index_cn.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>本地训练与预测 &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="FAQ" href="../index_cn.html"/>
        <link rel="next" title="集群训练与预测" href="../cluster/index_cn.html"/>
        <link rel="prev" title="参数设置" href="../parameter/index_cn.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="../../build_and_install/index_cn.html">安装与编译</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../howto/index_cn.html">进阶使用</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../dev/index_cn.html">开发标准</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../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/quickstart_cn.html">快速开始</a></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="../../build_and_install/index_cn.html">安装与编译</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../build_and_install/pip_install_cn.html">使用pip安装</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../build_and_install/docker_install_cn.html">使用Docker安装运行</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../build_and_install/build_from_source_cn.html">从源码编译</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../howto/index_cn.html">进阶使用</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../howto/cmd_parameter/index_cn.html">命令行参数设置</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/cmd_parameter/use_case_cn.html">使用案例</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/cmd_parameter/arguments_cn.html">参数概述</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/cmd_parameter/detail_introduction_cn.html">细节描述</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/cluster/index_cn.html">分布式训练</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/cluster/preparations_cn.html">环境准备</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/cluster/cmd_argument_cn.html">启动参数说明</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/cluster/multi_cluster/index_cn.html">在不同集群中运行</a><ul>
<li class="toctree-l4"><a class="reference internal" href="../../howto/cluster/multi_cluster/fabric_cn.html">使用fabric启动集群训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../howto/cluster/multi_cluster/openmpi_cn.html">在OpenMPI集群中提交训练作业</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../howto/cluster/multi_cluster/k8s_cn.html">Kubernetes单机训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../howto/cluster/multi_cluster/k8s_distributed_cn.html">Kubernetes分布式训练</a></li>
<li class="toctree-l4"><a class="reference internal" href="../../howto/cluster/multi_cluster/k8s_aws_cn.html">Distributed PaddlePaddle Training on AWS with Kubernetes</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/capi/index_cn.html">C-API预测库</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/capi/compile_paddle_lib_cn.html">安装与编译C-API预测库</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/capi/organization_of_the_inputs_cn.html">输入/输出数据组织</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/capi/workflow_of_capi_cn.html">C-API使用流程</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../howto/rnn/index_cn.html">RNN模型</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../howto/rnn/rnn_config_cn.html">RNN配置</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../howto/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/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性能调优</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../dev/index_cn.html">开发标准</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../dev/contribute_to_paddle_cn.html">如何贡献代码</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../dev/write_docs_cn.html">如何贡献文档</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../index_cn.html">FAQ</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../build_and_install/index_cn.html">编译安装与单元测试</a></li>
