<!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>模型配置 — 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="参数设置" href="../parameter/index_cn.html"/> <link rel="prev" title="编译安装与单元测试" href="../build_and_install/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="../../howto/index_cn.html">进阶指南</a></li> <li class="toctree-l1"><a class="reference internal" href="../../api/index_cn.html">API</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/build_and_install/index_cn.html">安装与编译</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/pip_install_cn.html">使用pip安装</a></li> <li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/docker_install_cn.html">使用Docker安装运行</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/dev/build_cn.html">用Docker编译和测试PaddlePaddle</a></li> <li class="toctree-l3"><a class="reference internal" href="../../getstarted/build_and_install/build_from_source_cn.html">从源码编译</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../../getstarted/concepts/use_concepts_cn.html">基本使用概念</a></li> </ul> </li> <li class="toctree-l1"><a class="reference internal" href="../../howto/index_cn.html">进阶指南</a><ul> <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/cmd_parameter/index_cn.html">设置命令行参数</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/use_case_cn.html">使用案例</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/arguments_cn.html">参数概述</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cmd_parameter/detail_introduction_cn.html">细节描述</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/cluster/cluster_train_cn.html">分布式训练</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cluster/fabric_cn.html">fabric集群</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cluster/openmpi_cn.html">openmpi集群</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cluster/k8s_cn.html">kubernetes单机</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cluster/k8s_distributed_cn.html">kubernetes distributed分布式</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/cluster/k8s_aws_cn.html">AWS上运行kubernetes集群训练</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../../howto/usage/capi/index_cn.html">PaddlePaddle C-API</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/capi/compile_paddle_lib_cn.html">编译 PaddlePaddle 预测库</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/usage/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/usage/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/dev/contribute_to_paddle_cn.html">如何贡献代码</a></li> <li class="toctree-l2"><a class="reference internal" href="../../howto/dev/write_docs_cn.html">如何贡献/修改文档</a></li> <li class="toctree-l2"><a class="reference internal" href="../../howto/deep_model/rnn/index_cn.html">RNN相关模型</a><ul> <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/rnn_config_cn.html">RNN配置</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/recurrent_group_cn.html">Recurrent Group教程</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hierarchical_layer_cn.html">支持双层序列作为输入的Layer</a></li> <li class="toctree-l3"><a class="reference internal" href="../../howto/deep_model/rnn/hrnn_rnn_api_compare_cn.html">单双层RNN API对比介绍</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../../howto/optimization/gpu_profiling_cn.html">GPU性能分析与调优</a></li> </ul> </li> <li class="toctree-l1"><a class="reference internal" href="../../api/index_cn.html">API</a><ul> <li class="toctree-l2"><a class="reference internal" href="../../api/v2/model_configs.html">模型配置</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">数据访问</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">训练与应用</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">data_feeder</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">param_attr</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 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 current"><a class="current reference internal" href="#">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"><a class="reference internal" href="../local/index_cn.html">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>模型配置</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="#id2">模型配置</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="id2">模型配置</a><ul> <li><a class="reference internal" href="#duplicated-layer-name" id="id3">1. 出现 <code class="code docutils literal"><span class="pre">Duplicated</span> <span class="pre">layer</span> <span class="pre">name</span></code> 错误怎么办</a></li> <li><a class="reference internal" href="#paddle-layer-memory-name" id="id4">2. <code class="code docutils literal"><span class="pre">paddle.layer.memory</span></code> 的参数 <code class="code docutils literal"><span class="pre">name</span></code> 如何使用</a></li> <li><a class="reference internal" href="#drop-out" id="id5">3. 