blob: 6e0261173f1e1d1033d103ac6db2969f5ba14222 [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>Image IO - Loading and pre-processing images — mxnet documentation</title>
<link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/>
<link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/>
<link href="../../_static/basic.css" rel="stylesheet" type="text/css">
<link href="../../_static/pygments.css" rel="stylesheet" type="text/css">
<link href="../../_static/mxnet.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../',
VERSION: '',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: ''
};
</script>
<script src="../../_static/jquery-1.11.1.js" type="text/javascript"></script>
<script src="../../_static/underscore.js" type="text/javascript"></script>
<script src="../../_static/searchtools_custom.js" type="text/javascript"></script>
<script src="../../_static/doctools.js" type="text/javascript"></script>
<script src="../../_static/selectlang.js" type="text/javascript"></script>
<script src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script>
<script type="text/javascript"> jQuery(function() { Search.loadIndex("/searchindex.js"); Search.init();}); </script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new
Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-96378503-1', 'auto');
ga('send', 'pageview');
</script>
<!-- -->
<!-- <script type="text/javascript" src="../../_static/jquery.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="../../_static/underscore.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="../../_static/doctools.js"></script> -->
<!-- -->
<!-- <script type="text/javascript" src="https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> -->
<!-- -->
<link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/>
</link></link></head>
<body role="document"><!-- Previous Navbar Layout
<div class="navbar navbar-default navbar-fixed-top">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar" aria-expanded="false" aria-controls="navbar">
<span class="sr-only">Toggle navigation</span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<a href="../../" class="navbar-brand">
<img src="http://data.mxnet.io/theme/mxnet.png">
</a>
</div>
<div id="navbar" class="navbar-collapse collapse">
<ul id="navbar" class="navbar navbar-left">
<li> <a href="../../get_started/index.html">Get Started</a> </li>
<li> <a href="../../tutorials/index.html">Tutorials</a> </li>
<li> <a href="../../how_to/index.html">How To</a> </li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">Packages <span class="caret"></span></a>
<ul class="dropdown-menu">
<li><a href="../../packages/python/index.html">
Python
</a></li>
<li><a href="../../packages/r/index.html">
R
</a></li>
<li><a href="../../packages/julia/index.html">
Julia
</a></li>
<li><a href="../../packages/c++/index.html">
C++
</a></li>
<li><a href="../../packages/scala/index.html">
Scala
</a></li>
<li><a href="../../packages/perl/index.html">
Perl
</a></li>
</ul>
</li>
<li> <a href="../../system/index.html">System</a> </li>
<li>
<form class="" role="search" action="../../search.html" method="get" autocomplete="off">
<div class="form-group inner-addon left-addon">
<i class="glyphicon glyphicon-search"></i>
<input type="text" name="q" class="form-control" placeholder="Search">
</div>
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form> </li>
</ul>
<ul id="navbar" class="navbar navbar-right">
<li> <a href="../../index.html"><span class="flag-icon flag-icon-us"></span></a> </li>
<li> <a href="../..//zh/index.html"><span class="flag-icon flag-icon-cn"></span></a> </li>
</ul>
</div>
</div>
</div>
Previous Navbar Layout End -->
<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="http://data.mxnet.io/theme/mxnet.png"/></a>
</h1>
<nav class="nav-bar" id="main-nav">
<a class="main-nav-link" href="../../get_started/install.html">Install</a>
<a class="main-nav-link" href="../../tutorials/index.html">Tutorials</a>
<a class="main-nav-link" href="../../how_to/index.html">How To</a>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API <span class="caret"></span></a>
<ul class="dropdown-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="../../api/python/index.html">Python</a></li>
<li><a class="main-nav-link" href="../../api/scala/index.html">Scala</a></li>
<li><a class="main-nav-link" href="../../api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="../../api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="../../api/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="../../api/perl/index.html">Perl</a></li>
</ul>
</span>
<a class="main-nav-link" href="../../architecture/index.html">Architecture</a>
<!-- <a class="main-nav-link" href="../../community/index.html">Community</a> -->
<a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a>
<span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">Versions(master)<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/test/>v0.10.14</a></li><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/test/versions/0.10/index.html>0.10</a></li><li><a class="main-nav-link" href=http://mxnet.incubator.apache.org/test/versions/master/index.html>master</a></li></ul></span></nav>
<script> function getRootPath(){ return "../../" } </script>
<div class="burgerIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"></a>
<ul class="dropdown-menu dropdown-menu-right" id="burgerMenu">
<li><a href="../../get_started/install.html">Install</a></li>
<li><a href="../../tutorials/index.html">Tutorials</a></li>