<li class="toctree-l2"><a class="reference internal" href="../model/index_cn.html">模型配置</a></li>
<li class="toctree-l2"><a class="reference internal" href="../parameter/index_cn.html">参数设置</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">本地训练与预测</a></li>
<li class="toctree-l2"><a class="reference internal" href="../cluster/index_cn.html">集群训练与预测</a></li>
</ul>
</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">FAQ</a> > </li>
      
    <li>本地训练与预测</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="id1">
<h1><a class="toc-backref" href="#id10">本地训练与预测</a><a class="headerlink" href="#id1" title="永久链接至标题">¶</a></h1>
<div class="contents topic" id="contents">
<p class="topic-title first">Contents</p>
<ul class="simple">
<li><a class="reference internal" href="#id1" id="id10">本地训练与预测</a><ul>
<li><a class="reference internal" href="#id2" id="id11">1. 如何减少内存占用</a><ul>
<li><a class="reference internal" href="#dataprovider" id="id12">减少DataProvider缓冲池内存</a></li>
<li><a class="reference internal" href="#id3" id="id13">神经元激活内存</a></li>
<li><a class="reference internal" href="#id4" id="id14">参数内存</a></li>
</ul>
</li>
<li><a class="reference internal" href="#id5" id="id15">2. 如何加速训练速度</a><ul>
<li><a class="reference internal" href="#id6" id="id16">减少数据载入的耗时</a></li>
<li><a class="reference internal" href="#id7" id="id17">加速训练速度</a></li>
<li><a class="reference internal" href="#id8" id="id18">利用更多的计算资源</a></li>
</ul>
</li>
<li><a class="reference internal" href="#gpu" id="id19">3. 如何指定GPU设备</a></li>
<li><a class="reference internal" href="#floating-point-exception" id="id20">4. 训练过程中出现 <code class="code docutils literal"><span class="pre">Floating</span> <span class="pre">point</span> <span class="pre">exception</span></code>, 训练因此退出怎么办?</a></li>
<li><a class="reference internal" href="#infer-layer" id="id21">5.  如何调用 infer 接口输出多个layer的预测结果</a></li>
<li><a class="reference internal" href="#layeroutput" id="id22">6.  如何在训练过程中获得某一个layer的output</a></li>
<li><a class="reference internal" href="#id9" id="id23">7.  如何在训练过程中获得参数的权重和梯度</a></li>
</ul>
</li>
</ul>
</div>
<div class="section" id="id2">
<h2><a class="toc-backref" href="#id11">1. 如何减少内存占用</a><a class="headerlink" href="#id2" title="永久链接至标题">¶</a></h2>
<p>神经网络的训练本身是一个非常消耗内存和显存的工作，经常会消耗数10GB的内存和数GB的显存。
PaddlePaddle的内存占用主要分为如下几个方面:</p>
<ul class="simple">
<li>DataProvider缓冲池内存（只针对内存）</li>
<li>神经元激活内存（针对内存和显存）</li>
<li>参数内存 （针对内存和显存）</li>
<li>其他内存杂项</li>
</ul>
<p>其中，其他内存杂项是指PaddlePaddle本身所用的一些内存，包括字符串分配，临时变量等等，暂不考虑在内。</p>
<div class="section" id="dataprovider">
<h3><a class="toc-backref" href="#id12">减少DataProvider缓冲池内存</a><a class="headerlink" href="#dataprovider" title="永久链接至标题">¶</a></h3>
<p>PyDataProvider使用的是异步加载，同时在内存里直接随即选取数据来做Shuffle。即</p>
<img src="../../_images/graphviz-9be6aad37f57c60f4b971dde0ef44ce27179cf9a.png" alt="digraph {
    rankdir=LR;
    数据文件 -&gt; 内存池 -&gt; PaddlePaddle训练
}" />
<p>所以，减小这个内存池即可减小内存占用，同时也可以加速开始训练前数据载入的过程。但是，这
个内存池实际上决定了shuffle的粒度。所以，如果将这个内存池减小，又要保证数据是随机的，
那么最好将数据文件在每次读取之前做一次shuffle。可能的代码为</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="c1">#   Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1">#     http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>


<span class="nd">@provider</span><span class="p">(</span><span class="n">min_pool_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">...</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="n">settings</span><span class="p">,</span> <span class="n">filename</span><span class="p">):</span>
    <span class="n">os</span><span class="o">.</span><span class="n">system</span><span class="p">(</span><span class="s1">&#39;shuf </span><span class="si">%s</span><span class="s1"> &gt; </span><span class="si">%s</span><span class="s1">.shuf&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="n">filename</span><span class="p">))</span>  <span class="c1"># shuffle before.</span>
