data.html



<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
  <meta charset="utf-8">
  
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  
  <title>Data Reader Interface and DataSets &mdash; PaddlePaddle  文档</title>
  

    <link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" />
  

        <link rel="index" title="索引"
              href="../../genindex.html"/>
        <link rel="search" title="搜索" href="../../search.html"/>
    <link rel="top" title="PaddlePaddle  文档" href="../../index.html"/>
        <link rel="up" title="API" href="../index_cn.html"/>
        <link rel="next" title="Training and Inference" href="run_logic.html"/>
        <link rel="prev" title="Parameter Attribute" href="config/attr.html"/> 

  <link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
  <link rel="stylesheet" href="../../_static/css/override.css" type="text/css" />
  <script>
  var _hmt = _hmt || [];
  (function() {
    var hm = document.createElement("script");
    hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
    var s = document.getElementsByTagName("script")[0]; 
    s.parentNode.insertBefore(hm, s);
  })();
  </script>

  
  <script src="../../_static/js/modernizr.min.js"></script>

</head>

<body class="wy-body-for-nav" role="document">

  
  <header class="site-header">
    <div class="site-logo">
      <a href="/"><img src="../../_static/images/PP_w.png"></a>
    </div>
    <div class="site-nav-links">
      <div class="site-menu">
        <a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Fork me on Github</a>
        <div class="language-switcher dropdown">
          <a type="button" data-toggle="dropdown">
            <span>English</span>
            <i class="fa fa-angle-up"></i>
            <i class="fa fa-angle-down"></i>
          </a>
          <ul class="dropdown-menu">
            <li><a href="/doc_cn">中文</a></li>
            <li><a href="/doc">English</a></li>
          </ul>
        </div>
        <ul class="site-page-links">
          <li><a href="/">Home</a></li>
        </ul>
      </div>
      <div class="doc-module">
        
        <ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../getstarted/index_cn.html">新手入门</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../howto/index_cn.html">进阶指南</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../index_cn.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../faq/index_cn.html">FAQ</a></li>
</ul>

        
<div role="search">
  <form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
    <input type="text" name="q" placeholder="Search docs" />
    <input type="hidden" name="check_keywords" value="yes" />
    <input type="hidden" name="area" value="default" />
  </form>
</div>        
      </div>
    </div>
  </header>
  
  <div class="main-content-wrap">

    
    <nav class="doc-menu-vertical" role="navigation">
        
          
          <ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../getstarted/index_cn.html">新手入门</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../getstarted/build_and_install/index_cn.html">安装与编译</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/docker_install_cn.html">PaddlePaddle的Docker容器使用方式</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/ubuntu_install_cn.html">Ubuntu部署PaddlePaddle</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/cmake/build_from_source_cn.html">PaddlePaddle的编译选项</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../getstarted/concepts/use_concepts_cn.html">基本使用概念</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../howto/index_cn.html">进阶指南</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/cmd_parameter/index_cn.html">设置命令行参数</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/use_case_cn.html">使用案例</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/arguments_cn.html">参数概述</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/detail_introduction_cn.html">细节描述</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/cluster/cluster_train_cn.html">运行分布式训练</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_basis_cn.html">Kubernetes 简介</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_cn.html">Kubernetes单机训练</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/usage/k8s/k8s_distributed_cn.html">Kubernetes分布式训练</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_cn.html">GPU性能分析与调优</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../index_cn.html">API</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="model_configs.html">模型配置</a><ul>
<li class="toctree-l3"><a class="reference internal" href="config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="config/evaluators.html">Evaluators</a></li>
<li class="toctree-l3"><a class="reference internal" href="config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">数据访问</a></li>
<li class="toctree-l2"><a class="reference internal" href="run_logic.html">训练与应用</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../faq/index_cn.html">FAQ</a></li>
</ul>

        
    </nav>
    
    <section class="doc-content-wrap">

      
<div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
      
        <li><a href="../index_cn.html">API</a> > </li>
      
    <li>Data Reader Interface and DataSets</li>
  </ul>
</div>
      
      <div class="wy-nav-content" id="doc-content">
        <div class="rst-content">
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
            