<li><a href="../../how_to/index.html">How To</a></li>
<li class="dropdown-submenu">
<a href="#" tabindex="-1">API</a>
<ul class="dropdown-menu">
<li><a href="../../api/python/index.html" tabindex="-1">Python</a>
</li>
<li><a href="../../api/scala/index.html" tabindex="-1">Scala</a>
</li>
<li><a href="../../api/r/index.html" tabindex="-1">R</a>
</li>
<li><a href="../../api/julia/index.html" tabindex="-1">Julia</a>
</li>
<li><a href="../../api/c++/index.html" tabindex="-1">C++</a>
</li>
<li><a href="../../api/perl/index.html" tabindex="-1">Perl</a>
</li>
</ul>
</li>
<li><a href="../../architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a></li>
<li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">Versions(master)</a><ul class="dropdown-menu"><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/test/>v0.10.14</a></li><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/test/versions/0.10/index.html>0.10</a></li><li><a tabindex="-1" href=http://mxnet.incubator.apache.org/test/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>
<div class="container">
<div class="row">
<div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../api/python/index.html">Python Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/r/index.html">R Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/julia/index.html">Julia Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/c++/index.html">C++ Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/scala/index.html">Scala Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../api/perl/index.html">Perl Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../how_to/index.html">HowTo Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../architecture/index.html">System Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../index.html">Tutorials</a></li>
</ul>
</div>
</div>
<div class="content">
<div class="section" id="image-io-loading-and-pre-processing-images">
<span id="image-io-loading-and-pre-processing-images"></span><h1>Image IO - Loading and pre-processing images<a class="headerlink" href="#image-io-loading-and-pre-processing-images" title="Permalink to this headline"></a></h1>
<p>This tutorial explains how to prepare, load and train with image data in
MXNet. All IO in MXNet is handled via <code class="docutils literal"><span class="pre">mx.io.DataIter</span></code> and its subclasses. In
this tutorial we focus on how to use pre-built data iterators as while as custom
iterators to process image data.</p>
<p>There are mainly three ways of loading image data in MXNet:</p>
<ul class="simple">
<li>[NEW] <code class="docutils literal"><span class="pre">mx.img.ImageIter</span></code>: implemented in python, easily customizable, can load
from both .rec files and raw image files.</li>
<li>[OLD] <code class="docutils literal"><span class="pre">mx.io.ImageRecordIter</span></code>: implemented in backend (C++), less customizable
but can be used in all language bindings, load from .rec files</li>
<li>Custom iterator by inheriting mx.io.DataIter</li>
</ul>
<p>First, we explain the record io file format used by mxnet:</p>
<div class="section" id="recordio">
<span id="recordio"></span><h2>RecordIO<a class="headerlink" href="#recordio" title="Permalink to this headline"></a></h2>
<p>Record IO is the main file format used by MXNet for data IO. It supports reading
and writing on various file systems including distributed file systems like
Hadoop HDFS and AWS S3. First, we download the Caltech 101 dataset that
contains 101 classes of objects and convert them into record io format:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="o">%</span><span class="n">matplotlib</span> <span class="n">inline</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">subprocess</span>
<span class="kn">import</span> <span class="nn">mxnet</span> <span class="kn">as</span> <span class="nn">mx</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="kn">as</span> <span class="nn">plt</span>
<span class="c1"># change this to your mxnet location</span>
<span class="n">MXNET_HOME</span> <span class="o">=</span> <span class="s1">'/scratch/mxnet'</span>
</pre></div>
</div>
<p>Download and unzip:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">os</span><span class="o">.</span><span class="n">system</span><span class="p">(</span><span class="s1">'wget http://www.vision.caltech.edu/Image_Datasets/Caltech101/101_ObjectCategories.tar.gz -P data/'</span><span class="p">)</span>
<span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="s1">'data'</span><span class="p">)</span>
<span class="n">os</span><span class="o">.</span><span class="n">system</span><span class="p">(</span><span class="s1">'tar -xf 101_ObjectCategories.tar.gz'</span><span class="p">)</span>
<span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="s1">'../'</span><span class="p">)</span>
</pre></div>
</div>
<p>Let’s take a look at the data. As you can see, under the
<a class="reference external" href="http://mxnet.io/tutorials/basic/data/101_ObjectCategories">root folder</a> every category has a
<a class="reference external" href="http://mxnet.io/tutorials/basic/data/101_ObjectCategories/yin_yang">subfolder</a>.</p>
<p>Now let’s convert them into record io format. First we need to make a list that
contains all the image files and their categories:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">os</span><span class="o">.</span><span class="n">system</span><span class="p">(</span><span class="s1">'python </span><span class="si">%s</span><span class="s1">/tools/im2rec.py --list=1 --recursive=1 --shuffle=1 --test-ratio=0.2 data/caltech data/101_ObjectCategories'</span><span class="o">%</span><span class="n">MXNET_HOME</span><span class="p">)</span>
