fluid_cluster_train_en.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>Fluid Distributed Training &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="../../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="../../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="../../index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="cluster_train_en.html">Distributed Training</a><ul>
<li class="toctree-l3"><a class="reference internal" href="fabric_en.html">fabric</a></li>
<li class="toctree-l3"><a class="reference internal" href="openmpi_en.html">openmpi</a></li>
<li class="toctree-l3"><a class="reference internal" href="k8s_en.html">kubernetes</a></li>
<li class="toctree-l3"><a class="reference internal" href="k8s_aws_en.html">kubernetes on AWS</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_en.html">Contribute Documentation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../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>
<li class="toctree-l3"><a class="reference internal" href="../../../api/v2/fluid/io.html">IO</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_ios_en.html">Build PaddlePaddle for iOS</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>Fluid Distributed Training</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="fluid-distributed-training">
<span id="fluid-distributed-training"></span><h1>Fluid Distributed Training<a class="headerlink" href="#fluid-distributed-training" title="Permalink to this headline">¶</a></h1>
<div class="section" id="introduction">
<span id="introduction"></span><h2>Introduction<a class="headerlink" href="#introduction" title="Permalink to this headline">¶</a></h2>
<p>In this article, we&#8217;ll explain how to config and run distributed training jobs with PaddlePaddle Fluid in a bare metal cluster.</p>
</div>
<div class="section" id="preparations">
<span id="preparations"></span><h2>Preparations<a class="headerlink" href="#preparations" title="Permalink to this headline">¶</a></h2>
<div class="section" id="get-your-cluster-ready">
<span id="get-your-cluster-ready"></span><h3>Get your cluster ready<a class="headerlink" href="#get-your-cluster-ready" title="Permalink to this headline">¶</a></h3>
<p>Prepare your computer nodes in the cluster. Nodes in this cluster can be of any specification that runs PaddlePaddle, and with a unique IP address assigned to it. Make sure they can communicate with each other.</p>
</div>
<div class="section" id="have-paddlepaddle-installed">
<span id="have-paddlepaddle-installed"></span><h3>Have PaddlePaddle installed<a class="headerlink" href="#have-paddlepaddle-installed" title="Permalink to this headline">¶</a></h3>
<p>PaddlePaddle must be installed on all nodes. If you have GPU cards on your nodes, be sure to properly install drivers and CUDA libraries.</p>
<p>PaddlePaddle build and installation guide can be found from <a class="reference external" href="http://www.paddlepaddle.org/docs/develop/documentation/en/getstarted/build_and_install/index_en.html">here</a>.</p>
</div>
<div class="section" id="update-training-script">
<span id="update-training-script"></span><h3>Update training script<a class="headerlink" href="#update-training-script" title="Permalink to this headline">¶</a></h3>
<div class="section" id="non-cluster-training-script">
<span id="non-cluster-training-script"></span><h4>Non-cluster training script<a class="headerlink" href="#non-cluster-training-script" title="Permalink to this headline">¶</a></h4>
<p>Let&#8217;s take <a class="reference external" href="http://www.paddlepaddle.org/docs/develop/book/01.fit_a_line/index.html">Deep Learning 101</a>&#8216;s first chapter: &#8220;fit a line&#8221; as an example.</p>
<p>This demo&#8217;s non-cluster version with fluid API is as follows:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">paddle.v2</span> <span class="kn">as</span> <span class="nn">paddle</span>
<span class="kn">import</span> <span class="nn">paddle.v2.fluid</span> <span class="kn">as</span> <span class="nn">fluid</span>

<span class="n">x</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">data</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;x&#39;</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="mi">13</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;float32&#39;</span><span class="p">)</span>
<span class="n">y_predict</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">fc</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">x</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="bp">None</span><span class="p">)</span>
<span class="n">y</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">data</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;y&#39;</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">dtype</span><span class="o">=</span><span class="s1">&#39;float32&#39;</span><span class="p">)</span>

<span class="n">cost</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">square_error_cost</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">y_predict</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">y</span><span class="p">)</span>
<span class="n">avg_cost</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">mean</span><span class="p">(</span><span class="n">x</span><span class="o">=</span><span class="n">cost</span><span class="p">)</span>

<span class="n">sgd_optimizer</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">SGD</span><span class="p">(</span><span class="n">learning_rate</span><span class="o">=</span><span class="mf">0.001</span><span class="p">)</span>
<span class="n">sgd_optimizer</span><span class="o">.</span><span class="n">minimize</span><span class="p">(</span><span class="n">avg_cost</span><span class="p">)</span>

