Google Git
Sign in
apache / mxnet-site / b9b555e4d6826387d69ad385b27a24c21f3a5b53 / . / _modules / mxnet / gluon / data / dataloader.html
blob: c754e24487bfaec336ef526269ba2ce6dab772ff [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.gluon.data.dataloader — 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>
<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="../../../../tutorials/index.html">Tutorials</a>
<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/1.1.0/example">Examples</a></li>
<li><a class="main-nav-link" href="../../../../api/python/gluon/model_zoo.html">Gluon Model Zoo</a></li>
</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>
<li><a class="main-nav-link" href="http://discuss.mxnet.io">Discuss</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">Versions(1.1.0)<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/>1.1.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/1.0.0/index.html>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/1.1.0/example" tabindex="-1">Examples</a></li>
<li><a href="../../../../api/python/gluon/model_zoo.html" tabindex="-1">Gluon Model Zoo</a></li>
</ul>
</li>
<li><a 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(1.1.0)</a><ul class="dropdown-menu"><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/>1.1.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/1.0.0/index.html>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.gluon.data.dataloader</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=</span>
<span class="sd">"""Dataset generator."""</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'DataLoader'</span><span class="p">]</span>
<span class="kn">import</span> <span class="nn">multiprocessing</span>
<span class="kn">import</span> <span class="nn">multiprocessing.queues</span>
<span class="kn">from</span> <span class="nn">multiprocessing.reduction</span> <span class="kn">import</span> <span class="n">ForkingPickler</span>
<span class="kn">import</span> <span class="nn">pickle</span>
<span class="kn">import</span> <span class="nn">io</span>
<span class="kn">import</span> <span class="nn">sys</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">.</span> <span class="kn">import</span> <span class="n">sampler</span> <span class="k">as</span> <span class="n">_sampler</span>
<span class="kn">from</span> <span class="nn">...</span> <span class="kn">import</span> <span class="n">nd</span><span class="p">,</span> <span class="n">context</span>
<span class="k">def</span> <span class="nf">rebuild_ndarray</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">):</span>
<span class="sd">"""Rebuild ndarray from pickled shared memory"""</span>
<span class="c1"># pylint: disable=no-value-for-parameter</span>
<span class="k">return</span> <span class="n">nd</span><span class="o">.</span><span class="n">NDArray</span><span class="p">(</span><span class="n">nd</span><span class="o">.</span><span class="n">ndarray</span><span class="o">.</span><span class="n">_new_from_shared_mem</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">reduce_ndarray</span><span class="p">(</span><span class="n">data</span><span class="p">):</span>
<span class="sd">"""Reduce ndarray to shared memory handle"""</span>
<span class="k">return</span> <span class="n">rebuild_ndarray</span><span class="p">,</span> <span class="n">data</span><span class="o">.</span><span class="n">_to_shared_mem</span><span class="p">()</span>
<span class="n">ForkingPickler</span><span class="o">.</span><span class="n">register</span><span class="p">(</span><span class="n">nd</span><span class="o">.</span><span class="n">NDArray</span><span class="p">,</span> <span class="n">reduce_ndarray</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">ConnectionWrapper</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""Connection wrapper for multiprocessing that supports sending</span>
<span class="sd"> NDArray via shared memory."""</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">conn</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_conn</span> <span class="o">=</span> <span class="n">conn</span>
<span class="k">def</span> <span class="nf">send</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">obj</span><span class="p">):</span>
<span class="sd">"""Send object"""</span>
<span class="n">buf</span> <span class="o">=</span> <span class="n">io</span><span class="o">.</span><span class="n">BytesIO</span><span class="p">()</span>
<span class="n">ForkingPickler</span><span class="p">(</span><span class="n">buf</span><span class="p">,</span> <span class="n">pickle</span><span class="o">.</span><span class="n">HIGHEST_PROTOCOL</span><span class="p">)</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="n">obj</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">send_bytes</span><span class="p">(</span><span class="n">buf</span><span class="o">.</span><span class="n">getvalue</span><span class="p">())</span>
<span class="k">def</span> <span class="nf">recv</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""Receive object"""</span>
<span class="n">buf</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">recv_bytes</span><span class="p">()</span>
<span class="k">return</span> <span class="n">pickle</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">buf</span><span class="p">)</span>
<span class="k">def</span> <span class="fm">__getattr__</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="sd">"""Emmulate conn"""</span>
<span class="n">attr</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'_conn'</span><span class="p">,</span> <span class="bp">None</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">attr</span><span class="p">,</span> <span class="n">name</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">Queue</span><span class="p">(</span><span class="n">multiprocessing</span><span class="o">.</span><span class="n">queues</span><span class="o">.</span><span class="n">Queue</span><span class="p">):</span>