两种使用 drop_out 的方法有何区别</a></li> <li><a class="reference internal" href="#recurrent-layer" id="id6">4. 不同的 recurrent layer 的区别</a></li> <li><a class="reference internal" href="#paddlepaddlesoftmax" id="id7">5. PaddlePaddle的softmax能否指定计算的维度</a></li> <li><a class="reference internal" href="#paddlepaddle" id="id8">6. PaddlePaddle是否支持维数可变的数据输入</a></li> </ul> </li> </ul> </div> <div class="section" id="duplicated-layer-name"> <h2><a class="toc-backref" href="#id3">1. 出现 <code class="code docutils literal"><span class="pre">Duplicated</span> <span class="pre">layer</span> <span class="pre">name</span></code> 错误怎么办</a><a class="headerlink" href="#duplicated-layer-name" title="永久链接至标题">¶</a></h2> <p>出现该错误的原因一般是用户对不同layer的参数 <code class="code docutils literal"><span class="pre">name</span></code> 设置了相同的取值。遇到该错误时,先找出参数 <code class="code docutils literal"><span class="pre">name</span></code> 取值相同的layer,然后将这些layer的参数 <code class="code docutils literal"><span class="pre">name</span></code> 设置为不同的值。</p> </div> <div class="section" id="paddle-layer-memory-name"> <h2><a class="toc-backref" href="#id4">2. <code class="code docutils literal"><span class="pre">paddle.layer.memory</span></code> 的参数 <code class="code docutils literal"><span class="pre">name</span></code> 如何使用</a><a class="headerlink" href="#paddle-layer-memory-name" title="永久链接至标题">¶</a></h2> <ul class="simple"> <li><code class="code docutils literal"><span class="pre">paddle.layer.memory</span></code> 用于获取特定layer上一时间步的输出,该layer是通过参数 <code class="code docutils literal"><span class="pre">name</span></code> 指定,即,<code class="code docutils literal"><span class="pre">paddle.layer.memory</span></code> 会关联参数 <code class="code docutils literal"><span class="pre">name</span></code> 取值相同的layer,并将该layer上一时间步的输出作为自身当前时间步的输出。</li> <li>PaddlePaddle的所有layer都有唯一的name,用户通过参数 <code class="code docutils literal"><span class="pre">name</span></code> 设定,当用户没有显式设定时,PaddlePaddle会自动设定。而 <code class="code docutils literal"><span class="pre">paddle.layer.memory</span></code> 不是真正的layer,其name由参数 <code class="code docutils literal"><span class="pre">memory_name</span></code> 设定,当用户没有显式设定时,PaddlePaddle会自动设定。<code class="code docutils literal"><span class="pre">paddle.layer.memory</span></code> 的参数 <code class="code docutils literal"><span class="pre">name</span></code> 用于指定其要关联的layer,需要用户显式设定。</li> </ul> </div> <div class="section" id="drop-out"> <h2><a class="toc-backref" href="#id5">3. 两种使用 drop_out 的方法有何区别</a><a class="headerlink" href="#drop-out" title="永久链接至标题">¶</a></h2> <ul> <li><p class="first">在PaddlePaddle中使用dropout有两种方式</p> <ul class="simple"> <li>在相应layer的 <code class="code docutils literal"><span class="pre">layer_atter</span></code> 设置 <code class="code docutils literal"><span class="pre">drop_rate</span></code>,以 <code class="code docutils literal"><span class="pre">paddle.layer.fc</span></code> 为例,代码如下:</li> </ul> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">fc</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</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="nb">input</span><span class="p">,</span> <span class="n">layer_attr</span><span class="o">=</span><span class="n">paddle</span><span class="o">.</span><span class="n">attr</span><span class="o">.</span><span class="n">ExtraLayerAttribute</span><span class="p">(</span><span class="n">drop_rate</span><span class="o">=</span><span class="mf">0.5</span><span class="p">))</span> </pre></div> </div> <ul class="simple"> <li>使用 <code class="code docutils literal"><span class="pre">paddle.layer.dropout</span></code>,以 <code class="code docutils literal"><span class="pre">paddle.layer.fc</span></code> 为例,代码如下:</li> </ul> <div class="highlight-python"><div class="highlight"><pre><span></span><span class="n">fc</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</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="nb">input</span><span class="p">)</span> <span class="n">drop_fc</span> <span class="o">=</span> <span class="n">paddle</span><span class="o">.</span><span class="n">layer</span><span class="o">.