  <div class="section" id="data-reader-interface-and-datasets">
<h1>Data Reader Interface and DataSets<a class="headerlink" href="#data-reader-interface-and-datasets" title="永久链接至标题">¶</a></h1>
<div class="section" id="datatypes">
<h2>DataTypes<a class="headerlink" href="#datatypes" title="永久链接至标题">¶</a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">dense_array</code><span class="sig-paren">(</span><em>dim</em>, <em>seq_type=0</em><span class="sig-paren">)</span></dt>
<dd><p>Dense Array. It means the input feature is dense array with float type.
For example, if the input is an image with 28*28 pixels, the input of
Paddle neural network could be a dense vector with dimension 784 or a
numpy array with shape (28, 28).</p>
<p>For the 2-D convolution operation, each sample in one mini-batch must have
the similarly size in PaddlePaddle now. But, it supports variable-dimension
feature across mini-batch. For the variable-dimension, the param dim is not
used. While the data reader must yield numpy array and the data feeder will
set the data shape correctly.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>dim</strong> (<em>int</em>) &#8211; dimension of this vector.</li>
<li><strong>seq_type</strong> (<em>int</em>) &#8211; sequence type of input.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">An input type object.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">InputType</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">dense_vector</code><span class="sig-paren">(</span><em>dim</em>, <em>seq_type=0</em><span class="sig-paren">)</span></dt>
<dd><p>Dense Array. It means the input feature is dense array with float type.
For example, if the input is an image with 28*28 pixels, the input of
Paddle neural network could be a dense vector with dimension 784 or a
numpy array with shape (28, 28).</p>
<p>For the 2-D convolution operation, each sample in one mini-batch must have
the similarly size in PaddlePaddle now. But, it supports variable-dimension
feature across mini-batch. For the variable-dimension, the param dim is not
used. While the data reader must yield numpy array and the data feeder will
set the data shape correctly.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>dim</strong> (<em>int</em>) &#8211; dimension of this vector.</li>
<li><strong>seq_type</strong> (<em>int</em>) &#8211; sequence type of input.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">An input type object.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">InputType</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">dense_vector_sequence</code><span class="sig-paren">(</span><em>dim</em><span class="sig-paren">)</span></dt>
<dd><p>Data type of a sequence of dense vector.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>dim</strong> (<em>int</em>) &#8211; dimension of dense vector.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">An input type object</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body">InputType</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">integer_value</code><span class="sig-paren">(</span><em>value_range</em>, <em>seq_type=0</em><span class="sig-paren">)</span></dt>
<dd><p>Data type of integer.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>seq_type</strong> (<em>int</em>) &#8211; sequence type of this input.</li>
<li><strong>value_range</strong> (<em>int</em>) &#8211; range of this integer.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">An input type object</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">InputType</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">integer_value_sequence</code><span class="sig-paren">(</span><em>value_range</em><span class="sig-paren">)</span></dt>
<dd><p>Data type of a sequence of integer.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>value_range</strong> (<em>int</em>) &#8211; range of each element.</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">sparse_binary_vector</code><span class="sig-paren">(</span><em>dim</em>, <em>seq_type=0</em><span class="sig-paren">)</span></dt>
<dd><p>Sparse binary vector. It means the input feature is a sparse vector and the
every element in this vector is either zero or one.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>dim</strong> (<em>int</em>) &#8211; dimension of this vector.</li>
<li><strong>seq_type</strong> (<em>int</em>) &#8211; sequence type of this input.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">An input type object.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">InputType</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">sparse_binary_vector_sequence</code><span class="sig-paren">(</span><em>dim</em><span class="sig-paren">)</span></dt>
<dd><dl class="docutils">
<dt>Data type of a sequence of sparse vector, which every element is either zero</dt>
<dd>or one.</dd>
</dl>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>dim</strong> (<em>int</em>) &#8211; dimension of sparse vector.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">An input type object</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body">InputType</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">sparse_non_value_slot</code><span class="sig-paren">(</span><em>dim</em>, <em>seq_type=0</em><span class="sig-paren">)</span></dt>
<dd><p>Sparse binary vector. It means the input feature is a sparse vector and the
every element in this vector is either zero or one.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>dim</strong> (<em>int</em>) &#8211; dimension of this vector.</li>
<li><strong>seq_type</strong> (<em>int</em>) &#8211; sequence type of this input.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">An input type object.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">InputType</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">sparse_value_slot</code><span class="sig-paren">(</span><em>dim</em>, <em>seq_type=0</em><span class="sig-paren">)</span></dt>
<dd><p>Sparse vector. It means the input feature is a sparse vector. Most of the
elements in this vector are zero, others could be any float value.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>dim</strong> (<em>int</em>) &#8211; dimension of this vector.</li>
<li><strong>seq_type</strong> (<em>int</em>) &#8211; sequence type of this input.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">An input type object.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">InputType</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">sparse_vector</code><span class="sig-paren">(</span><em>dim</em>, <em>seq_type=0</em><span class="sig-paren">)</span></dt>
<dd><p>Sparse vector. It means the input feature is a sparse vector. Most of the
elements in this vector are zero, others could be any float value.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>dim</strong> (<em>int</em>) &#8211; dimension of this vector.</li>
<li><strong>seq_type</strong> (<em>int</em>) &#8211; sequence type of this input.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">An input type object.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">InputType</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.data_type.</code><code class="descname">sparse_vector_sequence</code><span class="sig-paren">(</span><em>dim</em><span class="sig-paren">)</span></dt>
<dd><p>Data type of a sequence of sparse vector, which most elements are zero,
others could be any float value.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>dim</strong> (<em>int</em>) &#8211; dimension of sparse vector.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">An input type object</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body">InputType</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.data_type.</code><code class="descname">InputType</code><span class="sig-paren">(</span><em>dim</em>, <em>seq_type</em>, <em>tp</em><span class="sig-paren">)</span></dt>
<dd><p>InputType is the base class for paddle input types.</p>
<div class="admonition note">
<p class="first admonition-title">注解</p>
<p class="last">this is a base class, and should never be used by user.</p>
</div>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple">
<li><strong>dim</strong> (<em>int</em>) &#8211; dimension of input. If the input is an integer, it means the
value range. Otherwise, it means the size of layer.</li>
<li><strong>seq_type</strong> (<em>int</em>) &#8211; sequence type of input. 0 means it is not a sequence. 1
means it is a variable length sequence. 2 means it is a
nested sequence.</li>
<li><strong>type</strong> (<em>int</em>) &#8211; data type of input.</li>
</ul>
</td>
</tr>
</tbody>
</table>
</dd></dl>