    <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s1">&#39;</span><span class="si">%s</span><span class="s1">.shuf&#39;</span> <span class="o">%</span> <span class="n">filename</span><span class="p">,</span> <span class="s1">&#39;r&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
        <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">f</span><span class="p">:</span>
            <span class="k">yield</span> <span class="n">get_sample_from_line</span><span class="p">(</span><span class="n">line</span><span class="p">)</span>
</pre></div>
</div>
<p>这样做可以极大的减少内存占用，并且可能会加速训练过程，详细文档参考 <span class="xref std std-ref">api_pydataprovider2</span> 。</p>
</div>
<div class="section" id="id3">
<h3><a class="toc-backref" href="#id13">神经元激活内存</a><a class="headerlink" href="#id3" title="永久链接至标题">¶</a></h3>
<p>神经网络在训练的时候，会对每一个激活暂存一些数据，如神经元激活值等。
在反向传递的时候，这些数据会被用来更新参数。这些数据使用的内存主要和两个参数有关系，
一是batch size，另一个是每条序列(Sequence)长度。所以，其实也是和每个mini-batch中包含
的时间步信息成正比。</p>
<p>所以做法可以有两种：</p>
<ul class="simple">
<li>减小batch size。 即在网络配置中 <code class="code docutils literal"><span class="pre">settings(batch_size=1000)</span></code> 设置成一个小一些的值。但是batch size本身是神经网络的超参数，减小batch size可能会对训练结果产生影响。</li>
<li>减小序列的长度，或者直接扔掉非常长的序列。比如，一个数据集大部分序列长度是100-200,
但是突然有一个10000长的序列，就很容易导致内存超限，特别是在LSTM等RNN中。</li>
</ul>
</div>
<div class="section" id="id4">
<h3><a class="toc-backref" href="#id14">参数内存</a><a class="headerlink" href="#id4" title="永久链接至标题">¶</a></h3>
<p>PaddlePaddle支持非常多的优化算法(Optimizer)，不同的优化算法需要使用不同大小的内存。
例如使用 <code class="code docutils literal"><span class="pre">adadelta</span></code> 算法，则需要使用等于权重参数规模大约5倍的内存。举例，如果参数保存下来的模型目录
文件为 <code class="code docutils literal"><span class="pre">100M</span></code>， 那么该优化算法至少需要 <code class="code docutils literal"><span class="pre">500M</span></code> 的内存。</p>
<p>可以考虑使用一些优化算法，例如 <code class="code docutils literal"><span class="pre">momentum</span></code>。</p>
</div>
</div>
<div class="section" id="id5">
<h2><a class="toc-backref" href="#id15">2. 如何加速训练速度</a><a class="headerlink" href="#id5" title="永久链接至标题">¶</a></h2>
<p>加速PaddlePaddle训练可以考虑从以下几个方面：</p>
<ul class="simple">
<li>减少数据载入的耗时</li>
<li>加速训练速度</li>
<li>利用分布式训练驾驭更多的计算资源</li>
</ul>
<div class="section" id="id6">
<h3><a class="toc-backref" href="#id16">减少数据载入的耗时</a><a class="headerlink" href="#id6" title="永久链接至标题">¶</a></h3>
<p>使用<code class="code docutils literal"><span class="pre">pydataprovider</span></code>时，可以减少缓存池的大小，同时设置内存缓存功能，即可以极大的加速数据载入流程。
<code class="code docutils literal"><span class="pre">DataProvider</span></code> 缓存池的减小，和之前减小通过减小缓存池来减小内存占用的原理一致。</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="c1">#   Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1">#     http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>


<span class="nd">@provider</span><span class="p">(</span><span class="n">min_pool_size</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="o">...</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="n">settings</span><span class="p">,</span> <span class="n">filename</span><span class="p">):</span>
    <span class="n">os</span><span class="o">.</span><span class="n">system</span><span class="p">(</span><span class="s1">&#39;shuf </span><span class="si">%s</span><span class="s1"> &gt; </span><span class="si">%s</span><span class="s1">.shuf&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="n">filename</span><span class="p">))</span>  <span class="c1"># shuffle before.</span>
