selected_rows.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>Design Doc: Selected Rows &mdash; PaddlePaddle  documentation</title>
  

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

        <link rel="index" title="Index"
              href="../genindex.html"/>
        <link rel="search" title="Search" href="../search.html"/>
    <link rel="top" title="PaddlePaddle  documentation" href="../index.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>
<li class="toctree-l1"><a class="reference internal" href="../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1"><a class="reference internal" href="../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1"><a class="reference internal" href="../api/index_en.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../mobile/index_en.html">MOBILE</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>
<li class="toctree-l1"><a class="reference internal" href="../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/pip_install_en.html">Install Using pip</a></li>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/docker_install_en.html">Run in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/dev/build_en.html">Build using Docker</a></li>
<li class="toctree-l3"><a class="reference internal" href="../getstarted/build_and_install/build_from_source_en.html">Build from Sources</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/cluster/cluster_train_en.html">PaddlePaddle Distributed Training</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_en.html">Paddle On Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/usage/k8s/k8s_aws_en.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/dev/write_docs_en.html">Contribute Documentation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../api/index_en.html">API</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/evaluators.html">Evaluators</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/data.html">Data Reader Interface and DataSets</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/data/data_reader.html">Data Reader Interface</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/data/image.html">Image Interface</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/data/dataset.html">Dataset</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/run_logic.html">Training and Inference</a></li>
<li class="toctree-l2"><a class="reference internal" href="../api/v2/fluid.html">Fluid</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/layers.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/data_feeder.html">DataFeeder</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/executor.html">Executor</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/initializer.html">Initializer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/evaluator.html">Evaluator</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/nets.html">Nets</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/param_attr.html">ParamAttr</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/profiler.html">Profiler</a></li>
<li class="toctree-l3"><a class="reference internal" href="../api/v2/fluid/regularizer.html">Regularizer</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../mobile/index_en.html">MOBILE</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../mobile/cross_compiling_for_android_en.html">Build PaddlePaddle for Android</a></li>
<li class="toctree-l2"><a class="reference internal" href="../mobile/cross_compiling_for_raspberry_en.html">Build PaddlePaddle for Raspberry Pi</a></li>
</ul>
</li>
</ul>

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

      
<div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
      
    <li>Design Doc: Selected Rows</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="design-doc-selected-rows">
<span id="design-doc-selected-rows"></span><h1>Design Doc: Selected Rows<a class="headerlink" href="#design-doc-selected-rows" title="Permalink to this headline">¶</a></h1>
<p><code class="docutils literal"><span class="pre">SelectedRows</span></code> is a type of sparse tensor data type, which is designed to support <code class="docutils literal"><span class="pre">embedding</span></code> operators. The gradient of embedding table is a sparse tensor. Only a few rows are non-zero values in this tensor. It is straight-forward to represent a sparse tensor by the following sparse tensor data structure:</p>
<div class="highlight-cpp"><div class="highlight"><pre><span></span><span class="k">class</span> <span class="nc">SelectedRows</span> <span class="p">{</span>
 <span class="k">private</span><span class="o">:</span>
  <span class="n">vector</span><span class="o">&lt;</span><span class="kt">int</span><span class="o">&gt;</span> <span class="n">rows_</span><span class="p">;</span>
  <span class="n">Tensor</span> <span class="n">value_</span><span class="p">;</span>
  <span class="kt">int</span> <span class="n">height_</span><span class="p">;</span>
<span class="p">};</span>
</pre></div>
</div>
<p>The field <code class="docutils literal"><span class="pre">height_</span></code> is the first dimension of <code class="docutils literal"><span class="pre">SelectedRows</span></code>. The <code class="docutils literal"><span class="pre">rows</span></code> are the indices of the non-zero rows of <code class="docutils literal"><span class="pre">SelectedRows</span></code>. The <code class="docutils literal"><span class="pre">value_</span></code> field is an N-dim tensor of shape <code class="docutils literal"><span class="pre">[rows.size()</span> <span class="pre">/*</span> <span class="pre">NUM_ROWS</span> <span class="pre">*/,</span> <span class="pre">...]</span></code>, which supplies values for each row. The dimension of <code class="docutils literal"><span class="pre">SelectedRows</span></code> satisfies <code class="docutils literal"><span class="pre">[height_]</span> <span class="pre">+</span> <span class="pre">value_.shape[1:]</span></code>.</p>
<p>Suppose that a SelectedRows-typed variable <code class="docutils literal"><span class="pre">x</span></code> has many rows, but only two of them have values &#8211; row 73 is <code class="docutils literal"><span class="pre">[1,</span> <span class="pre">2]</span></code> and row 84 is <code class="docutils literal"><span class="pre">[3,</span> <span class="pre">4]</span></code>, the <code class="docutils literal"><span class="pre">SelectedRows</span></code> representation would be:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="n">x</span> <span class="o">=</span> <span class="n">SelectedRow</span> <span class="p">{</span>
  <span class="n">rows</span> <span class="o">=</span> <span class="p">[</span><span class="mi">73</span><span class="p">,</span> <span class="mi">84</span><span class="p">],</span>
  <span class="n">value</span> <span class="o">=</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="p">[</span><span class="mi">3</span><span class="p">,</span><span class="mi">4</span><span class="p">]]</span>
<span class="p">}</span>
</pre></div>
</div>
<div class="section" id="selectedrows-in-protobuf">
<span id="selectedrows-in-protobuf"></span><h2>SelectedRows in Protobuf<a class="headerlink" href="#selectedrows-in-protobuf" title="Permalink to this headline">¶</a></h2>
<p><code class="docutils literal"><span class="pre">SelectedRows</span></code> is a type of <code class="docutils literal"><span class="pre">Variable</span></code>. <code class="docutils literal"><span class="pre">VarDesc</span></code> in protobuf should describe the <code class="docutils literal"><span class="pre">SelectedRows</span></code> information. Only the tensor dimension of a <code class="docutils literal"><span class="pre">SelectedRows</span></code> will be described in compile-time because the <code class="docutils literal"><span class="pre">rows_</span></code> and <code class="docutils literal"><span class="pre">value_</span></code> are dependent on the training data.
So we use <code class="docutils literal"><span class="pre">TensorDesc</span></code> to unify <code class="docutils literal"><span class="pre">data_type</span></code> and <code class="docutils literal"><span class="pre">dims</span></code>. A LodTensorDesc contains a <code class="docutils literal"><span class="pre">TensorDesc</span></code> and <code class="docutils literal"><span class="pre">lod_level</span></code>. The description of <code class="docutils literal"><span class="pre">SelectedRows</span></code> is a Tensor description.</p>
<div class="highlight-proto"><div class="highlight"><pre><span></span><span class="kd">message</span> <span class="nc">TensorDesc</span> <span class="p">{</span>
  <span class="k">required</span> <span class="n">DataType</span> <span class="na">data_type</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
  <span class="k">repeated</span> <span class="kt">int64</span> <span class="na">dims</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span> <span class="c1">// [UNK, 640, 480] is saved as [-1, 640, 480]</span>
<span class="p">}</span>

