span><span class="p">(</span><span class="n">j</span><span class="p">,</span> <span class="n">i</span><span class="p">),</span> <span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">ng</span><span class="o">*</span><span class="n">nh</span><span class="p">,),</span>
<span class="n">init</span><span class="o">=</span><span class="n">h2h_bias_initializer</span><span class="p">,</span>
<span class="n">allow_deferred_init</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
<span class="n">ni</span> <span class="o">=</span> <span class="n">nh</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_unfused</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_unfuse</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="n">s</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{name}</span><span class="s1">(</span><span class="si">{mapping}</span><span class="s1">, </span><span class="si">{_layout}</span><span class="s1">'</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">', num_layers=</span><span class="si">{_num_layers}</span><span class="s1">'</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dropout</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">', dropout=</span><span class="si">{_dropout}</span><span class="s1">'</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">', bidirectional'</span>
<span class="n">s</span> <span class="o">+=</span> <span class="s1">')'</span>
<span class="n">shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">i2h_weight</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span>
<span class="n">mapping</span> <span class="o">=</span> <span class="s1">'</span><span class="si">{0}</span><span class="s1"> -> </span><span class="si">{1}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">if</span> <span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span> <span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
<span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span>
<span class="n">mapping</span><span class="o">=</span><span class="n">mapping</span><span class="p">,</span>
<span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">state_info</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span>
<span class="k">def</span> <span class="nf">_unfuse</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Unfuses the fused RNN in to a stack of rnn cells."""</span>
<span class="n">get_cell</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'rnn_relu'</span><span class="p">:</span> <span class="k">lambda</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">rnn_cell</span><span class="o">.</span><span class="n">RNNCell</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">,</span>
<span class="n">activation</span><span class="o">=</span><span class="s1">'relu'</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">),</span>
<span class="s1">'rnn_tanh'</span><span class="p">:</span> <span class="k">lambda</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">rnn_cell</span><span class="o">.</span><span class="n">RNNCell</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">,</span>
<span class="n">activation</span><span class="o">=</span><span class="s1">'tanh'</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">),</span>
<span class="s1">'lstm'</span><span class="p">:</span> <span class="k">lambda</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">rnn_cell</span><span class="o">.</span><span class="n">LSTMCell</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">,</span>
<span class="o">**</span><span class="n">kwargs</span><span class="p">),</span>
<span class="s1">'gru'</span><span class="p">:</span> <span class="k">lambda</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="n">rnn_cell</span><span class="o">.</span><span class="n">GRUCell</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</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">_mode</span><span class="p">]</span>
<span class="n">stack</span> <span class="o">=</span> <span class="n">rnn_cell</span><span class="o">.</span><span class="n">SequentialRNNCell</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">prefix</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">params</span><span class="p">)</span>
<span class="k">with</span> <span class="n">stack</span><span class="o">.</span><span class="n">name_scope</span><span class="p">():</span>
<span class="n">ni</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_size</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="bp">self</span><span class="o">.</span><span class="n">_num_layers</span><span class="p">):</span>
<span class="n">kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'input_size'</span><span class="p">:</span> <span class="n">ni</span><span class="p">,</span>
<span class="s1">'i2h_weight_initializer'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_i2h_weight_initializer</span><span class="p">,</span>
<span class="s1">'h2h_weight_initializer'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_h2h_weight_initializer</span><span class="p">,</span>
<span class="s1">'i2h_bias_initializer'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_i2h_bias_initializer</span><span class="p">,</span>