    <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s1">&#39;</span><span class="si">%s</span><span class="s1">.shuf&#39;</span> <span class="o">%</span> <span class="n">filename</span><span class="p">,</span> <span class="s1">&#39;r&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
        <span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">f</span><span class="p">:</span>
            <span class="k">yield</span> <span class="n">get_sample_from_line</span><span class="p">(</span><span class="n">line</span><span class="p">)</span>
</pre></div>
</div>
<p>同时 <code class="code docutils literal"><span class="pre">&#64;provider</span></code> 接口有一个 <code class="code docutils literal"><span class="pre">cache</span></code> 参数来控制缓存方法，将其设置成 <code class="code docutils literal"><span class="pre">CacheType.CACHE_PASS_IN_MEM</span></code> 的话，会将第一个 <code class="code docutils literal"><span class="pre">pass</span></code> (过完所有训练数据即为一个pass)生成的数据缓存在内存里，在之后的 <code class="code docutils literal"><span class="pre">pass</span></code> 中，不会再从 <code class="code docutils literal"><span class="pre">python</span></code> 端读取数据，而是直接从内存的缓存里读取数据。这也会极大减少数据读入的耗时。</p>
</div>
<div class="section" id="id7">
<h3><a class="toc-backref" href="#id17">加速训练速度</a><a class="headerlink" href="#id7" title="永久链接至标题">¶</a></h3>
<p>PaddlePaddle支持Sparse的训练，sparse训练需要训练特征是 <code class="code docutils literal"><span class="pre">sparse_binary_vector</span></code> 、 <code class="code docutils literal"><span class="pre">sparse_vector</span></code> 、或者 <code class="code docutils literal"><span class="pre">integer_value</span></code> 的任一一种。同时，与这个训练数据交互的Layer，需要将其Parameter设置成 sparse 更新模式，即设置 <code class="code docutils literal"><span class="pre">sparse_update=True</span></code></p>
<p>这里使用简单的 <code class="code docutils literal"><span class="pre">word2vec</span></code> 训练语言模型距离，具体使用方法为:</p>
<p>使用一个词前两个词和后两个词，来预测这个中间的词。这个任务的DataProvider为:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="c1">#   Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1">#     http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>

<span class="n">DICT_DIM</span> <span class="o">=</span> <span class="mi">3000</span>


<span class="nd">@provider</span><span class="p">(</span><span class="n">input_types</span><span class="o">=</span><span class="p">[</span><span class="n">integer_sequence</span><span class="p">(</span><span class="n">DICT_DIM</span><span class="p">),</span> <span class="n">integer_value</span><span class="p">(</span><span class="n">DICT_DIM</span><span class="p">)])</span>
<span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="n">settings</span><span class="p">,</span> <span class="n">filename</span><span class="p">):</span>
    <span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">filename</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
        <span class="c1"># yield word ids to predict inner word id</span>
        <span class="c1"># such as [28, 29, 10, 4], 4</span>
        <span class="c1"># It means the sentance is  28, 29, 4, 10, 4.</span>
        <span class="k">yield</span> <span class="n">read_next_from_file</span><span class="p">(</span><span class="n">f</span><span class="p">)</span>
</pre></div>
</div>
<p>这个任务的配置为:</p>
<div class="highlight-default"><div class="highlight"><pre><span></span><span class="c1">#   Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.</span>
<span class="c1">#</span>
<span class="c1"># Licensed under the Apache License, Version 2.0 (the &quot;License&quot;);</span>
<span class="c1"># you may not use this file except in compliance with the License.</span>
<span class="c1"># You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1">#     http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>

<span class="o">...</span>  <span class="c1"># the settings and define data provider is omitted.</span>