<span class="sd">"""Wrapper for multiprocessing queue that dumps NDArray with shared memory."""</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">args</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="n">sys</span><span class="o">.</span><span class="n">version_info</span><span class="p">[</span><span class="mi">0</span><span class="p">]</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">Queue</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">args</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="nb">super</span><span class="p">(</span><span class="n">Queue</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">args</span><span class="p">,</span> <span class="n">ctx</span><span class="o">=</span><span class="n">multiprocessing</span><span class="o">.</span><span class="n">get_context</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">_reader</span> <span class="o">=</span> <span class="n">ConnectionWrapper</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_reader</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_writer</span> <span class="o">=</span> <span class="n">ConnectionWrapper</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_writer</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_send</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_writer</span><span class="o">.</span><span class="n">send</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_recv</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_reader</span><span class="o">.</span><span class="n">recv</span>
<span class="k">def</span> <span class="nf">default_batchify_fn</span><span class="p">(</span><span class="n">data</span><span class="p">):</span>
<span class="sd">"""Collate data into batch."""</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">nd</span><span class="o">.</span><span class="n">NDArray</span><span class="p">):</span>
<span class="k">return</span> <span class="n">nd</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="o">*</span><span class="n">data</span><span class="p">)</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="nb">tuple</span><span class="p">):</span>
<span class="n">data</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="n">data</span><span class="p">)</span>
<span class="k">return</span> <span class="p">[</span><span class="n">default_batchify_fn</span><span class="p">(</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">data</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="k">return</span> <span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">data</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">default_mp_batchify_fn</span><span class="p">(</span><span class="n">data</span><span class="p">):</span>
<span class="sd">"""Collate data into batch. Use shared memory for stacking."""</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">nd</span><span class="o">.</span><span class="n">NDArray</span><span class="p">):</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">empty</span><span class="p">((</span><span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">),)</span> <span class="o">+</span> <span class="n">data</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="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">ctx</span><span class="o">=</span><span class="n">context</span><span class="o">.</span><span class="n">Context</span><span class="p">(</span><span class="s1">'cpu_shared'</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span>
<span class="k">return</span> <span class="n">nd</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="o">*</span><span class="n">data</span><span class="p">,</span> <span class="n">out</span><span class="o">=</span><span class="n">out</span><span class="p">)</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="nb">tuple</span><span class="p">):</span>
<span class="n">data</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="n">data</span><span class="p">)</span>
<span class="k">return</span> <span class="p">[</span><span class="n">default_mp_batchify_fn</span><span class="p">(</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">data</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
<span class="k">return</span> <span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">data</span><span class="o">.</span><span class="n">dtype</span><span class="p">,</span>
<span class="n">ctx</span><span class="o">=</span><span class="n">context</span><span class="o">.</span><span class="n">Context</span><span class="p">(</span><span class="s1">'cpu_shared'</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">worker_loop</span><span class="p">(</span><span class="n">dataset</span><span class="p">,</span> <span class="n">key_queue</span><span class="p">,</span> <span class="n">data_queue</span><span class="p">,</span> <span class="n">batchify_fn</span><span class="p">):</span>
<span class="sd">"""Worker loop for multiprocessing DataLoader."""</span>
<span class="k">while</span> <span class="bp">True</span><span class="p">:</span>
<span class="n">idx</span><span class="p">,</span> <span class="n">samples</span> <span class="o">=</span> <span class="n">key_queue</span><span class="o">.</span><span class="n">get</span><span class="p">()</span>
<span class="k">if</span> <span class="n">idx</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">break</span>
<span class="n">batch</span> <span class="o">=</span> <span class="n">batchify_fn</span><span class="p">([</span><span class="n">dataset</span><span class="p">[</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">samples</span><span class="p">])</span>
