model_format.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: Model Format &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"/> 

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

</head>

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

  <div class="wy-grid-for-nav">

    
    <nav data-toggle="wy-nav-shift" class="wy-nav-side">
      <div class="wy-side-scroll">
        <div class="wy-side-nav-search">
          

            <a href="../index_en.html" class="icon icon-home"> PaddlePaddle
          

          </a>

          
<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 class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
          
            
                <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="../build_and_install/index_en.html">Install and Build</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="../dev/index_en.html">Development</a></li>
<li class="toctree-l1"><a class="reference internal" href="../faq/index_en.html">FAQ</a></li>
</ul>

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

    <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">

      
      <nav class="wy-nav-top" role="navigation" aria-label="top navigation">
        <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
        <a href="../index_en.html">PaddlePaddle</a>
      </nav>


      <div class="wy-nav-content">
        <div class="rst-content">
          

<div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
    <li><a href="../index_en.html">Docs</a> &raquo;</li>
      
    <li>Design Doc: Model Format</li>
      <li class="wy-breadcrumbs-aside">
        
          
            <a href="../_sources/design/model_format.md.txt" rel="nofollow"> View page source</a>
          
        
      </li>
  </ul>
  <hr/>
</div>
          <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
           <div itemprop="articleBody">
            
  <div class="section" id="design-doc-model-format">
<span id="design-doc-model-format"></span><h1>Design Doc: Model Format<a class="headerlink" href="#design-doc-model-format" title="Permalink to this headline">¶</a></h1>
<div class="section" id="motivation">
<span id="motivation"></span><h2>Motivation<a class="headerlink" href="#motivation" title="Permalink to this headline">¶</a></h2>
<p>A model is an output of the training process. One complete model consists of two parts, the <strong>topology</strong> and the <strong>parameters</strong>. In order to support industrial deployment, the model format must be self-complete and must not expose any training source code.</p>
<p>As a result, In PaddlePaddle, the <strong>topology</strong> is represented as a  <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/1c0a4c901c9fc881d120249c703b15d1c50dae7d/doc/design/program.md">ProgramDesc</a>, which describes the model structure. The <strong>parameters</strong> contain all the trainable weights in the model. We must support large size parameters and efficient serialization/deserialization of parameters.</p>
</div>
<div class="section" id="implementation">
<span id="implementation"></span><h2>Implementation<a class="headerlink" href="#implementation" title="Permalink to this headline">¶</a></h2>
<p>The topology is saved as a plain text in a detailed self-contain protobuf file.</p>
<p>The parameters are saved as a binary file. As we all know, the protobuf message has a limit of <a class="reference external" href="https://developers.google.com/protocol-buffers/docs/reference/cpp/google.protobuf.io.coded_stream#CodedInputStream.SetTotalBytesLimit.details">64M size</a>. We have done a <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/pull/4610">benchmark experiment</a>, which shows that protobuf is not fit for the task.</p>
<p>As a result, we design a particular format for tensor serialization. By default, an arbitrary tensor in Paddle is a <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/lod_tensor.md">LoDTensor</a>, and has a description information proto of <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/framework/framework.proto#L99">LoDTensorDesc</a>. We save the DescProto as the byte string header. It contains all the necessary information, such as the <code class="docutils literal"><span class="pre">dims</span></code>, and the <code class="docutils literal"><span class="pre">LoD</span></code> information in <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/1c0a4c901c9fc881d120249c703b15d1c50dae7d/paddle/framework/lod_tensor.md">LoDTensor</a>. A tensor stores values in a continuous memory buffer. For speed we dump the raw memory to disk and save it as the byte string content. So, the binary format of one tensor is,</p>
<p>The table below shows a tensor&#8217;s byte view in detail. Note that all the signed values are written in the little-endian format.</p>
<p>|field name  | type | description |
| &#8212; | &#8212; | &#8212; |
| version | uint32_t | Version of saved file. Always 0 now. |
| tensor desc length | uint32_t | TensorDesc(Protobuf message) length in bytes. |
| tensor desc | void* | TensorDesc protobuf binary message |
| tensor data | void* | Tensor&#8217;s data in binary format. The length of <code class="docutils literal"><span class="pre">tensor_data</span></code> is decided by <code class="docutils literal"><span class="pre">TensorDesc.dims()</span></code> and <code class="docutils literal"><span class="pre">TensorDesc.data_type()</span></code> |
| lod_level | uint64_t | Level of LoD |
| length of lod[0] | uint64_t | [Optional] length of lod[0] in bytes. |
| data of lod[0] | uint64_t*  | [Optional] lod[0].data() |
| ... | ... | ... |</p>
</div>
<div class="section" id="summary">
<span id="summary"></span><h2>Summary<a class="headerlink" href="#summary" title="Permalink to this headline">¶</a></h2>
<ul class="simple">
<li>We introduce a model format.</li>
<li>The model represented by its forward-pass computation procedure is saved in a <strong>ProgramDesc</strong> protobuf message.</li>
<li>A bunch of specified format binary tensors describe the <strong>parameters</strong>.</li>
</ul>
</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
        };
    </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 type="text/javascript">
      jQuery(function () {
          SphinxRtdTheme.StickyNav.enable();
      });
  </script>
   

</body>
</html>