<span class="n">DICT_DIM</span> <span class="o">=</span> <span class="mi">3000</span>  <span class="c1"># dictionary dimension.</span>
<span class="n">word_ids</span> <span class="o">=</span> <span class="n">data_layer</span><span class="p">(</span><span class="s1">&#39;word_ids&#39;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">DICT_DIM</span><span class="p">)</span>

<span class="n">emb</span> <span class="o">=</span> <span class="n">embedding_layer</span><span class="p">(</span>
    <span class="nb">input</span><span class="o">=</span><span class="n">word_ids</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">param_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">sparse_update</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
<span class="n">emb_sum</span> <span class="o">=</span> <span class="n">pooling_layer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">emb</span><span class="p">,</span> <span class="n">pooling_type</span><span class="o">=</span><span class="n">SumPooling</span><span class="p">())</span>
<span class="n">predict</span> <span class="o">=</span> <span class="n">fc_layer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">emb_sum</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">DICT_DIM</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="n">Softmax</span><span class="p">())</span>
<span class="n">outputs</span><span class="p">(</span>
    <span class="n">classification_cost</span><span class="p">(</span>
        <span class="nb">input</span><span class="o">=</span><span class="n">predict</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">data_layer</span><span class="p">(</span>
            <span class="s1">&#39;label&#39;</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="n">DICT_DIM</span><span class="p">)))</span>
</pre></div>
</div>
</div>
<div class="section" id="id8">
<h3><a class="toc-backref" href="#id18">利用更多的计算资源</a><a class="headerlink" href="#id8" title="永久链接至标题">¶</a></h3>
<p>利用更多的计算资源可以分为以下几个方式来进行:</p>
<ul class="simple">
<li>单机CPU训练<ul>
<li>使用多线程训练。设置命令行参数 <code class="code docutils literal"><span class="pre">trainer_count</span></code>。</li>
</ul>
</li>
<li>单机GPU训练<ul>
<li>使用显卡训练。设置命令行参数 <code class="code docutils literal"><span class="pre">use_gpu</span></code>。</li>
<li>使用多块显卡训练。设置命令行参数 <code class="code docutils literal"><span class="pre">use_gpu</span></code> 和 <code class="code docutils literal"><span class="pre">trainer_count</span></code> 。</li>
</ul>
</li>
<li>多机训练<ul>
<li>请参考 <span class="xref std std-ref">cluster_train</span> 。</li>
</ul>
</li>
</ul>
</div>
</div>
<div class="section" id="gpu">
<h2><a class="toc-backref" href="#id19">3. 如何指定GPU设备</a><a class="headerlink" href="#gpu" title="永久链接至标题">¶</a></h2>
<p>例如机器上有4块GPU，编号从0开始，指定使用2、3号GPU：</p>
<ul class="simple">
<li>方式1：通过 <a class="reference external" href="http://www.acceleware.com/blog/cudavisibledevices-masking-gpus">CUDA_VISIBLE_DEVICES</a> 环境变量来指定特定的GPU。</li>
</ul>
<div class="highlight-bash"><div class="highlight"><pre><span></span>env <span class="nv">CUDA_VISIBLE_DEVICES</span><span class="o">=</span><span class="m">2</span>,3 paddle train --use_gpu<span class="o">=</span><span class="nb">true</span> --trainer_count<span class="o">=</span><span class="m">2</span>
</pre></div>
</div>
<ul class="simple">
<li>方式2：通过命令行参数 <code class="docutils literal"><span class="pre">--gpu_id</span></code> 指定。</li>
</ul>
<div class="highlight-bash"><div class="highlight"><pre><span></span>paddle train --use_gpu<span class="o">=</span><span class="nb">true</span> --trainer_count<span class="o">=</span><span class="m">2</span> --gpu_id<span class="o">=</span><span class="m">2</span>
</pre></div>
</div>
</div>
<div class="section" id="floating-point-exception">