<span class="s1">'h2h_bias_initializer'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_h2h_bias_initializer</span><span class="p">}</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
<span class="n">stack</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">rnn_cell</span><span class="o">.</span><span class="n">BidirectionalCell</span><span class="p">(</span>
<span class="n">get_cell</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="s1">'l</span><span class="si">%d</span><span class="s1">_'</span><span class="o">%</span><span class="n">i</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">),</span>
<span class="n">get_cell</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="s1">'r</span><span class="si">%d</span><span class="s1">_'</span><span class="o">%</span><span class="n">i</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">stack</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">get_cell</span><span class="p">(</span><span class="n">prefix</span><span class="o">=</span><span class="s1">'l</span><span class="si">%d</span><span class="s1">_'</span><span class="o">%</span><span class="n">i</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">))</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dropout</span> <span class="o">></span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">i</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">stack</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">rnn_cell</span><span class="o">.</span><span class="n">DropoutCell</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_dropout</span><span class="p">))</span>
<span class="n">ni</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span>
<span class="k">return</span> <span class="n">stack</span>
<span class="k">def</span> <span class="nf">begin_state</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">func</span><span class="o">=</span><span class="n">ndarray</span><span class="o">.</span><span class="n">zeros</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">"""Initial state for this cell.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> batch_size: int</span>
<span class="sd"> Only required for `NDArray` API. Size of the batch ('N' in layout).</span>
<span class="sd"> Dimension of the input.</span>
<span class="sd"> func : callable, default `ndarray.zeros`</span>
<span class="sd"> Function for creating initial state.</span>
<span class="sd"> For Symbol API, func can be `symbol.zeros`, `symbol.uniform`,</span>
<span class="sd"> `symbol.var` etc. Use `symbol.var` if you want to directly</span>
<span class="sd"> feed input as states.</span>
<span class="sd"> For NDArray API, func can be `ndarray.zeros`, `ndarray.ones`, etc.</span>
<span class="sd"> **kwargs :</span>
<span class="sd"> Additional keyword arguments passed to func. For example</span>
<span class="sd"> `mean`, `std`, `dtype`, etc.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> states : nested list of Symbol</span>
<span class="sd"> Starting states for the first RNN step.</span>
<span class="sd"> """</span>
<span class="n">states</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">info</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">state_info</span><span class="p">(</span><span class="n">batch_size</span><span class="p">)):</span>
<span class="k">if</span> <span class="n">info</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">info</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">info</span> <span class="o">=</span> <span class="n">kwargs</span>
<span class="n">states</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">func</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">'</span><span class="si">%s</span><span class="s1">h0_</span><span class="si">%d</span><span class="s1">'</span><span class="o">%</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">prefix</span><span class="p">,</span> <span class="n">i</span><span class="p">),</span> <span class="o">**</span><span class="n">info</span><span class="p">))</span>
<span class="k">return</span> <span class="n">states</span>
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">inputs</span><span class="p">,</span> <span class="n">states</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="n">batch_size</span> <span class="o">=</span> <span class="n">inputs</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">_layout</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'N'</span><span class="p">)]</span>
<span class="n">skip_states</span> <span class="o">=</span> <span class="n">states</span> <span class="ow">is</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">skip_states</span><span class="p">:</span>
<span class="n">states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">begin_state</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">inputs</span><span class="o">.</span><span class="n">context</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">states</span><span class="p">,</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">NDArray</span><span class="p">):</span>
<span class="n">states</span> <span class="o">=</span> <span class="p">[</span><span class="n">states</span><span class="p">]</span>