</div>
<div class="section" id="datafeeder">
<h2>DataFeeder<a class="headerlink" href="#datafeeder" title="永久链接至标题">¶</a></h2>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.data_feeder.</code><code class="descname">DataFeeder</code><span class="sig-paren">(</span><em>data_types</em>, <em>feeding=None</em><span class="sig-paren">)</span></dt>
<dd><p>DataFeeder converts the data returned by paddle.reader into a data structure
of Arguments which is defined in the API. The paddle.reader usually returns
a list of mini-batch data entries. Each data entry in the list is one sample.
Each sample is a list or a tuple with one feature or multiple features.
DataFeeder converts this mini-batch data entries into Arguments in order
to feed it to C++ interface.</p>
<p>The simple usage shows below</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">feeding</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;image&#39;</span><span class="p">,</span> <span class="s1">&#39;label&#39;</span><span class="p">]</span>
<span class="n">data_types</span> <span class="o">=</span> <span class="n">enumerate_data_types_of_data_layers</span><span class="p">(</span><span class="n">topology</span><span class="p">)</span>
<span class="n">feeder</span> <span class="o">=</span> <span class="n">DataFeeder</span><span class="p">(</span><span class="n">data_types</span><span class="o">=</span><span class="n">data_types</span><span class="p">,</span> <span class="n">feeding</span><span class="o">=</span><span class="n">feeding</span><span class="p">)</span>

<span class="n">minibatch_data</span> <span class="o">=</span> <span class="p">[([</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">2.0</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">,</span> <span class="o">...</span><span class="p">],</span> <span class="mi">5</span><span class="p">)]</span>

