| <!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>Create a Dataset Using RecordIO — 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="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> |
| </ul> |
| </div> |
| </div> |
| <div class="content"> |
| <div class="section" id="create-a-dataset-using-recordio"> |
| <span id="create-a-dataset-using-recordio"></span><h1>Create a Dataset Using RecordIO<a class="headerlink" href="#create-a-dataset-using-recordio" title="Permalink to this headline">¶</a></h1> |
| <p>RecordIO implements a file format for a sequence of records. We recommend storing images as records and packing them together. The benefits include:</p> |
| <ul class="simple"> |
| <li>Storing images in a compact format–e.g., JPEG, for records–greatly reduces the size of the dataset on the disk.</li> |
| <li>Packing data together allows continuous reading on the disk.</li> |
| <li>RecordIO has a simple way to partition, simplifying distributed setting. We provide an example later.</li> |
| </ul> |
| <p>We provide the <a class="reference external" href="https://github.com/dmlc/mxnet/blob/master/tools/im2rec.cc">im2rec tool</a> so you can create an Image RecordIO dataset by yourself. The following walkthrough shows you how.</p> |
| <div class="section" id="prerequisites"> |
| <span id="prerequisites"></span><h2>Prerequisites<a class="headerlink" href="#prerequisites" title="Permalink to this headline">¶</a></h2> |
| <p>Download the data. You don’t need to resize the images manually. You can use <code class="docutils literal"><span class="pre">im2rec</span></code> to resize them automatically. For details, see the “Extension: Using Multiple Labels for a Single Image,” later in this topic.</p> |
| </div> |
| <div class="section" id="step-1-make-an-image-list-file"> |
| <span id="step-1-make-an-image-list-file"></span><h2>Step 1. Make an Image List File<a class="headerlink" href="#step-1-make-an-image-list-file" title="Permalink to this headline">¶</a></h2> |
| <p>After you download the data, you need to make an image list file. The format is:</p> |
| <div class="highlight-python"><div class="highlight"><pre><span></span>integer_image_index \t label_index \t path_to_image |
| </pre></div> |
| </div> |
| <p>Typically, the program takes the list of names of all of the images, shuffles them, then separates them into two lists: a training filename list and a testing filename list. Write the list in the right format.</p> |
| <p>This is an example file:</p> |
| <div class="highlight-bash"><div class="highlight"><pre><span></span><span class="m">95099</span> <span class="m">464</span> n04467665_17283.JPEG |
| <span class="m">10025081</span> <span class="m">412</span> ILSVRC2010_val_00025082.JPEG |
| <span class="m">74181</span> <span class="m">789</span> n01915811_2739.JPEG |
| <span class="m">10035553</span> <span class="m">859</span> ILSVRC2010_val_00035554.JPEG |
| <span class="m">10048727</span> <span class="m">929</span> ILSVRC2010_val_00048728.JPEG |
| <span class="m">94028</span> <span class="m">924</span> n01980166_4956.JPEG |
| <span class="m">1080682</span> <span class="m">650</span> n11807979_571.JPEG |
| <span class="m">972457</span> <span class="m">633</span> n07723039_1627.JPEG |
| <span class="m">7534</span> <span class="m">11</span> n01630670_4486.JPEG |
| <span class="m">1191261</span> <span class="m">249</span> n12407079_5106.JPEG |
| </pre></div> |
| </div> |
| </div> |
| <div class="section" id="step-2-create-the-binary-file"> |
| <span id="step-2-create-the-binary-file"></span><h2>Step 2. Create the Binary File<a class="headerlink" href="#step-2-create-the-binary-file" title="Permalink to this headline">¶</a></h2> |
| <p>To generate a binary image, use <code class="docutils literal"><span class="pre">im2rec</span></code> in the tool folder. <code class="docutils literal"><span class="pre">im2rec</span></code> takes the path of the <code class="docutils literal"><span class="pre">_image</span> <span class="pre">list</span> <span class="pre">file_</span></code> you generated, the <code class="docutils literal"><span class="pre">_root</span> <span class="pre">path_</span></code> of the images, and the <code class="docutils literal"><span class="pre">_output</span> <span class="pre">file</span> <span class="pre">path_</span></code> as input. This process usually takes several hours, so be patient.</p> |
| <p>Sample command:</p> |
| <div class="highlight-bash"><div class="highlight"><pre><span></span>./bin/im2rec image.lst image_root_dir output.bin <span class="nv">resize</span><span class="o">=</span><span class="m">256</span> |
| </pre></div> |
| </div> |
| <p>For more details, run <code class="docutils literal"><span class="pre">./bin/im2rec</span></code>.</p> |
| </div> |
| <div class="section" id="extension-multiple-labels-for-a-single-image"> |
| <span id="extension-multiple-labels-for-a-single-image"></span><h2>Extension: Multiple Labels for a Single Image<a class="headerlink" href="#extension-multiple-labels-for-a-single-image" title="Permalink to this headline">¶</a></h2> |
| <p>The <code class="docutils literal"><span class="pre">im2rec</span></code> tool and <code class="docutils literal"><span class="pre">mx.io.ImageRecordIter</span></code> have multi-label support for a single image. |
| For example, if you have four labels for a single image, you can use the following procedure to use the RecordIO tools.</p> |
| <ol class="simple"> |
| <li>Write the image list files as follows:</li> |
| </ol> |
| <div class="highlight-python"><div class="highlight"><pre><span></span>integer_image_index \t label_1 \t label_2 \t label_3 \t label_4 \t path_to_image |
| </pre></div> |
| </div> |
| <ol class="simple"> |
| <li>Run <code class="docutils literal"><span class="pre">im2rec</span></code>, adding a ‘label_width=4’ to the command argument, for example:</li> |
| </ol> |
| <div class="highlight-bash"><div class="highlight"><pre><span></span>./bin/im2rec image.lst image_root_dir output.bin <span class="nv">resize</span><span class="o">=</span><span class="m">256</span> <span class="nv">label_width</span><span class="o">=</span><span class="m">4</span> |
| </pre></div> |
| </div> |
| <ol class="simple"> |
| <li>In the iterator generation code, set <code class="docutils literal"><span class="pre">label_width=4</span></code> and <code class="docutils literal"><span class="pre">path_imglist=<<The</span> <span class="pre">PATH</span> <span class="pre">TO</span> <span class="pre">YOUR</span> <span class="pre">image.lst>></span></code>, for example:</li> |
| </ol> |
| <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">dataiter</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/cifar/train.rec"</span><span class="p">,</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">28</span><span class="p">,</span><span class="mi">28</span><span class="p">),</span> |
| <span class="n">path_imglist</span><span class="o">=</span><span class="s2">"data/cifar/image.lst"</span><span class="p">,</span> |
| <span class="n">label_width</span><span class="o">=</span><span class="mi">4</span> |
| <span class="p">)</span> |
| </pre></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="#">Create a Dataset Using RecordIO</a><ul> |
| <li><a class="reference internal" href="#prerequisites">Prerequisites</a></li> |
| <li><a class="reference internal" href="#step-1-make-an-image-list-file">Step 1. Make an Image List File</a></li> |
| <li><a class="reference internal" href="#step-2-create-the-binary-file">Step 2. Create the Binary File</a></li> |
| <li><a class="reference internal" href="#extension-multiple-labels-for-a-single-image">Extension: Multiple Labels for a Single Image</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> |