<span class="k">for</span> <span class="n">state</span><span class="p">,</span> <span class="n">info</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">states</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_info</span><span class="p">(</span><span class="n">batch_size</span><span class="p">)):</span>
<span class="k">if</span> <span class="n">state</span><span class="o">.</span><span class="n">shape</span> <span class="o">!=</span> <span class="n">info</span><span class="p">[</span><span class="s1">'shape'</span><span class="p">]:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"Invalid recurrent state shape. Expecting </span><span class="si">%s</span><span class="s2">, got </span><span class="si">%s</span><span class="s2">."</span><span class="o">%</span><span class="p">(</span>
<span class="nb">str</span><span class="p">(</span><span class="n">info</span><span class="p">[</span><span class="s1">'shape'</span><span class="p">]),</span> <span class="nb">str</span><span class="p">(</span><span class="n">state</span><span class="o">.</span><span class="n">shape</span><span class="p">)))</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_size</span> <span class="o">==</span> <span class="mi">0</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="bp">self</span><span class="o">.</span><span class="n">_dir</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">i2h_weight</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">shape</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_gates</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">,</span> <span class="n">inputs</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="bp">self</span><span class="o">.</span><span class="n">i2h_weight</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">_finish_deferred_init</span><span class="p">()</span>
<span class="k">if</span> <span class="n">inputs</span><span class="o">.</span><span class="n">context</span><span class="o">.</span><span class="n">device_type</span> <span class="o">==</span> <span class="s1">'gpu'</span><span class="p">:</span>
<span class="n">out</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_forward_gpu</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">states</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">out</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_forward_cpu</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">states</span><span class="p">)</span>
<span class="c1"># out is (output, state)</span>
<span class="k">return</span> <span class="n">out</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">if</span> <span class="n">skip_states</span> <span class="k">else</span> <span class="n">out</span>
<span class="k">def</span> <span class="nf">_forward_cpu</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">inputs</span><span class="p">,</span> <span class="n">states</span><span class="p">):</span>
<span class="n">ns</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">states</span><span class="p">)</span>
<span class="n">axis</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_layout</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'T'</span><span class="p">)</span>
<span class="n">states</span> <span class="o">=</span> <span class="nb">sum</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="p">((</span><span class="n">j</span> <span class="k">for</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">states</span><span class="p">)),</span> <span class="p">())</span>
<span class="n">outputs</span><span class="p">,</span> <span class="n">states</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_unfused</span><span class="o">.</span><span class="n">unroll</span><span class="p">(</span>
<span class="n">inputs</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="n">axis</span><span class="p">],</span> <span class="n">inputs</span><span class="p">,</span> <span class="n">states</span><span class="p">,</span>
<span class="n">layout</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_layout</span><span class="p">,</span> <span class="n">merge_outputs</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">new_states</span> <span class="o">=</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">ns</span><span class="p">):</span>
<span class="n">state</span> <span class="o">=</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span><span class="o">*</span><span class="p">(</span><span class="n">j</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="mi">1</span><span class="p">,)</span><span class="o">+</span><span class="n">j</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="k">for</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">states</span><span class="p">[</span><span class="n">i</span><span class="p">::</span><span class="n">ns</span><span class="p">]),</span> <span class="n">dim</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="n">new_states</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">state</span><span class="p">)</span>
<span class="k">return</span> <span class="n">outputs</span><span class="p">,</span> <span class="n">new_states</span>