<h2><a class="toc-backref" href="#id20">4. 训练过程中出现 <code class="code docutils literal"><span class="pre">Floating</span> <span class="pre">point</span> <span class="pre">exception</span></code>, 训练因此退出怎么办?</a><a class="headerlink" href="#floating-point-exception" title="永久链接至标题">¶</a></h2>
<p>Paddle二进制在运行时捕获了浮点数异常，只要出现浮点数异常(即训练过程中出现NaN或者Inf)，立刻退出。浮点异常通常的原因是浮点数溢出、除零等问题。
主要原因包括两个方面:</p>
<ul class="simple">
<li>训练过程中参数或者训练过程中的梯度尺度过大，导致参数累加，乘除等时候，导致了浮点数溢出。</li>
<li>模型一直不收敛，发散到了一个数值特别大的地方。</li>
<li>训练数据有问题，导致参数收敛到了一些奇异的情况。或者输入数据尺度过大，有些特征的取值达到数百万，这时进行矩阵乘法运算就可能导致浮点数溢出。</li>
</ul>
<p>这里有两种有效的解决方法：</p>
<ol class="arabic simple">
<li>设置 <code class="code docutils literal"><span class="pre">gradient_clipping_threshold</span></code> 参数，示例代码如下：</li>
</ol>
<div class="highlight-python"><div class="highlight"><pre><span></span>
</pre></div>
</div>
<dl class="docutils">
<dt>optimizer = paddle.optimizer.RMSProp(</dt>
<dd>learning_rate=1e-3,
gradient_clipping_threshold=10.0,
regularization=paddle.optimizer.L2Regularization(rate=8e-4))</dd>
</dl>
<p>具体可以参考  <a class="reference external" href="https://github.com/PaddlePaddle/models/blob/develop/nmt_without_attention/train.py#L35">nmt_without_attention</a> 示例。</p>
<ol class="arabic simple" start="2">
<li>设置 <code class="code docutils literal"><span class="pre">error_clipping_threshold</span></code> 参数，示例代码如下：</li>
</ol>
<div class="highlight-python"><div class="highlight"><pre><span></span>
</pre></div>
</div>
<dl class="docutils">
<dt>decoder_inputs = paddle.layer.fc(</dt>
<dd><p class="first">act=paddle.activation.Linear(),
size=decoder_size * 3,
bias_attr=False,
input=[context, current_word],
layer_attr=paddle.attr.ExtraLayerAttribute(</p>
<blockquote class="last">
<div>error_clipping_threshold=100.0))</div></blockquote>
</dd>
</dl>
<p>完整代码可以参考示例 <a class="reference external" href="https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/train.py#L66">machine translation</a> 。</p>
<p>两种方法的区别：</p>
<ol class="arabic simple">
<li>两者都是对梯度的截断，但截断时机不同，前者在 <code class="code docutils literal"><span class="pre">optimzier</span></code> 更新网络参数时应用；后者在激活函数反向计算时被调用；</li>
<li>截断对象不同：前者截断可学习参数的梯度，后者截断回传给前层的梯度;</li>
</ol>
<p>除此之外，还可以通过减小学习率或者对数据进行归一化处理来解决这类问题。</p>
</div>
<div class="section" id="infer-layer">
<h2><a class="toc-backref" href="#id21">5.  如何调用 infer 接口输出多个layer的预测结果</a><a class="headerlink" href="#infer-layer" title="永久链接至标题">¶</a></h2>
<ul class="simple">
<li>将需要输出的层作为 <code class="code docutils literal"><span class="pre">paddle.inference.Inference()</span></code> 接口的 <code class="code docutils literal"><span class="pre">output_layer</span></code> 参数输入，代码如下：</li>
</ul>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">inferer</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">inference</span><span class="o">.</span><span class="n">Inference</span><span class="p">(</span><span class="n">output_layer</span><span class="o">=</span><span class="p">[</span><span class="n">layer1</span><span class="p">,</span> <span class="n">layer2</span><span class="p">],</span> <span class="n">parameters</span><span class="o">=</span><span class="n">parameters</span><span class="p">)</span>
</pre></div>
</div>
<ul class="simple">
<li>指定要输出的字段进行输出。以输出 <code class="code docutils literal"><span class="pre">value</span></code> 字段为例，代码如下：</li>
</ul>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">out</span> <span class="o">=</span> <span class="n">inferer</span><span class="o">.</span><span class="n">infer</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">data_batch</span><span class="p">,</span> <span class="n">field</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;value&quot;</span><span class="p">])</span>
</pre></div>
</div>
<p>需要注意的是：</p>
<ul class="simple">