<span class="kd">message</span> <span class="nc">LodTensorDesc</span> <span class="p">{</span>
  <span class="k">required</span> <span class="n">TensorDesc</span> <span class="na">tensor</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
  <span class="k">optional</span> <span class="n">int</span> <span class="na">lod_level</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
<span class="p">}</span>

<span class="kd">message</span> <span class="nc">VarDesc</span> <span class="p">{</span>
  <span class="k">required</span> <span class="kt">string</span> <span class="na">name</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
  <span class="kd">enum</span> <span class="n">VarType</span> <span class="p">{</span> 
    <span class="na">LOD_TENSOR</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
    <span class="na">SELECTED_ROWS</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
  <span class="p">}</span>
  <span class="k">required</span> <span class="n">VarType</span> <span class="na">type</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
  <span class="k">optional</span> <span class="n">LodTensorDesc</span> <span class="na">lod_desc</span> <span class="o">=</span> <span class="mi">3</span><span class="p">;</span>
  <span class="k">optional</span> <span class="n">TensorDesc</span> <span class="na">selected_rows_desc</span> <span class="o">=</span> <span class="mi">4</span><span class="p">;</span>
  <span class="k">optional</span> <span class="kt">bool</span> <span class="na">persistable</span> <span class="o">=</span> <span class="mi">5</span> <span class="p">[</span> <span class="k">default</span> <span class="o">=</span> <span class="kc">false</span> <span class="p">];</span>
<span class="p">}</span>
</pre></div>
</div>
</div>
<div class="section" id="infershape-for-selected-rows">
<span id="infershape-for-selected-rows"></span><h2>InferShape for Selected Rows<a class="headerlink" href="#infershape-for-selected-rows" title="Permalink to this headline">¶</a></h2>
<p>Just like <code class="docutils literal"><span class="pre">LoD</span></code> information, <code class="docutils literal"><span class="pre">InferShape</span></code> method will infer the output tensor type as well. The operator should decide whether its output is a <code class="docutils literal"><span class="pre">SelectedRows</span></code> or <code class="docutils literal"><span class="pre">Dense</span></code> tensor.</p>
<p>For example, the gradient operator of <code class="docutils literal"><span class="pre">TableLookup</span></code> will always generate <code class="docutils literal"><span class="pre">SelectedRows</span></code>. Its <code class="docutils literal"><span class="pre">InferShape</span></code> method should be like following</p>
<div class="highlight-cpp"><div class="highlight"><pre><span></span><span class="kt">void</span> <span class="n">TableLookupGrad</span><span class="o">::</span><span class="n">InferShape</span><span class="p">(</span><span class="n">context</span><span class="p">)</span> <span class="p">{</span>
  <span class="p">...</span>
  <span class="n">context</span><span class="p">.</span><span class="n">SetDataType</span><span class="p">(</span><span class="s">&quot;Embedding.Grad&quot;</span><span class="p">,</span> <span class="n">kSelectedRows</span><span class="p">);</span>
<span class="p">}</span>
</pre></div>
</div>
</div>
<div class="section" id="sparse-operators">
<span id="sparse-operators"></span><h2>Sparse Operators<a class="headerlink" href="#sparse-operators" title="Permalink to this headline">¶</a></h2>
<p>There are several operators that need to be written to support <code class="docutils literal"><span class="pre">SelectedRows</span></code>. These are:</p>
<ol class="simple">
<li>Operators which generate <code class="docutils literal"><span class="pre">SelectedRows</span></code> gradient. e.g. Gradient of <code class="docutils literal"><span class="pre">TableLookupOp</span></code>.</li>
<li>Optimize operators which support <code class="docutils literal"><span class="pre">SelectedRows</span></code> gradient. e.g. <code class="docutils literal"><span class="pre">SGD</span></code> or <code class="docutils literal"><span class="pre">AdaGrad</span></code> for <code class="docutils literal"><span class="pre">SelectedRows</span></code>. However, there should be only one <code class="docutils literal"><span class="pre">SGD</span></code> operator. <code class="docutils literal"><span class="pre">OpWithKernel::Run</span></code> should select a suitable kernel for both <code class="docutils literal"><span class="pre">dense</span></code> tensor or <code class="docutils literal"><span class="pre">SelectedRows</span></code>.</li>
</ol>
</div>
</div>


           </div>
          </div>
          <footer>
  

  <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="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></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>