<span class="n">BATCH_SIZE</span> <span class="o">=</span> <span class="mi">20</span>

<span class="n">train_reader</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">batch</span><span class="p">(</span>
    <span class="n">paddle</span><span class="o">.</span><span class="n">reader</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span>
        <span class="n">paddle</span><span class="o">.</span><span class="n">dataset</span><span class="o">.</span><span class="n">uci_housing</span><span class="o">.</span><span class="n">train</span><span class="p">(),</span> <span class="n">buf_size</span><span class="o">=</span><span class="mi">500</span><span class="p">),</span>
    <span class="n">batch_size</span><span class="o">=</span><span class="n">BATCH_SIZE</span><span class="p">)</span>

<span class="n">place</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">CPUPlace</span><span class="p">()</span>
<span class="n">feeder</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">DataFeeder</span><span class="p">(</span><span class="n">place</span><span class="o">=</span><span class="n">place</span><span class="p">,</span> <span class="n">feed_list</span><span class="o">=</span><span class="p">[</span><span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">])</span>
<span class="n">exe</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">Executor</span><span class="p">(</span><span class="n">place</span><span class="p">)</span>

<span class="n">exe</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">fluid</span><span class="o">.</span><span class="n">default_startup_program</span><span class="p">())</span>

<span class="n">PASS_NUM</span> <span class="o">=</span> <span class="mi">100</span>
<span class="k">for</span> <span class="n">pass_id</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">PASS_NUM</span><span class="p">):</span>
    <span class="n">fluid</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">save_persistables</span><span class="p">(</span><span class="n">exe</span><span class="p">,</span> <span class="s2">&quot;./fit_a_line.model/&quot;</span><span class="p">)</span>
    <span class="n">fluid</span><span class="o">.</span><span class="n">io</span><span class="o">.</span><span class="n">load_persistables</span><span class="p">(</span><span class="n">exe</span><span class="p">,</span> <span class="s2">&quot;./fit_a_line.model/&quot;</span><span class="p">)</span>
    <span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">train_reader</span><span class="p">():</span>
        <span class="n">avg_loss_value</span><span class="p">,</span> <span class="o">=</span> <span class="n">exe</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">fluid</span><span class="o">.</span><span class="n">default_main_program</span><span class="p">(),</span>
                                  <span class="n">feed</span><span class="o">=</span><span class="n">feeder</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="n">data</span><span class="p">),</span>
                                  <span class="n">fetch_list</span><span class="o">=</span><span class="p">[</span><span class="n">avg_cost</span><span class="p">])</span>

        <span class="k">if</span> <span class="n">avg_loss_value</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">&lt;</span> <span class="mf">10.0</span><span class="p">:</span>
            <span class="nb">exit</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>  <span class="c1"># if avg cost less than 10.0, we think our code is good.</span>
<span class="nb">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
</pre></div>
</div>
<p>We created a simple fully connected neural networks training program and handed it to the fluid executor to run for 100 passes.</p>
<p>Now let&#8217;s try to convert it to a distributed version to run in a cluster.</p>
</div>
<div class="section" id="introducing-parameter-server">
<span id="introducing-parameter-server"></span><h4>Introducing parameter server<a class="headerlink" href="#introducing-parameter-server" title="Permalink to this headline">¶</a></h4>
<p>As you see from the non-cluster version of training script, there is only one role in it: the trainer, who does the computing as well as holding parameters. In cluster training, since multi-trainers are working on the same task, they need one centralized place to hold and distribute parameters. This centralized place is called the Parameter Server in PaddlePaddle.</p>
<p><img alt="parameter server architect" src="../../../_images/trainer.png" /></p>
<p>Parameter Server in fluid does not only hold parameters but is also assigned with a part of the program. Trainers communicate with parameter servers via send/receive OPs. For more tech detail, please refer to this <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/dist_refactor/distributed_architecture.md">document</a>.</p>
<p>Now we need to create program for both trainers and parameter servers, the question is how?</p>
</div>
<div class="section" id="slice-the-program">
<span id="slice-the-program"></span><h4>Slice the program<a class="headerlink" href="#slice-the-program" title="Permalink to this headline">¶</a></h4>
<p>Fluid provides a tool called &#8220;Distribute Transpiler&#8221; to automatically convert the non-cluster program into cluster program.</p>
<p>The idea behind this tool is to find optimize OPs and gradient parameters, slice the program into 2 pieces and connect them with send/receive OP.</p>
<p>Optimize OPs and gradient parameters can be found from the return values of optimizer&#8217;s minimize function.</p>
<p>To put them together:</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="o">...</span> <span class="c1">#define the program, cost, and create sgd optimizer</span>