<span class="k">def</span> <span class="nf">_forward_gpu</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">inputs</span><span class="p">,</span> <span class="n">states</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_layout</span> <span class="o">==</span> <span class="s1">'NTC'</span><span class="p">:</span>
<span class="n">inputs</span> <span class="o">=</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">dim1</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">dim2</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="n">ctx</span> <span class="o">=</span> <span class="n">inputs</span><span class="o">.</span><span class="n">context</span>
<span class="n">params</span> <span class="o">=</span> <span class="nb">sum</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">i2h_weight</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">h2h_weight</span><span class="p">),</span> <span class="p">())</span>
<span class="n">params</span> <span class="o">+=</span> <span class="nb">sum</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">i2h_bias</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">h2h_bias</span><span class="p">),</span> <span class="p">())</span>
<span class="n">params</span> <span class="o">=</span> <span class="p">(</span><span class="n">i</span><span class="o">.</span><span class="n">data</span><span class="p">(</span><span class="n">ctx</span><span class="p">)</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="o">-</span><span class="mi">1</span><span class="p">,))</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">params</span><span class="p">)</span>
<span class="n">params</span> <span class="o">=</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span><span class="o">*</span><span class="n">params</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="n">rnn</span> <span class="o">=</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">RNN</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">params</span><span class="p">,</span> <span class="o">*</span><span class="n">states</span><span class="p">,</span> <span class="n">state_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">,</span>
<span class="n">num_layers</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span><span class="p">,</span> <span class="n">bidirectional</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_dir</span> <span class="o">==</span> <span class="mi">2</span><span class="p">,</span>
<span class="n">p</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_dropout</span><span class="p">,</span> <span class="n">state_outputs</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_mode</span><span class="p">)</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="p">:</span>
<span class="n">outputs</span><span class="p">,</span> <span class="n">states</span> <span class="o">=</span> <span class="n">rnn</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="p">[</span><span class="n">rnn</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">rnn</span><span class="p">[</span><span class="mi">2</span><span class="p">]]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">outputs</span><span class="p">,</span> <span class="n">states</span> <span class="o">=</span> <span class="n">rnn</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="p">[</span><span class="n">rnn</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">_layout</span> <span class="o">==</span> <span class="s1">'NTC'</span><span class="p">:</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="n">ndarray</span><span class="o">.</span><span class="n">swapaxes</span><span class="p">(</span><span class="n">outputs</span><span class="p">,</span> <span class="n">dim1</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">dim2</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="k">return</span> <span class="n">outputs</span><span class="p">,</span> <span class="n">states</span>
<div class="viewcode-block" id="RNN"><a class="viewcode-back" href="../../../../api/python/gluon/rnn.html#mxnet.gluon.rnn.RNN">[docs]</a><span class="k">class</span> <span class="nc">RNN</span><span class="p">(</span><span class="n">_RNNLayer</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Applies a multi-layer Elman RNN with `tanh` or `ReLU` non-linearity to an input sequence.</span>
<span class="sd"> For each element in the input sequence, each layer computes the following</span>
<span class="sd"> function:</span>
<span class="sd"> .. math::</span>
<span class="sd"> h_t = \tanh(w_{ih} * x_t + b_{ih} + w_{hh} * h_{(t-1)} + b_{hh})</span>
<span class="sd"> where :math:`h_t` is the hidden state at time `t`, and :math:`x_t` is the hidden</span>
<span class="sd"> state of the previous layer at time `t` or :math:`input_t` for the first layer.</span>
<span class="sd"> If nonlinearity='relu', then `ReLU` is used instead of `tanh`.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> hidden_size: int</span>
<span class="sd"> The number of features in the hidden state h.</span>
<span class="sd"> num_layers: int, default 1</span>
<span class="sd"> Number of recurrent layers.</span>
<span class="sd"> activation: {'relu' or 'tanh'}, default 'tanh'</span>