<li>如果指定了2个layer作为输出层，实际上需要的输出结果是两个矩阵；</li>
<li>假设第一个layer的输出A是一个 N1 * M1 的矩阵，第二个 Layer 的输出B是一个 N2 * M2 的矩阵；</li>
<li>paddle.v2 默认会将A和B 横向拼接，当N1 和 N2 大小不一样时，会报如下的错误：</li>
</ul>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="ne">ValueError</span><span class="p">:</span> <span class="nb">all</span> <span class="n">the</span> <span class="nb">input</span> <span class="n">array</span> <span class="n">dimensions</span> <span class="k">except</span> <span class="k">for</span> <span class="n">the</span> <span class="n">concatenation</span> <span class="n">axis</span> <span class="n">must</span> <span class="n">match</span> <span class="n">exactly</span>
</pre></div>
</div>
<p>多个层的输出矩阵的高度不一致导致拼接失败，这种情况常常发生在：</p>
<ul class="simple">
<li>同时输出序列层和非序列层；</li>
<li>多个输出层处理多个不同长度的序列;</li>
</ul>
<p>此时可以在调用infer接口时通过设置 <code class="code docutils literal"><span class="pre">flatten_result=False</span></code> , 跳过“拼接”步骤，来解决上面的问题。这时，infer接口的返回值是一个python list:</p>
<ul class="simple">
<li>list 中元素的个数等于网络中输出层的个数；</li>
<li>list 中每个元素是一个layer的输出结果矩阵，类型是numpy的ndarray；</li>
<li>每一个layer输出矩阵的高度，在非序列输入时：等于样本数；序列输入时等于：输入序列中元素的总数；宽度等于配置中layer的size；</li>
</ul>
</div>
<div class="section" id="layeroutput">
<h2><a class="toc-backref" href="#id22">6.  如何在训练过程中获得某一个layer的output</a><a class="headerlink" href="#layeroutput" title="永久链接至标题">¶</a></h2>
<p>可以在event_handler中，通过 <code class="code docutils literal"><span class="pre">event.gm.getLayerOutputs(&quot;layer_name&quot;)</span></code> 获得在模型配置中某一层的name <code class="code docutils literal"><span class="pre">layer_name</span></code> 在当前
mini-batch forward的output的值。获得的值类型均为 <code class="code docutils literal"><span class="pre">numpy.ndarray</span></code> ，可以通过这个输出来完成自定义的评估指标计算等功能。例如下面代码：</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">score_diff</span><span class="p">(</span><span class="n">right_score</span><span class="p">,</span> <span class="n">left_score</span><span class="p">):</span>
    <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="n">average</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">abs</span><span class="p">(</span><span class="n">right_score</span> <span class="o">-</span> <span class="n">left_score</span><span class="p">))</span>

<span class="k">def</span> <span class="nf">event_handler</span><span class="p">(</span><span class="n">event</span><span class="p">):</span>
    <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">event</span><span class="p">,</span> <span class="n">paddle</span><span class="o">.</span><span class="n">event</span><span class="o">.</span><span class="n">EndIteration</span><span class="p">):</span>
        <span class="k">if</span> <span class="n">event</span><span class="o">.</span><span class="n">batch_id</span> <span class="o">%</span> <span class="mi">25</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
            <span class="n">diff</span> <span class="o">=</span> <span class="n">score_diff</span><span class="p">(</span>
                <span class="n">event</span><span class="o">.</span><span class="n">gm</span><span class="o">.</span><span class="n">getLayerOutputs</span><span class="p">(</span><span class="s2">&quot;right_score&quot;</span><span class="p">)[</span><span class="s2">&quot;right_score&quot;</span><span class="p">][</span>
                    <span class="s2">&quot;value&quot;</span><span class="p">],</span>
                <span class="n">event</span><span class="o">.</span><span class="n">gm</span><span class="o">.</span><span class="n">getLayerOutputs</span><span class="p">(</span><span class="s2">&quot;left_score&quot;</span><span class="p">)[</span><span class="s2">&quot;left_score&quot;</span><span class="p">][</span>
                    <span class="s2">&quot;value&quot;</span><span class="p">])</span>