<span class="n">arg</span> <span class="o">=</span> <span class="n">feeder</span><span class="p">(</span><span class="n">minibatch_data</span><span class="p">)</span>
</pre></div>
</div>
<p>If mini-batch data and data layers are not one to one mapping, we
could pass a dictionary to feeding parameter to represent the mapping
relationship.</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">data_types</span> <span class="o">=</span> <span class="p">[(</span><span class="s1">&#39;image&#39;</span><span class="p">,</span> <span class="n">paddle</span><span class="o">.</span><span class="n">data_type</span><span class="o">.</span><span class="n">dense_vector</span><span class="p">(</span><span class="mi">784</span><span class="p">)),</span>
              <span class="p">(</span><span class="s1">&#39;label&#39;</span><span class="p">,</span> <span class="n">paddle</span><span class="o">.</span><span class="n">data_type</span><span class="o">.</span><span class="n">integer_value</span><span class="p">(</span><span class="mi">10</span><span class="p">))]</span>
<span class="n">feeding</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;image&#39;</span><span class="p">:</span><span class="mi">0</span><span class="p">,</span> <span class="s1">&#39;label&#39;</span><span class="p">:</span><span class="mi">1</span><span class="p">}</span>
<span class="n">feeder</span> <span class="o">=</span> <span class="n">DataFeeder</span><span class="p">(</span><span class="n">data_types</span><span class="o">=</span><span class="n">data_types</span><span class="p">,</span> <span class="n">feeding</span><span class="o">=</span><span class="n">feeding</span><span class="p">)</span>
<span class="n">minibatch_data</span> <span class="o">=</span> <span class="p">[</span>
                   <span class="p">(</span> <span class="p">[</span><span class="mf">1.0</span><span class="p">,</span><span class="mf">2.0</span><span class="p">,</span><span class="mf">3.0</span><span class="p">,</span><span class="mf">4.0</span><span class="p">],</span> <span class="mi">5</span><span class="p">,</span> <span class="p">[</span><span class="mi">6</span><span class="p">,</span><span class="mi">7</span><span class="p">,</span><span class="mi">8</span><span class="p">]</span> <span class="p">),</span>  <span class="c1"># first sample</span>
                   <span class="p">(</span> <span class="p">[</span><span class="mf">1.0</span><span class="p">,</span><span class="mf">2.0</span><span class="p">,</span><span class="mf">3.0</span><span class="p">,</span><span class="mf">4.0</span><span class="p">],</span> <span class="mi">5</span><span class="p">,</span> <span class="p">[</span><span class="mi">6</span><span class="p">,</span><span class="mi">7</span><span class="p">,</span><span class="mi">8</span><span class="p">]</span> <span class="p">)</span>   <span class="c1"># second sample</span>
                 <span class="p">]</span>
<span class="c1"># or minibatch_data = [</span>
<span class="c1">#                       [ [1.0,2.0,3.0,4.0], 5, [6,7,8] ],  # first sample</span>
<span class="c1">#                       [ [1.0,2.0,3.0,4.0], 5, [6,7,8] ]   # second sample</span>
<span class="c1">#                     ]</span>
<span class="n">arg</span> <span class="o">=</span> <span class="n">feeder</span><span class="o">.</span><span class="n">convert</span><span class="p">(</span><span class="n">minibatch_data</span><span class="p">)</span>
</pre></div>
</div>
<div class="admonition note">
<p class="first admonition-title">注解</p>
<p class="last">This module is for internal use only. Users should use the <cite>reader</cite>
interface.</p>
</div>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple">
<li><strong>data_types</strong> (<em>list</em>) &#8211; A list to specify data name and type. Each item is
a tuple of (data_name, data_type).</li>
<li><strong>feeding</strong> (<em>dict|collections.Sequence|None</em>) &#8211; A dictionary or a sequence to specify the position of each
data in the input data.</li>
</ul>
</td>
</tr>
</tbody>
</table>
<dl class="method">
<dt>
<code class="descname">convert</code><span class="sig-paren">(</span><em>dat</em>, <em>argument=None</em><span class="sig-paren">)</span></dt>
<dd><table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple">
<li><strong>dat</strong> (<em>list</em>) &#8211; A list of mini-batch data. Each sample is a list or tuple
one feature or multiple features.</li>
<li><strong>argument</strong> (<em>py_paddle.swig_paddle.Arguments</em>) &#8211; An Arguments object contains this mini-batch data with
one or multiple features. The Arguments definition is
in the API.</li>
</ul>
</td>
</tr>
</tbody>
</table>
</dd></dl>