</span><span class="n">dropout</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">fc</span><span class="p">,</span> <span class="n">dropout_rate</span><span class="o">=</span><span class="mf">0.5</span><span class="p">)</span> </pre></div> </div> </li> <li><p class="first"><code class="code docutils literal"><span class="pre">paddle.layer.dropout</span></code> 实际上使用了 <code class="code docutils literal"><span class="pre">paddle.layer.add_to</span></code>,并在该layer里采用第一种方式设置 <code class="code docutils literal"><span class="pre">drop_rate</span></code> 来使用dropout的。这种方式对内存消耗较大。</p> </li> <li><p class="first">PaddlePaddle在激活函数里实现dropout,而不是在layer里实现。</p> </li> <li><p class="first"><code class="code docutils literal"><span class="pre">paddle.layer.lstmemory</span></code>、<code class="code docutils literal"><span class="pre">paddle.layer.grumemory</span></code>、<code class="code docutils literal"><span class="pre">paddle.layer.recurrent</span></code> 不是通过一般的方式来实现对输出的激活,所以不能采用第一种方式在这几个layer里设置 <code class="code docutils literal"><span class="pre">drop_rate</span></code> 来使用dropout。若要对这几个layer使用dropout,可采用第二种方式,即使用 <code class="code docutils literal"><span class="pre">paddle.layer.dropout</span></code>。</p> </li> </ul> </div> <div class="section" id="recurrent-layer"> <h2><a class="toc-backref" href="#id6">4. 不同的 recurrent layer 的区别</a><a class="headerlink" href="#recurrent-layer" title="永久链接至标题">¶</a></h2> <p>以LSTM为例,在PaddlePaddle中包含以下 recurrent layer:</p> <ul class="simple"> <li><code class="code docutils literal"><span class="pre">paddle.layer.lstmemory</span></code></li> <li><code class="code docutils literal"><span class="pre">paddle.networks.simple_lstm</span></code></li> <li><code class="code docutils literal"><span class="pre">paddle.networks.lstmemory_group</span></code></li> <li><code class="code docutils literal"><span class="pre">paddle.networks.bidirectional_lstm</span></code></li> </ul> <p>按照具体实现方式可以归纳为2类:</p> <ol class="arabic simple"> <li>由 recurrent_group 实现的 recurrent layer:</li> </ol> <blockquote> <div><ul class="simple"> <li>用户在使用这一类recurrent layer时,可以访问由recurrent unit在一个时间步内计算得到的中间值(例如:hidden states, memory cells等);</li> <li>上述的 <code class="code docutils literal"><span class="pre">paddle.networks.lstmemory_group</span></code> 是这一类的 recurrent layer ;</li> </ul> </div></blockquote> <ol class="arabic simple" start="2"> <li>将recurrent layer作为一个整体来实现:</li> </ol> <blockquote> <div><ul class="simple"> <li>用户在使用这一类recurrent layer,只能访问它们的输出值;</li> <li>上述的 <code class="code docutils literal"><span class="pre">paddle.networks.lstmemory_group</span></code> 、 <code class="code docutils literal"><span class="pre">paddle.networks.simple_lstm</span></code> 和 <code class="code docutils literal"><span class="pre">paddle.networks.bidirectional_lstm</span></code> 属于这一类的实现;</li> </ul> </div></blockquote> <p>将recurrent layer作为一个整体来实现, 能够针对CPU和GPU的计算做更多优化, 所以相比于recurrent group的实现方式, 第二类 recurrent layer 计算效率更高。 在实际应用中,如果用户不需要访问LSTM的中间变量,而只需要获得recurrent layer计算的输出,我们建议使用第二类实现。</p> <p>此外,关于LSTM, PaddlePaddle中还包含 <code class="code docutils literal"><span class="pre">paddle.networks.lstmemory_unit</span></code> 这一计算单元:</p> <blockquote> <div><ul class="simple"> <li>不同于上述介绍的recurrent layer , <code class="code docutils literal"><span class="pre">paddle.networks.lstmemory_unit</span></code> 定义了LSTM单元在一个时间步内的计算过程,它并不是一个完整的recurrent layer,也不能接收序列数据作为输入;</li> <li><code class="code docutils literal"><span class="pre">paddle.networks.lstmemory_unit</span></code> 只能在recurrent_group中作为step function使用;</li> </ul> </div></blockquote> </div> <div class="section" id="paddlepaddlesoftmax"> <h2><a class="toc-backref" href="#id7">5. PaddlePaddle的softmax能否指定计算的维度</a><a class="headerlink" href="#paddlepaddlesoftmax" title="永久链接至标题">¶</a></h2> <p>PaddlePaddle的softmax不能指定计算维度,只能按行计算。 在图像任务中,对于NCHW,如果需要在C维度计算softmax,可以先使用 <code class="code docutils literal"><span class="pre">paddle.layer.switch_order</span></code> 改变维度顺序,即将NCHW转换成NHWC,再做一定的reshape,最后计算softmax。</p> </div> <div class="section" id="paddlepaddle"> <h2><a class="toc-backref" href="#id8">6. PaddlePaddle是否支持维数可变的数据输入</a><a class="headerlink" href="#paddlepaddle" title="永久链接至标题">¶</a></h2> <p>PaddlePaddle提供的 <code class="code docutils literal"><span class="pre">paddle.data_type.dense_array</span></code> 支持维数可变的数据输入。在使用时,将对应数据层的维数设置成一个大于输入数据维数的值用于占位即可。</p> </div> </div> </div> </div> <footer> <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> <a href="../parameter/index_cn.html" class="btn btn-neutral float-right" title="参数设置" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a> <a href="../build_and_install/index_cn.html" class="btn btn-neutral" title="编译安装与单元测试" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a> </div> <hr/> <div role="contentinfo"> <p> © 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>