</pre></div>
</div>
<p>The resulting <a class="reference external" href="http://mxnet.io/tutorials/basic/data/caltech_train.lst">list file</a> is in the format
<code class="docutils literal"><span class="pre">index\t(one</span> <span class="pre">or</span> <span class="pre">more</span> <span class="pre">label)\tpath</span></code>. In this case there is only one label for
each image but you can modify the list to add in more for multi label training.</p>
<p>Then we can use this list to create our record io file:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">os</span><span class="o">.</span><span class="n">system</span><span class="p">(</span><span class="s2">"python </span><span class="si">%s</span><span class="s2">/tools/im2rec.py --num-thread=4 --pass-through=1 data/caltech data/101_ObjectCategories"</span><span class="o">%</span><span class="n">MXNET_HOME</span><span class="p">)</span>
</pre></div>
</div>
<p>The record io files are now saved at <a class="reference external" href="http://mxnet.io/tutorials/basic/data">here</a></p>
</div>
<div class="section" id="imagerecorditer">
<span id="imagerecorditer"></span><h2>ImageRecordIter<a class="headerlink" href="#imagerecorditer" title="Permalink to this headline"></a></h2>
<p><code class="docutils literal"><span class="pre">mx.io.ImageRecordIter</span></code> can be used for loading image data saved in record io
format. It is available in all frontend languages, but as it’s implemented in
C++, it is less flexible.</p>
<p>To use ImageRecordIter, simply create an instance by loading your record file:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">data_iter</span> <span class="o">=</span> <span class="n">mx</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">ImageRecordIter</span><span class="p">(</span>
<span class="n">path_imgrec</span><span class="o">=</span><span class="s2">"./data/caltech_train.rec"</span><span class="p">,</span> <span class="c1"># the target record file</span>
<span class="n">data_shape</span><span class="o">=</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">227</span><span class="p">,</span> <span class="mi">227</span><span class="p">),</span> <span class="c1"># output data shape. An 227x227 region will be cropped from the original image.</span>
<span class="n">batch_size</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="c1"># number of samples per batch</span>
<span class="n">resize</span><span class="o">=</span><span class="mi">256</span> <span class="c1"># resize the shorter edge to 256 before cropping</span>
<span class="c1"># ... you can add more augumentation options here. use help(mx.io.ImageRecordIter) to see all possible choices</span>
<span class="p">)</span>
<span class="n">data_iter</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>
<span class="n">batch</span> <span class="o">=</span> <span class="n">data_iter</span><span class="o">.</span><span class="n">next</span><span class="p">()</span>
<span class="n">data</span> <span class="o">=</span> <span class="n">batch</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="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">):</span>
<span class="n">plt</span><span class="o">.</span><span class="n">subplot</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span><span class="mi">4</span><span class="p">,</span><span class="n">i</span><span class="o">+</span><span class="mi">1</span><span class="p">)</span>
<span class="n">plt</span><span class="o">.</span><span class="n">imshow</span><span class="p">(</span><span class="n">data</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">asnumpy</span><span class="p">()</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span><span class="o">.</span><span class="n">transpose</span><span class="p">((</span><span class="mi">1</span><span class="p">,</span><span class="mi">2</span><span class="p">,</span><span class="mi">0</span><span class="p">)))</span>
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
<div class="btn-group" role="group">
<div class="download_btn"><a download="image_io_python.ipynb" href="image_io_python.ipynb"><span class="glyphicon glyphicon-download-alt"></span> image_io_python.ipynb</a></div></div></div>
</div>
<div class="container">
<div class="footer">
<p> © 2015-2017 DMLC. All rights reserved. </p>
</div>
</div>
</div>
<div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
<h3><a href="../../index.html">Table Of Contents</a></h3>
<ul>
<li><a class="reference internal" href="#">Image IO - Loading and pre-processing images</a><ul>
<li><a class="reference internal" href="#recordio">RecordIO</a></li>
<li><a class="reference internal" href="#imagerecorditer">ImageRecordIter</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div> <!-- pagename != index -->
<script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script>
<script src="../../_static/js/sidebar.js" type="text/javascript"></script>
<script src="../../_static/js/search.js" type="text/javascript"></script>
<script src="../../_static/js/navbar.js" type="text/javascript"></script>
<script src="../../_static/js/clipboard.min.js" type="text/javascript"></script>
<script src="../../_static/js/copycode.js" type="text/javascript"></script>
<script type="text/javascript">
$('body').ready(function () {
$('body').css('visibility', 'visible');
});
</script>
</div></body>
</html>