<span class="n">data_queue</span><span class="o">.</span><span class="n">put</span><span class="p">((</span><span class="n">idx</span><span class="p">,</span> <span class="n">batch</span><span class="p">))</span>
<div class="viewcode-block" id="DataLoader"><a class="viewcode-back" href="../../../../api/python/gluon/data.html#mxnet.gluon.data.DataLoader">[docs]</a><span class="k">class</span> <span class="nc">DataLoader</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">"""Loads data from a dataset and returns mini-batches of data.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> dataset : Dataset</span>
<span class="sd"> Source dataset. Note that numpy and mxnet arrays can be directly used</span>
<span class="sd"> as a Dataset.</span>
<span class="sd"> batch_size : int</span>
<span class="sd"> Size of mini-batch.</span>
<span class="sd"> shuffle : bool</span>
<span class="sd"> Whether to shuffle the samples.</span>
<span class="sd"> sampler : Sampler</span>
<span class="sd"> The sampler to use. Either specify sampler or shuffle, not both.</span>
<span class="sd"> last_batch : {'keep', 'discard', 'rollover'}</span>
<span class="sd"> How to handle the last batch if batch_size does not evenly divide</span>
<span class="sd"> `len(dataset)`.</span>
<span class="sd"> keep - A batch with less samples than previous batches is returned.</span>
<span class="sd"> discard - The last batch is discarded if its incomplete.</span>
<span class="sd"> rollover - The remaining samples are rolled over to the next epoch.</span>
<span class="sd"> batch_sampler : Sampler</span>
<span class="sd"> A sampler that returns mini-batches. Do not specify batch_size,</span>
<span class="sd"> shuffle, sampler, and last_batch if batch_sampler is specified.</span>
<span class="sd"> batchify_fn : callable</span>
<span class="sd"> Callback function to allow users to specify how to merge samples</span>
<span class="sd"> into a batch. Defaults to `default_batchify_fn`::</span>
<span class="sd"> def default_batchify_fn(data):</span>
<span class="sd"> if isinstance(data[0], nd.NDArray):</span>
<span class="sd"> return nd.stack(*data)</span>
<span class="sd"> elif isinstance(data[0], tuple):</span>
<span class="sd"> data = zip(*data)</span>
<span class="sd"> return [default_batchify_fn(i) for i in data]</span>
<span class="sd"> else:</span>
<span class="sd"> data = np.asarray(data)</span>
<span class="sd"> return nd.array(data, dtype=data.dtype)</span>
<span class="sd"> num_workers : int, default 0</span>
<span class="sd"> The number of multiprocessing workers to use for data preprocessing.</span>
<span class="sd"> `num_workers > 0` is not supported on Windows yet.</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">dataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">shuffle</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span> <span class="n">sampler</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">last_batch</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">batch_sampler</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">batchify_fn</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span>
<span class="n">num_workers</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_dataset</span> <span class="o">=</span> <span class="n">dataset</span>
<span class="k">if</span> <span class="n">batch_sampler</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">batch_size</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"batch_size must be specified unless "</span> \
<span class="s2">"batch_sampler is specified"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">sampler</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">shuffle</span><span class="p">:</span>
<span class="n">sampler</span> <span class="o">=</span> <span class="n">_sampler</span><span class="o">.</span><span class="n">RandomSampler</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">dataset</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">sampler</span> <span class="o">=</span> <span class="n">_sampler</span><span class="o">.</span><span class="n">SequentialSampler</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">dataset</span><span class="p">))</span>
<span class="k">elif</span> <span class="n">shuffle</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"shuffle must not be specified if sampler is specified"</span><span class="p">)</span>
<span class="n">batch_sampler</span> <span class="o">=</span> <span class="n">_sampler</span><span class="o">.</span><span class="n">BatchSampler</span><span class="p">(</span>
<span class="n">sampler</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">last_batch</span> <span class="k">if</span> <span class="n">last_batch</span> <span class="k">else</span> <span class="s1">'keep'</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">batch_size</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span> <span class="ow">or</span> <span class="n">shuffle</span> <span class="ow">or</span> <span class="n">sampler</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span> <span class="ow">or</span> \
<span class="n">last_batch</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"batch_size, shuffle, sampler and last_batch must "</span> \
<span class="s2">"not be specified if batch_sampler is specified."</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_batch_sampler</span> <span class="o">=</span> <span class="n">batch_sampler</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_num_workers</span> <span class="o">=</span> <span class="n">num_workers</span>
<span class="k">if</span> <span class="n">batchify_fn</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">num_workers</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_batchify_fn</span> <span class="o">=</span> <span class="n">default_mp_batchify_fn</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_batchify_fn</span> <span class="o">=</span> <span class="n">default_batchify_fn</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_batchify_fn</span> <span class="o">=</span> <span class="n">batchify_fn</span>