<span class="n">optimize_ops</span><span class="p">,</span> <span class="n">params_grads</span> <span class="o">=</span> <span class="n">sgd_optimizer</span><span class="o">.</span><span class="n">minimize</span><span class="p">(</span><span class="n">avg_cost</span><span class="p">)</span> <span class="c1">#get optimize OPs and gradient parameters</span>

<span class="n">t</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">DistributeTranspiler</span><span class="p">()</span> <span class="c1"># create transpiler instance</span>
<span class="c1"># slice the program into 2 pieces with optimizer_ops and gradient parameters list, as well as pserver_endpoints, which is a comma separated list of [IP:PORT] and number of trainers</span>
<span class="n">t</span><span class="o">.</span><span class="n">transpile</span><span class="p">(</span><span class="n">optimize_ops</span><span class="p">,</span> <span class="n">params_grads</span><span class="p">,</span> <span class="n">pservers</span><span class="o">=</span><span class="n">pserver_endpoints</span><span class="p">,</span> <span class="n">trainers</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span> 

<span class="o">...</span> <span class="c1">#create executor</span>

<span class="c1"># in pserver, run this</span>
<span class="n">exe</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">fluid</span><span class="o">.</span><span class="n">default_startup_program</span><span class="p">())</span>
<span class="c1">#current_endpoint here means current pserver IP:PORT you wish to run on</span>
<span class="n">exe</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">t</span><span class="o">.</span><span class="n">get_pserver_program</span><span class="p">(</span><span class="n">current_endpoint</span><span class="p">))</span>

<span class="c1"># in trainer, run this</span>
<span class="o">...</span> <span class="c1"># define data reader</span>
<span class="n">exe</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">fluid</span><span class="o">.</span><span class="n">default_startup_program</span><span class="p">())</span>
<span class="k">for</span> <span class="n">pass_id</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">100</span><span class="p">):</span>
    <span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">train_reader</span><span class="p">():</span>
        <span class="n">exe</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">t</span><span class="o">.</span><span class="n">get_trainer_program</span><span class="p">())</span>


</pre></div>
</div>
</div>
</div>
<div class="section" id="e2e-demo">
<span id="e2e-demo"></span><h3>E2E demo<a class="headerlink" href="#e2e-demo" title="Permalink to this headline">¶</a></h3>
<p>Please find the complete demo from <a class="reference external" href="https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/v2/fluid/tests/book_distribute/notest_dist_fit_a_line.py">here</a>. In parameter server node run this in the command line:</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="nv">PSERVERS</span><span class="o">=</span><span class="m">192</span>.168.1.2:6174 <span class="nv">SERVER_ENDPOINT</span><span class="o">=</span><span class="m">192</span>.168.1.2:6174 <span class="nv">TRAINING_ROLE</span><span class="o">=</span>PSERVER python notest_dist_fit_a_line.py
</pre></div>
</div>
<p><em>please note we assume that your parameter server runs at 192.168.1.2:6174</em></p>
<p>Wait until the prompt <code class="docutils literal"><span class="pre">Server</span> <span class="pre">listening</span> <span class="pre">on</span> <span class="pre">192.168.1.2:6174</span></code></p>
<p>Then in 2 of your trainer node run this:</p>
<div class="highlight-bash"><div class="highlight"><pre><span></span><span class="nv">PSERVERS</span><span class="o">=</span><span class="m">192</span>.168.1.2:6174 <span class="nv">SERVER_ENDPOINT</span><span class="o">=</span><span class="m">192</span>.168.1.2:6174 <span class="nv">TRAINING_ROLE</span><span class="o">=</span>TRAINER python notest_dist_fit_a_line.py
</pre></div>
</div>
<p><em>the reason you need to run this command twice in 2 nodes is: in the script we set the trainer count to be 2. You can change this setting on line 50</em></p>
<p>Now you have 2 trainers and 1 parameter server up and running.</p>
</div>
</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>