<span class="sd"> The activation function to use.</span>
<span class="sd"> layout : str, default 'TNC'</span>
<span class="sd"> The format of input and output tensors. T, N and C stand for</span>
<span class="sd"> sequence length, batch size, and feature dimensions respectively.</span>
<span class="sd"> dropout: float, default 0</span>
<span class="sd"> If non-zero, introduces a dropout layer on the outputs of each</span>
<span class="sd"> RNN layer except the last layer.</span>
<span class="sd"> bidirectional: bool, default False</span>
<span class="sd"> If `True`, becomes a bidirectional RNN.</span>
<span class="sd"> i2h_weight_initializer : str or Initializer</span>
<span class="sd"> Initializer for the input weights matrix, used for the linear</span>
<span class="sd"> transformation of the inputs.</span>
<span class="sd"> h2h_weight_initializer : str or Initializer</span>
<span class="sd"> Initializer for the recurrent weights matrix, used for the linear</span>
<span class="sd"> transformation of the recurrent state.</span>
<span class="sd"> i2h_bias_initializer : str or Initializer</span>
<span class="sd"> Initializer for the bias vector.</span>
<span class="sd"> h2h_bias_initializer : str or Initializer</span>
<span class="sd"> Initializer for the bias vector.</span>
<span class="sd"> input_size: int, default 0</span>
<span class="sd"> The number of expected features in the input x.</span>
<span class="sd"> If not specified, it will be inferred from input.</span>
<span class="sd"> prefix : str or None</span>
<span class="sd"> Prefix of this `Block`.</span>
<span class="sd"> params : ParameterDict or None</span>
<span class="sd"> Shared Parameters for this `Block`.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with shape `(sequence_length, batch_size, input_size)`</span>
<span class="sd"> when `layout` is "TNC". For other layouts dimensions are permuted accordingly.</span>
<span class="sd"> - **states**: initial recurrent state tensor with shape</span>
<span class="sd"> `(num_layers, batch_size, num_hidden)`. If `bidirectional` is True,</span>
<span class="sd"> shape will instead be `(2*num_layers, batch_size, num_hidden)`. If</span>
<span class="sd"> `states` is None, zeros will be used as default begin states.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with shape `(sequence_length, batch_size, num_hidden)`</span>
<span class="sd"> when `layout` is "TNC". If `bidirectional` is True, output shape will instead</span>
<span class="sd"> be `(sequence_length, batch_size, 2*num_hidden)`</span>
<span class="sd"> - **out_states**: output recurrent state tensor with the same shape as `states`.</span>
<span class="sd"> If `states` is None `out_states` will not be returned.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> >>> layer = mx.gluon.rnn.RNN(100, 3)</span>
<span class="sd"> >>> layer.initialize()</span>
<span class="sd"> >>> input = mx.nd.random.uniform(shape=(5, 3, 10))</span>
<span class="sd"> >>> # by default zeros are used as begin state</span>
<span class="sd"> >>> output = layer(input)</span>
<span class="sd"> >>> # manually specify begin state.</span>
<span class="sd"> >>> h0 = mx.nd.random.uniform(shape=(3, 3, 100))</span>
<span class="sd"> >>> output, hn = layer(input, h0)</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">num_layers</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">activation</span><span class="o">=</span><span class="s1">'relu'</span><span class="p">,</span>
<span class="n">layout</span><span class="o">=</span><span class="s1">'TNC'</span><span class="p">,</span> <span class="n">dropout</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">bidirectional</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">i2h_weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">h2h_weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">i2h_bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">h2h_bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span>
<span class="n">input_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">RNN</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">hidden_size</span><span class="p">,</span> <span class="n">num_layers</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span>
<span class="n">dropout</span><span class="p">,</span> <span class="n">bidirectional</span><span class="p">,</span> <span class="n">input_size</span><span class="p">,</span>
<span class="n">i2h_weight_initializer</span><span class="p">,</span> <span class="n">h2h_weight_initializer</span><span class="p">,</span>
<span class="n">i2h_bias_initializer</span><span class="p">,</span> <span class="n">h2h_bias_initializer</span><span class="p">,</span>
<span class="s1">'rnn_'</span><span class="o">+</span><span class="n">activation</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">state_info</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="k">return</span> <span class="p">[{</span><span class="s1">'shape'</span><span class="p">:</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">),</span>
<span class="s1">'__layout__'</span><span class="p">:</span> <span class="s1">'LNC'</span><span class="p">}]</span></div>