</dd></dl>

</div>
<div class="section" id="reader">
<h2>Reader<a class="headerlink" href="#reader" title="永久链接至标题">¶</a></h2>
<p>At training and testing time, PaddlePaddle programs need to read data. To ease
the users&#8217; work to write data reading code, we define that</p>
<ul class="simple">
<li>A <em>reader</em> is a function that reads data (from file, network, random number
generator, etc) and yields data items.</li>
<li>A <em>reader creator</em> is a function that returns a reader function.</li>
<li>A <em>reader decorator</em> is a function, which accepts one or more readers, and
returns a reader.</li>
<li>A <em>batch reader</em> is a function that reads data (from <em>reader</em>, file, network,
random number generator, etc) and yields a batch of data items.</li>
</ul>
<div class="section" id="data-reader-interface">
<h3>Data Reader Interface<a class="headerlink" href="#data-reader-interface" title="永久链接至标题">¶</a></h3>
<p>Indeed, <em>data reader</em> doesn&#8217;t have to be a function that reads and yields data
items. It can be any function with no parameter that creates a iterable
(anything can be used in <code class="code docutils literal"><span class="pre">for</span> <span class="pre">x</span> <span class="pre">in</span> <span class="pre">iterable</span></code>):</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">iterable</span> <span class="o">=</span> <span class="n">data_reader</span><span class="p">()</span>
</pre></div>
</div>
<p>Element produced from the iterable should be a <strong>single</strong> entry of data,
<strong>not</strong> a mini batch. That entry of data could be a single item, or a tuple of
items.
Item should be of <a class="reference external" href="http://www.paddlepaddle.org/doc/ui/data_provider/pydataprovider2.html?highlight=dense_vector#input-types">supported type</a> (e.g., numpy 1d
array of float32, int, list of int)</p>
<p>An example implementation for single item data reader creator:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">reader_creator_random_image</span><span class="p">(</span><span class="n">width</span><span class="p">,</span> <span class="n">height</span><span class="p">):</span>
    <span class="k">def</span> <span class="nf">reader</span><span class="p">():</span>
        <span class="k">while</span> <span class="bp">True</span><span class="p">:</span>
            <span class="k">yield</span> <span class="n">numpy</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">width</span><span class="o">*</span><span class="n">height</span><span class="p">)</span>
<span class="k">return</span> <span class="n">reader</span>
</pre></div>
</div>
<p>An example implementation for multiple item data reader creator:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">reader_creator_random_image_and_label</span><span class="p">(</span><span class="n">width</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">label</span><span class="p">):</span>
    <span class="k">def</span> <span class="nf">reader</span><span class="p">():</span>
        <span class="k">while</span> <span class="bp">True</span><span class="p">:</span>
            <span class="k">yield</span> <span class="n">numpy</span><span class="o">.</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">width</span><span class="o">*</span><span class="n">height</span><span class="p">),</span> <span class="n">label</span>
<span class="k">return</span> <span class="n">reader</span>
</pre></div>
</div>
<p>TODO(yuyang18): Should we add whole design doc here?</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.</code><code class="descname">map_readers</code><span class="sig-paren">(</span><em>func</em>, <em>*readers</em><span class="sig-paren">)</span></dt>
<dd><p>Creates a data reader that outputs return value of function using
output of each data readers as arguments.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>func</strong> &#8211; function to use. The type of func should be (Sample) =&gt; Sample</li>
<li><strong>readers</strong> &#8211; readers whose outputs will be used as arguments of func.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Type:</th><td class="field-body"><p class="first">callable</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body"><p class="first">the created data reader.</p>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">callable</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.</code><code class="descname">buffered</code><span class="sig-paren">(</span><em>reader</em>, <em>size</em><span class="sig-paren">)</span></dt>
<dd><p>Creates a buffered data reader.</p>
<p>The buffered data reader will read and save data entries into a
buffer. Reading from the buffered data reader will proceed as long
as the buffer is not empty.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>reader</strong> (<em>callable</em>) &#8211; the data reader to read from.</li>
<li><strong>size</strong> (<em>int</em>) &#8211; max buffer size.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first last">the buffered data reader.</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.</code><code class="descname">compose</code><span class="sig-paren">(</span><em>*readers</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt>
<dd><p>Creates a data reader whose output is the combination of input readers.</p>
<p>If input readers output following data entries:
(1, 2)    3    (4, 5)
The composed reader will output:
(1, 2, 3, 4, 5)</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>readers</strong> &#8211; readers that will be composed together.</li>
<li><strong>check_alignment</strong> (<em>bool</em>) &#8211; if True, will check if input readers are aligned
correctly. If False, will not check alignment and trailing outputs
will be discarded. Defaults to True.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">the new data reader.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">引发:</th><td class="field-body"><p class="first last"><strong>ComposeNotAligned</strong> &#8211; outputs of readers are not aligned.
Will not raise when check_alignment is set to False.</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.</code><code class="descname">chain</code><span class="sig-paren">(</span><em>*readers</em><span class="sig-paren">)</span></dt>
<dd><p>Creates a data reader whose output is the outputs of input data
readers chained together.</p>
<p>If input readers output following data entries:
[0, 0, 0]
[1, 1, 1]
[2, 2, 2]
The chained reader will output:
[0, 0, 0, 1, 1, 1, 2, 2, 2]</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>readers</strong> &#8211; input readers.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">the new data reader.</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.</code><code class="descname">shuffle</code><span class="sig-paren">(</span><em>reader</em>, <em>buf_size</em><span class="sig-paren">)</span></dt>
<dd><p>Creates a data reader whose data output is shuffled.</p>
<p>Output from the iterator that created by original reader will be
buffered into shuffle buffer, and then shuffled. The size of shuffle buffer
is determined by argument buf_size.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>reader</strong> (<em>callable</em>) &#8211; the original reader whose output will be shuffled.</li>
<li><strong>buf_size</strong> (<em>int</em>) &#8211; shuffle buffer size.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">the new reader whose output is shuffled.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">callable</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.</code><code class="descname">firstn</code><span class="sig-paren">(</span><em>reader</em>, <em>n</em><span class="sig-paren">)</span></dt>
<dd><p>Limit the max number of samples that reader could return.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>reader</strong> (<em>callable</em>) &#8211; the data reader to read from.</li>
<li><strong>n</strong> (<em>int</em>) &#8211; the max number of samples that return.</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">the decorated reader.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">callable</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.</code><code class="descname">xmap_readers</code><span class="sig-paren">(</span><em>mapper</em>, <em>reader</em>, <em>process_num</em>, <em>buffer_size</em>, <em>order=False</em><span class="sig-paren">)</span></dt>
<dd><p>Use multiprocess to map samples from reader by a mapper defined by user.
And this function contains a buffered decorator.
:param mapper:  a function to map sample.
:type mapper: callable
:param reader: the data reader to read from
:type reader: callable
:param process_num: process number to handle original sample
:type process_num: int
:param buffer_size: max buffer size
:type buffer_size: int
:param order: keep the order of reader
:type order: bool
:return: the decarated reader
:rtype: callable</p>
</dd></dl>