<span class="k">def</span> <span class="fm">__iter__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_num_workers</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batch_sampler</span><span class="p">:</span>
<span class="k">yield</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batchify_fn</span><span class="p">([</span><span class="bp">self</span><span class="o">.</span><span class="n">_dataset</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span> <span class="k">for</span> <span class="n">idx</span> <span class="ow">in</span> <span class="n">batch</span><span class="p">])</span>
<span class="k">return</span>
<span class="n">key_queue</span> <span class="o">=</span> <span class="n">Queue</span><span class="p">()</span>
<span class="n">data_queue</span> <span class="o">=</span> <span class="n">Queue</span><span class="p">(</span><span class="mi">2</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">_num_workers</span><span class="p">)</span>
<span class="n">workers</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">_</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_workers</span><span class="p">):</span>
<span class="n">worker</span> <span class="o">=</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">Process</span><span class="p">(</span>
<span class="n">target</span><span class="o">=</span><span class="n">worker_loop</span><span class="p">,</span>
<span class="n">args</span><span class="o">=</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_dataset</span><span class="p">,</span> <span class="n">key_queue</span><span class="p">,</span> <span class="n">data_queue</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batchify_fn</span><span class="p">))</span>
<span class="n">worker</span><span class="o">.</span><span class="n">daemon</span> <span class="o">=</span> <span class="bp">True</span>
<span class="n">worker</span><span class="o">.</span><span class="n">start</span><span class="p">()</span>
<span class="n">workers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">worker</span><span class="p">)</span>
<span class="k">for</span> <span class="n">idx</span><span class="p">,</span> <span class="n">batch</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">_batch_sampler</span><span class="p">):</span>
<span class="n">key_queue</span><span class="o">.</span><span class="n">put</span><span class="p">((</span><span class="n">idx</span><span class="p">,</span> <span class="n">batch</span><span class="p">))</span>
<span class="n">num_batches</span> <span class="o">=</span> <span class="n">idx</span> <span class="o">+</span> <span class="mi">1</span>
<span class="n">data_buffer</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">curr_idx</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_batches</span><span class="p">):</span>
<span class="n">idx</span><span class="p">,</span> <span class="n">batch</span> <span class="o">=</span> <span class="n">data_queue</span><span class="o">.</span><span class="n">get</span><span class="p">()</span>
<span class="n">data_buffer</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span> <span class="o">=</span> <span class="n">batch</span>
<span class="k">while</span> <span class="n">curr_idx</span> <span class="ow">in</span> <span class="n">data_buffer</span><span class="p">:</span>
<span class="k">yield</span> <span class="n">data_buffer</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="n">curr_idx</span><span class="p">)</span>
<span class="n">curr_idx</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="k">for</span> <span class="n">_</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_workers</span><span class="p">):</span>
<span class="n">key_queue</span><span class="o">.</span><span class="n">put</span><span class="p">((</span><span class="bp">None</span><span class="p">,</span> <span class="bp">None</span><span class="p">))</span>
<span class="k">for</span> <span class="n">worker</span> <span class="ow">in</span> <span class="n">workers</span><span class="p">:</span>
<span class="n">worker</span><span class="o">.</span><span class="n">join</span><span class="p">()</span>
<span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_batch_sampler</span><span class="p">)</span></div>
</pre></div>
</div>
</div>
<div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
</div>
</div>
</div><div class="footer">
<div class="section-disclaimer">
<div class="container">
<div>
<img height="60" src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/apache_incubator_logo.png"/>
<p>
Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), <strong>sponsored by the <i>Apache Incubator</i></strong>. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
</p>
<p>
"Copyright © 2017-2018, The Apache Software Foundation
Apache MXNet, MXNet, Apache, the Apache feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the Apache Software Foundation."
</p>
</div>
</div>
</div>
</div> <!-- pagename != index -->
</div>
<script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script>
<script src="../../../../_static/js/sidebar.js" type="text/javascript"></script>
<script src="../../../../_static/js/search.js" type="text/javascript"></script>
<script src="../../../../_static/js/navbar.js" type="text/javascript"></script>
<script src="../../../../_static/js/clipboard.min.js" type="text/javascript"></script>
<script src="../../../../_static/js/copycode.js" type="text/javascript"></script>
<script src="../../../../_static/js/page.js" type="text/javascript"></script>
<script type="text/javascript">
$('body').ready(function () {
$('body').css('visibility', 'visible');
});
</script>
</body>
</html>