<div class="viewcode-block" id="LSTM"><a class="viewcode-back" href="../../../../api/python/gluon/rnn.html#mxnet.gluon.rnn.LSTM">[docs]</a><span class="k">class</span> <span class="nc">LSTM</span><span class="p">(</span><span class="n">_RNNLayer</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Applies a multi-layer long short-term memory (LSTM) RNN to an input sequence.</span>
<span class="sd"> For each element in the input sequence, each layer computes the following</span>
<span class="sd"> function:</span>
<span class="sd"> .. math::</span>
<span class="sd"> \begin{array}{ll}</span>
<span class="sd"> i_t = sigmoid(W_{ii} x_t + b_{ii} + W_{hi} h_{(t-1)} + b_{hi}) \\</span>
<span class="sd"> f_t = sigmoid(W_{if} x_t + b_{if} + W_{hf} h_{(t-1)} + b_{hf}) \\</span>
<span class="sd"> g_t = \tanh(W_{ig} x_t + b_{ig} + W_{hc} h_{(t-1)} + b_{hg}) \\</span>
<span class="sd"> o_t = sigmoid(W_{io} x_t + b_{io} + W_{ho} h_{(t-1)} + b_{ho}) \\</span>
<span class="sd"> c_t = f_t * c_{(t-1)} + i_t * g_t \\</span>
<span class="sd"> h_t = o_t * \tanh(c_t)</span>
<span class="sd"> \end{array}</span>
<span class="sd"> where :math:`h_t` is the hidden state at time `t`, :math:`c_t` is the</span>
<span class="sd"> cell state at time `t`, :math:`x_t` is the hidden state of the previous</span>
<span class="sd"> layer at time `t` or :math:`input_t` for the first layer, and :math:`i_t`,</span>
<span class="sd"> :math:`f_t`, :math:`g_t`, :math:`o_t` are the input, forget, cell, and</span>
<span class="sd"> out gates, respectively.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> hidden_size: int</span>
<span class="sd"> The number of features in the hidden state h.</span>
<span class="sd"> num_layers: int, default 1</span>
<span class="sd"> Number of recurrent layers.</span>
<span class="sd"> layout : str, default 'TNC'</span>
<span class="sd"> The format of input and output tensors. T, N and C stand for</span>
<span class="sd"> sequence length, batch size, and feature dimensions respectively.</span>
<span class="sd"> dropout: float, default 0</span>
<span class="sd"> If non-zero, introduces a dropout layer on the outputs of each</span>
<span class="sd"> RNN layer except the last layer.</span>
<span class="sd"> bidirectional: bool, default False</span>
<span class="sd"> If `True`, becomes a bidirectional RNN.</span>
<span class="sd"> i2h_weight_initializer : str or Initializer</span>
<span class="sd"> Initializer for the input weights matrix, used for the linear</span>
<span class="sd"> transformation of the inputs.</span>
<span class="sd"> h2h_weight_initializer : str or Initializer</span>
<span class="sd"> Initializer for the recurrent weights matrix, used for the linear</span>
<span class="sd"> transformation of the recurrent state.</span>
<span class="sd"> i2h_bias_initializer : str or Initializer, default 'lstmbias'</span>
<span class="sd"> Initializer for the bias vector. By default, bias for the forget</span>
<span class="sd"> gate is initialized to 1 while all other biases are initialized</span>
<span class="sd"> to zero.</span>
<span class="sd"> h2h_bias_initializer : str or Initializer</span>
<span class="sd"> Initializer for the bias vector.</span>
<span class="sd"> input_size: int, default 0</span>
<span class="sd"> The number of expected features in the input x.</span>
<span class="sd"> If not specified, it will be inferred from input.</span>
<span class="sd"> prefix : str or None</span>
<span class="sd"> Prefix of this `Block`.</span>
<span class="sd"> params : `ParameterDict` or `None`</span>
<span class="sd"> Shared Parameters for this `Block`.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with shape `(sequence_length, batch_size, input_size)`</span>
<span class="sd"> when `layout` is "TNC". For other layouts dimensions are permuted accordingly.</span>
<span class="sd"> - **states**: a list of two initial recurrent state tensors. Each has shape</span>
<span class="sd"> `(num_layers, batch_size, num_hidden)`. If `bidirectional` is True,</span>
<span class="sd"> shape will instead be `(2*num_layers, batch_size, num_hidden)`. If</span>
<span class="sd"> `states` is None, zeros will be used as default begin states.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with shape `(sequence_length, batch_size, num_hidden)`</span>
<span class="sd"> when `layout` is "TNC". If `bidirectional` is True, output shape will instead</span>
<span class="sd"> be `(sequence_length, batch_size, 2*num_hidden)`</span>
<span class="sd"> - **out_states**: a list of two output recurrent state tensors with the same</span>
<span class="sd"> shape as in `states`. If `states` is None `out_states` will not be returned.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> >>> layer = mx.gluon.rnn.LSTM(100, 3)</span>
<span class="sd"> >>> layer.initialize()</span>
<span class="sd"> >>> input = mx.nd.random.uniform(shape=(5, 3, 10))</span>
<span class="sd"> >>> # by default zeros are used as begin state</span>
<span class="sd"> >>> output = layer(input)</span>
<span class="sd"> >>> # manually specify begin state.</span>
<span class="sd"> >>> h0 = mx.nd.random.uniform(shape=(3, 3, 100))</span>
<span class="sd"> >>> c0 = mx.nd.random.uniform(shape=(3, 3, 100))</span>