</div>
<p>Creator package contains some simple reader creator, which could
be used in user program.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.creator.</code><code class="descname">np_array</code><span class="sig-paren">(</span><em>x</em><span class="sig-paren">)</span></dt>
<dd><p>Creates a reader that yields elements of x, if it is a
numpy vector. Or rows of x, if it is a numpy matrix.
Or any sub-hyperplane indexed by the highest dimension.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>x</strong> &#8211; the numpy array to create reader from.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">data reader created from x.</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.creator.</code><code class="descname">text_file</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Creates a data reader that outputs text line by line from given text file.
Trailing new line (&#8216;\n&#8217;) of each line will be removed.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Path:</th><td class="field-body">path of the text file.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">data reader of text file</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.reader.creator.</code><code class="descname">cloud_reader</code><span class="sig-paren">(</span><em>paths</em>, <em>etcd_endpoints</em>, <em>timeout_sec=5</em>, <em>buf_size=64</em><span class="sig-paren">)</span></dt>
<dd><dl class="docutils">
<dt>Create a data reader that yield a record one by one from</dt>
<dd>the paths:</dd>
</dl>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Path:</th><td class="field-body">path of recordio files.</td>
</tr>
<tr class="field-even field"><th class="field-name">Etcd_endpoints:</th><td class="field-body">the endpoints for etcd cluster</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">data reader of recordio files.</td>
</tr>
</tbody>
</table>
</dd></dl>

</div>
<div class="section" id="minibatch">
<h2>minibatch<a class="headerlink" href="#minibatch" title="永久链接至标题">¶</a></h2>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.minibatch.</code><code class="descname">batch</code><span class="sig-paren">(</span><em>reader</em>, <em>batch_size</em><span class="sig-paren">)</span></dt>
<dd><p>Create a batched reader.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>reader</strong> (<em>callable</em>) &#8211; the data reader to read from.</li>
<li><strong>batch_size</strong> (<em>int</em>) &#8211; size of each mini-batch</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">the batched reader.</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">callable</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

</div>
<div class="section" id="dataset">
<h2>Dataset<a class="headerlink" href="#dataset" title="永久链接至标题">¶</a></h2>
<p>Dataset package.</p>
<div class="section" id="mnist">
<h3>mnist<a class="headerlink" href="#mnist" title="永久链接至标题">¶</a></h3>
<p>MNIST dataset.</p>
<p>This module will download dataset from <a class="reference external" href="http://yann.lecun.com/exdb/mnist/">http://yann.lecun.com/exdb/mnist/</a> and
parse training set and test set into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.mnist.</code><code class="descname">train</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>MNIST training set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.mnist.</code><code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>MNIST test set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Test reader creator.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.mnist.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>

</div>
<div class="section" id="cifar">
<h3>cifar<a class="headerlink" href="#cifar" title="永久链接至标题">¶</a></h3>
<p>CIFAR dataset.</p>
<p>This module will download dataset from
<a class="reference external" href="https://www.cs.toronto.edu/~kriz/cifar.html">https://www.cs.toronto.edu/~kriz/cifar.html</a> and parse train/test set into
paddle reader creators.</p>
<p>The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes,
with 6000 images per class. There are 50000 training images and 10000 test
images.</p>
<p>The CIFAR-100 dataset is just like the CIFAR-10, except it has 100 classes
containing 600 images each. There are 500 training images and 100 testing
images per class.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">train100</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>CIFAR-100 training set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 99].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">test100</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>CIFAR-100 test set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Test reader creator.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">train10</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>CIFAR-10 training set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">test10</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>CIFAR-10 test set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Test reader creator.</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>

</div>
<div class="section" id="conll05">
<h3>conll05<a class="headerlink" href="#conll05" title="永久链接至标题">¶</a></h3>
<p>Conll05 dataset.
Paddle semantic role labeling Book and demo use this dataset as an example.
Because Conll05 is not free in public, the default downloaded URL is test set
of Conll05 (which is public). Users can change URL and MD5 to their Conll
dataset. And a pre-trained word vector model based on Wikipedia corpus is used
to initialize SRL model.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.conll05.</code><code class="descname">get_dict</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the word, verb and label dictionary of Wikipedia corpus.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.conll05.</code><code class="descname">get_embedding</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the trained word vector based on Wikipedia corpus.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.conll05.</code><code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Conll05 test set creator.</p>
<p>Because the training dataset is not free, the test dataset is used for
training. It returns a reader creator, each sample in the reader is nine
features, including sentence sequence, predicate, predicate context,
predicate context flag and tagged sequence.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