            <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">((</span><span class="s2">&quot;Pass </span><span class="si">%d</span><span class="s2"> Batch </span><span class="si">%d</span><span class="s2"> : Cost </span><span class="si">%.6f</span><span class="s2">, &quot;</span>
                        <span class="s2">&quot;average absolute diff scores: </span><span class="si">%.6f</span><span class="s2">&quot;</span><span class="p">)</span> <span class="o">%</span>
                        <span class="p">(</span><span class="n">event</span><span class="o">.</span><span class="n">pass_id</span><span class="p">,</span> <span class="n">event</span><span class="o">.</span><span class="n">batch_id</span><span class="p">,</span> <span class="n">event</span><span class="o">.</span><span class="n">cost</span><span class="p">,</span> <span class="n">diff</span><span class="p">))</span>
</pre></div>
</div>
<p>注意：此方法不能获取 <code class="code docutils literal"><span class="pre">paddle.layer.recurrent_group</span></code> 里step的内容，但可以获取 <code class="code docutils literal"><span class="pre">paddle.layer.recurrent_group</span></code> 的输出。</p>
</div>
<div class="section" id="id9">
<h2><a class="toc-backref" href="#id23">7.  如何在训练过程中获得参数的权重和梯度</a><a class="headerlink" href="#id9" title="永久链接至标题">¶</a></h2>
<p>在某些情况下，获得当前mini-batch的权重（或称作weights, parameters）有助于在训练时观察具体数值，方便排查以及快速定位问题。
可以通过在 <code class="code docutils literal"><span class="pre">event_handler</span></code> 中打印其值（注意，需要使用 <code class="code docutils literal"><span class="pre">paddle.event.EndForwardBackward</span></code> 保证使用GPU训练时也可以获得），
示例代码如下：</p>
<div class="highlight-python"><div class="highlight"><pre><span></span><span class="o">...</span>
<span class="n">parameters</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">parameters</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">cost</span><span class="p">)</span>
<span class="o">...</span>
<span class="k">def</span> <span class="nf">event_handler</span><span class="p">(</span><span class="n">event</span><span class="p">):</span>
    <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">event</span><span class="p">,</span> <span class="n">paddle</span><span class="o">.</span><span class="n">event</span><span class="o">.</span><span class="n">EndForwardBackward</span><span class="p">):</span>
        <span class="k">if</span> <span class="n">event</span><span class="o">.</span><span class="n">batch_id</span> <span class="o">%</span> <span class="mi">25</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
            <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">parameters</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
                <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Param </span><span class="si">%s</span><span class="s2">, Grad </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span>
                    <span class="n">parameters</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">p</span><span class="p">),</span> <span class="n">parameters</span><span class="o">.</span><span class="n">get_grad</span><span class="p">(</span><span class="n">p</span><span class="p">))</span>
</pre></div>
</div>
<p>注意：“在训练过程中获得某一个layer的output”和“在训练过程中获得参数的权重和梯度”都会造成训练中的数据从C++拷贝到numpy，会对训练性能造成影响。不要在注重性能的训练场景下使用。</p>
</div>
</div>


           </div>
          </div>
          <footer>
  
    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
      
        <a href="../cluster/index_cn.html" class="btn btn-neutral float-right" title="集群训练与预测" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
      
      
        <a href="../parameter/index_cn.html" class="btn btn-neutral" title="参数设置" 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>