<span class="sd"> >>> output, hn = layer(input, [h0, c0])</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">num_layers</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'TNC'</span><span class="p">,</span>
<span class="n">dropout</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">bidirectional</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">input_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
<span class="n">i2h_weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">h2h_weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">i2h_bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">h2h_bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</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">LSTM</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">hidden_size</span><span class="p">,</span> <span class="n">num_layers</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span>
<span class="n">dropout</span><span class="p">,</span> <span class="n">bidirectional</span><span class="p">,</span> <span class="n">input_size</span><span class="p">,</span>
<span class="n">i2h_weight_initializer</span><span class="p">,</span> <span class="n">h2h_weight_initializer</span><span class="p">,</span>
<span class="n">i2h_bias_initializer</span><span class="p">,</span> <span class="n">h2h_bias_initializer</span><span class="p">,</span>
<span class="s1">'lstm'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">state_info</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="k">return</span> <span class="p">[{</span><span class="s1">'shape'</span><span class="p">:</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">),</span>
<span class="s1">'__layout__'</span><span class="p">:</span> <span class="s1">'LNC'</span><span class="p">},</span>
<span class="p">{</span><span class="s1">'shape'</span><span class="p">:</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">),</span>
<span class="s1">'__layout__'</span><span class="p">:</span> <span class="s1">'LNC'</span><span class="p">}]</span></div>
<div class="viewcode-block" id="GRU"><a class="viewcode-back" href="../../../../api/python/gluon/rnn.html#mxnet.gluon.rnn.GRU">[docs]</a><span class="k">class</span> <span class="nc">GRU</span><span class="p">(</span><span class="n">_RNNLayer</span><span class="p">):</span>
<span class="sa">r</span><span class="sd">"""Applies a multi-layer gated recurrent unit (GRU) RNN to an input sequence.</span>
<span class="sd"> For each element in the input sequence, each layer computes the following</span>
<span class="sd"> function:</span>
<span class="sd"> .. math::</span>
<span class="sd"> \begin{array}{ll}</span>
<span class="sd"> r_t = sigmoid(W_{ir} x_t + b_{ir} + W_{hr} h_{(t-1)} + b_{hr}) \\</span>
<span class="sd"> i_t = sigmoid(W_{ii} x_t + b_{ii} + W_hi h_{(t-1)} + b_{hi}) \\</span>
<span class="sd"> n_t = \tanh(W_{in} x_t + b_{in} + r_t * (W_{hn} h_{(t-1)}+ b_{hn})) \\</span>
<span class="sd"> h_t = (1 - i_t) * n_t + i_t * h_{(t-1)} \\</span>
<span class="sd"> \end{array}</span>
<span class="sd"> where :math:`h_t` is the hidden state at time `t`, :math:`x_t` is the hidden</span>
<span class="sd"> state of the previous layer at time `t` or :math:`input_t` for the first layer,</span>
<span class="sd"> and :math:`r_t`, :math:`i_t`, :math:`n_t` are the reset, input, and new gates, respectively.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> hidden_size: int</span>
<span class="sd"> The number of features in the hidden state h</span>
<span class="sd"> num_layers: int, default 1</span>
<span class="sd"> Number of recurrent layers.</span>
<span class="sd"> layout : str, default 'TNC'</span>
<span class="sd"> The format of input and output tensors. T, N and C stand for</span>
<span class="sd"> sequence length, batch size, and feature dimensions respectively.</span>
<span class="sd"> dropout: float, default 0</span>
<span class="sd"> If non-zero, introduces a dropout layer on the outputs of each</span>
<span class="sd"> RNN layer except the last layer</span>
<span class="sd"> bidirectional: bool, default False</span>
<span class="sd"> If True, becomes a bidirectional RNN.</span>
<span class="sd"> i2h_weight_initializer : str or Initializer</span>
<span class="sd"> Initializer for the input weights matrix, used for the linear</span>
<span class="sd"> transformation of the inputs.</span>
<span class="sd"> h2h_weight_initializer : str or Initializer</span>
<span class="sd"> Initializer for the recurrent weights matrix, used for the linear</span>
<span class="sd"> transformation of the recurrent state.</span>
<span class="sd"> i2h_bias_initializer : str or Initializer</span>
<span class="sd"> Initializer for the bias vector.</span>
<span class="sd"> h2h_bias_initializer : str or Initializer</span>
<span class="sd"> Initializer for the bias vector.</span>
<span class="sd"> input_size: int, default 0</span>
<span class="sd"> The number of expected features in the input x.</span>
<span class="sd"> If not specified, it will be inferred from input.</span>
<span class="sd"> prefix : str or None</span>
<span class="sd"> Prefix of this `Block`.</span>
<span class="sd"> params : ParameterDict or None</span>