</div>
<div class="section" id="imdb">
<h3>imdb<a class="headerlink" href="#imdb" title="永久链接至标题">¶</a></h3>
<p>IMDB dataset.</p>
<p>This module downloads IMDB dataset from
<a class="reference external" href="http://ai.stanford.edu/%7Eamaas/data/sentiment/">http://ai.stanford.edu/%7Eamaas/data/sentiment/</a>. This dataset contains a set
of 25,000 highly polar movie reviews for training, and 25,000 for testing.
Besides, this module also provides API for building dictionary.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imdb.</code><code class="descname">build_dict</code><span class="sig-paren">(</span><em>pattern</em>, <em>cutoff</em><span class="sig-paren">)</span></dt>
<dd><p>Build a word dictionary from the corpus. Keys of the dictionary are words,
and values are zero-based IDs of these words.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imdb.</code><code class="descname">train</code><span class="sig-paren">(</span><em>word_idx</em><span class="sig-paren">)</span></dt>
<dd><p>IMDB training set creator.</p>
<p>It returns a reader creator, each sample in the reader is an zero-based ID
sequence and label in [0, 1].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>word_idx</strong> (<em>dict</em>) &#8211; word dictionary</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imdb.</code><code class="descname">test</code><span class="sig-paren">(</span><em>word_idx</em><span class="sig-paren">)</span></dt>
<dd><p>IMDB test set creator.</p>
<p>It returns a reader creator, each sample in the reader is an zero-based ID
sequence and label in [0, 1].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><strong>word_idx</strong> (<em>dict</em>) &#8211; word dictionary</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body">Test reader creator</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imdb.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>

</div>
<div class="section" id="imikolov">
<h3>imikolov<a class="headerlink" href="#imikolov" title="永久链接至标题">¶</a></h3>
<p>imikolov&#8217;s simple dataset.</p>
<p>This module will download dataset from
<a class="reference external" href="http://www.fit.vutbr.cz/~imikolov/rnnlm/">http://www.fit.vutbr.cz/~imikolov/rnnlm/</a> and parse training set and test set
into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imikolov.</code><code class="descname">build_dict</code><span class="sig-paren">(</span><em>min_word_freq=50</em><span class="sig-paren">)</span></dt>
<dd><p>Build a word dictionary from the corpus,  Keys of the dictionary are words,
and values are zero-based IDs of these words.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imikolov.</code><code class="descname">train</code><span class="sig-paren">(</span><em>word_idx</em>, <em>n</em>, <em>data_type=1</em><span class="sig-paren">)</span></dt>
<dd><p>imikolov training set creator.</p>
<p>It returns a reader creator, each sample in the reader is a word ID
tuple.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>word_idx</strong> (<em>dict</em>) &#8211; word dictionary</li>
<li><strong>n</strong> (<em>int</em>) &#8211; sliding window size if type is ngram, otherwise max length of sequence</li>
<li><strong>data_type</strong> (<em>member variable of DataType</em><em> (</em><em>NGRAM</em><em> or </em><em>SEQ</em><em>)</em>) &#8211; data type (ngram or sequence)</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">Training reader creator</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">callable</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imikolov.</code><code class="descname">test</code><span class="sig-paren">(</span><em>word_idx</em>, <em>n</em>, <em>data_type=1</em><span class="sig-paren">)</span></dt>
<dd><p>imikolov test set creator.</p>
<p>It returns a reader creator, each sample in the reader is a word ID
tuple.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first simple">
<li><strong>word_idx</strong> (<em>dict</em>) &#8211; word dictionary</li>
<li><strong>n</strong> (<em>int</em>) &#8211; sliding window size if type is ngram, otherwise max length of sequence</li>
<li><strong>data_type</strong> (<em>member variable of DataType</em><em> (</em><em>NGRAM</em><em> or </em><em>SEQ</em><em>)</em>) &#8211; data type (ngram or sequence)</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">返回:</th><td class="field-body"><p class="first">Test reader creator</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">返回类型:</th><td class="field-body"><p class="first last">callable</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imikolov.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>

</div>
<div class="section" id="movielens">
<h3>movielens<a class="headerlink" href="#movielens" title="永久链接至标题">¶</a></h3>
<p>Movielens 1-M dataset.</p>
<p>Movielens 1-M dataset contains 1 million ratings from 6000 users on 4000
movies, which was collected by GroupLens Research. This module will download
Movielens 1-M dataset from
<a class="reference external" href="http://files.grouplens.org/datasets/movielens/ml-1m.zip">http://files.grouplens.org/datasets/movielens/ml-1m.zip</a> and parse training
set and test set into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">get_movie_title_dict</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get movie title dictionary.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">max_movie_id</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the maximum value of movie id.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">max_user_id</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the maximum value of user id.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">max_job_id</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the maximum value of job id.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">movie_categories</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get movie categoriges dictionary.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">user_info</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get user info dictionary.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">movie_info</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get movie info dictionary.</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>