<span class="sd"> Shared Parameters for this `Block`.</span>
<span class="sd"> Inputs:</span>
<span class="sd"> - **data**: input tensor with shape `(sequence_length, batch_size, input_size)`</span>
<span class="sd"> when `layout` is "TNC". For other layouts dimensions are permuted accordingly.</span>
<span class="sd"> - **states**: initial recurrent state tensor with shape</span>
<span class="sd"> `(num_layers, batch_size, num_hidden)`. If `bidirectional` is True,</span>
<span class="sd"> shape will instead be `(2*num_layers, batch_size, num_hidden)`. If</span>
<span class="sd"> `states` is None, zeros will be used as default begin states.</span>
<span class="sd"> Outputs:</span>
<span class="sd"> - **out**: output tensor with shape `(sequence_length, batch_size, num_hidden)`</span>
<span class="sd"> when `layout` is "TNC". If `bidirectional` is True, output shape will instead</span>
<span class="sd"> be `(sequence_length, batch_size, 2*num_hidden)`</span>
<span class="sd"> - **out_states**: output recurrent state tensor with the same shape as `states`.</span>
<span class="sd"> If `states` is None `out_states` will not be returned.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> >>> layer = mx.gluon.rnn.GRU(100, 3)</span>
<span class="sd"> >>> layer.initialize()</span>
<span class="sd"> >>> input = mx.nd.random.uniform(shape=(5, 3, 10))</span>
<span class="sd"> >>> # by default zeros are used as begin state</span>
<span class="sd"> >>> output = layer(input)</span>
<span class="sd"> >>> # manually specify begin state.</span>
<span class="sd"> >>> h0 = mx.nd.random.uniform(shape=(3, 3, 100))</span>
<span class="sd"> >>> output, hn = layer(input, h0)</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">num_layers</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">layout</span><span class="o">=</span><span class="s1">'TNC'</span><span class="p">,</span>
<span class="n">dropout</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">bidirectional</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">input_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
<span class="n">i2h_weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">h2h_weight_initializer</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">i2h_bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</span><span class="p">,</span> <span class="n">h2h_bias_initializer</span><span class="o">=</span><span class="s1">'zeros'</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">GRU</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">hidden_size</span><span class="p">,</span> <span class="n">num_layers</span><span class="p">,</span> <span class="n">layout</span><span class="p">,</span>
<span class="n">dropout</span><span class="p">,</span> <span class="n">bidirectional</span><span class="p">,</span> <span class="n">input_size</span><span class="p">,</span>
<span class="n">i2h_weight_initializer</span><span class="p">,</span> <span class="n">h2h_weight_initializer</span><span class="p">,</span>
<span class="n">i2h_bias_initializer</span><span class="p">,</span> <span class="n">h2h_bias_initializer</span><span class="p">,</span>
<span class="s1">'gru'</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">state_info</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="k">return</span> <span class="p">[{</span><span class="s1">'shape'</span><span class="p">:</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_layers</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">_dir</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_hidden_size</span><span class="p">),</span>
<span class="s1">'__layout__'</span><span class="p">:</span> <span class="s1">'LNC'</span><span class="p">}]</span></div>
</pre></div>
</div>
</div>
<div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
</div>
</div>
</div><div class="footer">
<div class="section-disclaimer">
<div class="container">
<div>
<img height="60" src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/apache_incubator_logo.png"/>
<p>
Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), <strong>sponsored by the <i>Apache Incubator</i></strong>. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
</p>
<p>
"Copyright © 2017-2018, The Apache Software Foundation
Apache MXNet, MXNet, Apache, the Apache feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the Apache Software Foundation."
</p>
</div>
</div>
</div>
</div> <!-- pagename != index -->
</div>
<script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script>
<script src="../../../../_static/js/sidebar.js" type="text/javascript"></script>
<script src="../../../../_static/js/search.js" type="text/javascript"></script>
<script src="../../../../_static/js/navbar.js" type="text/javascript"></script>
<script src="../../../../_static/js/clipboard.min.js" type="text/javascript"></script>
<script src="../../../../_static/js/copycode.js" type="text/javascript"></script>
<script src="../../../../_static/js/page.js" type="text/javascript"></script>
<script src="../../../../_static/js/docversion.js" type="text/javascript"></script>
<script type="text/javascript">
$('body').ready(function () {
$('body').css('visibility', 'visible');
});
</script>
</body>
</html>