<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">MovieInfo</code><span class="sig-paren">(</span><em>index</em>, <em>categories</em>, <em>title</em><span class="sig-paren">)</span></dt>
<dd><p>Movie id, title and categories information are stored in MovieInfo.</p>
</dd></dl>

<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">UserInfo</code><span class="sig-paren">(</span><em>index</em>, <em>gender</em>, <em>age</em>, <em>job_id</em><span class="sig-paren">)</span></dt>
<dd><p>User id, gender, age, and job information are stored in UserInfo.</p>
</dd></dl>

</div>
<div class="section" id="sentiment">
<h3>sentiment<a class="headerlink" href="#sentiment" title="永久链接至标题">¶</a></h3>
<p>The script fetch and preprocess movie_reviews data set that provided by NLTK</p>
<p>TODO(yuyang18): Complete dataset.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.sentiment.</code><code class="descname">get_word_dict</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Sorted the words by the frequency of words which occur in sample
:return:</p>
<blockquote>
<div>words_freq_sorted</div></blockquote>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.sentiment.</code><code class="descname">train</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Default training set reader creator</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.sentiment.</code><code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Default test set reader creator</p>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.sentiment.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>

</div>
<div class="section" id="uci-housing">
<h3>uci_housing<a class="headerlink" href="#uci-housing" title="永久链接至标题">¶</a></h3>
<p>UCI Housing dataset.</p>
<p>This module will download dataset from
<a class="reference external" href="https://archive.ics.uci.edu/ml/machine-learning-databases/housing/">https://archive.ics.uci.edu/ml/machine-learning-databases/housing/</a> and
parse training set and test set into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.uci_housing.</code><code class="descname">train</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>UCI_HOUSING training set creator.</p>
<p>It returns a reader creator, each sample in the reader is features after
normalization and price number.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.uci_housing.</code><code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>UCI_HOUSING test set creator.</p>
<p>It returns a reader creator, each sample in the reader is features after
normalization and price number.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Test reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

</div>
<div class="section" id="wmt14">
<h3>wmt14<a class="headerlink" href="#wmt14" title="永久链接至标题">¶</a></h3>
<p>WMT14 dataset.
The original WMT14 dataset is too large and a small set of data for set is
provided. This module will download dataset from
<a class="reference external" href="http://paddlepaddle.cdn.bcebos.com/demo/wmt_shrinked_data/wmt14.tgz">http://paddlepaddle.cdn.bcebos.com/demo/wmt_shrinked_data/wmt14.tgz</a> and
parse training set and test set into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.wmt14.</code><code class="descname">train</code><span class="sig-paren">(</span><em>dict_size</em><span class="sig-paren">)</span></dt>
<dd><p>WMT14 training set creator.</p>
<p>It returns a reader creator, each sample in the reader is source language
word ID sequence, target language word ID sequence and next word ID
sequence.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.wmt14.</code><code class="descname">test</code><span class="sig-paren">(</span><em>dict_size</em><span class="sig-paren">)</span></dt>
<dd><p>WMT14 test set creator.</p>
<p>It returns a reader creator, each sample in the reader is source language
word ID sequence, target language word ID sequence and next word ID
sequence.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">返回:</th><td class="field-body">Test reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">返回类型:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>

<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.wmt14.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>

</div>
</div>
</div>


           </div>
          </div>
          <footer>
  
    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
      
        <a href="run_logic.html" class="btn btn-neutral float-right" title="Training and Inference" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
      
      
        <a href="config/attr.html" class="btn btn-neutral" title="Parameter Attribute" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
      
    </div>
  

  <hr/>

  <div role="contentinfo">
    <p>
        &copy; Copyright 2016, PaddlePaddle developers.

    </p>
  </div>
  Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. 

</footer>

        </div>
      </div>

    </section>

  </div>
  

    <script type="text/javascript">
        var DOCUMENTATION_OPTIONS = {
            URL_ROOT:'../../',
            VERSION:'',
            COLLAPSE_INDEX:false,
            FILE_SUFFIX:'.html',
            HAS_SOURCE:  true,
            SOURCELINK_SUFFIX: ".txt",
        };
    </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="../../_static/translations.js"></script>
      <script type="text/javascript" src="https://cdn.bootcss.com/mathjax/2.7.0/MathJax.js"></script>
       
  
    <script type="text/javascript" src="../../_static/js/theme.js"></script>
  
  
  <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
  <script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
  <script src="../../_static/js/paddle_doc_init.js"></script> 

</body>
</html>