<!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>Optimizer — 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="Model Configuration" href="../model_configs.html"/> <link rel="next" title="Pooling" href="pooling.html"/> <link rel="prev" title="Evaluators" href="evaluators.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 current"><a class="reference internal" href="../../index_cn.html">API</a></li> <li class="toctree-l1"><a class="reference internal" href="../../../faq/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 current"><a class="reference internal" href="../../index_cn.html">API</a><ul class="current"> <li class="toctree-l2 current"><a class="reference internal" href="../model_configs.html">模型配置</a><ul class="current"> <li class="toctree-l3"><a class="reference internal" href="activation.html">Activation</a></li> <li class="toctree-l3"><a class="reference internal" href="layer.html">Layers</a></li> <li class="toctree-l3"><a class="reference internal" href="evaluators.html">Evaluators</a></li> <li class="toctree-l3 current"><a class="current reference internal" href="#">Optimizer</a></li> <li class="toctree-l3"><a class="reference internal" href="pooling.html">Pooling</a></li> <li class="toctree-l3"><a class="reference internal" href="networks.html">Networks</a></li> <li class="toctree-l3"><a class="reference internal" href="attr.html">Parameter Attribute</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../data.html">数据访问</a><ul> <li class="toctree-l3"><a class="reference internal" href="../data/data_reader.html">Data Reader Interface</a></li> <li class="toctree-l3"><a class="reference internal" href="../data/image.html">Image Interface</a></li> <li class="toctree-l3"><a class="reference internal" href="../data/dataset.html">Dataset</a></li> </ul> </li> <li class="toctree-l2"><a class="reference internal" href="../run_logic.html">训练与应用</a></li> <li class="toctree-l2"><a class="reference internal" href="../fluid.html">Fluid</a><ul> <li class="toctree-l3"><a class="reference internal" href="../fluid/layers.html">layers</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/data_feeder.html">data_feeder</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/executor.html">executor</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/initializer.html">initializer</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/evaluator.html">evaluator</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/nets.html">nets</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/optimizer.html">optimizer</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/param_attr.html">param_attr</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/profiler.html">profiler</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/regularizer.html">regularizer</a></li> <li class="toctree-l3"><a class="reference internal" href="../fluid/io.html">io</a></li> </ul> </li> </ul> </li> <li class="toctree-l1"><a class="reference internal" href="../../../faq/index_cn.html">FAQ</a><ul> <li class="toctree-l2"><a class="reference internal" href="../../../faq/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="../../../faq/model/index_cn.html">模型配置</a></li> <li class="toctree-l2"><a class="reference internal" href="../../../faq/parameter/index_cn.html">参数设置</a></li> <li class="toctree-l2"><a class="reference internal" href="../../../faq/local/index_cn.html">本地训练与预测</a></li> <li class="toctree-l2"><a class="reference internal" href="../../../faq/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">API</a> > </li> <li><a href="../model_configs.html">Model Configuration</a> > </li> <li>Optimizer</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="optimizer"> <h1>Optimizer<a class="headerlink" href="#optimizer" title="永久链接至标题">¶</a></h1> <div class="section" id="momentum"> <h2>Momentum<a class="headerlink" href="#momentum" title="永久链接至标题">¶</a></h2> <dl class="class"> <dt> <em class="property">class </em><code class="descclassname">paddle.v2.optimizer.</code><code class="descname">Momentum</code><span class="sig-paren">(</span><em>momentum=None</em>, <em>sparse=False</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt> <dd><p>Momentum Optimizer.</p> <p>When sparse=False, the momentum update formula is as follows:</p> <div class="math"> \[\begin{split}v_{t} &= k * v_{t-1} - \gamma_t (g_{t} + \lambda w_{t-1}) \\ w_{t} &= w_{t-1} + v_{t} \\\end{split}\]</div> <p>where, <span class="math">\(k\)</span> is momentum, <span class="math">\(\lambda\)</span> is decay rate, <span class="math">\(\gamma_t\)</span> is learning rate at the t’th iteration. <span class="math">\(w_{t}\)</span> is the weight as the t’th iteration. And the <span class="math">\(v_{t}\)</span> is the history momentum variable.</p> <p>When sparse=True, the update scheme:</p> <div class="math"> \[\begin{split}\alpha_t &= \alpha_{t-1} / k \\ \beta_t &= \beta_{t-1} / (1 + \lambda \gamma_t) \\ u_t &= u_{t-1} - \alpha_t \gamma_t g_t \\ v_t &= v_{t-1} + \tau_{t-1} \alpha_t \gamma_t g_t \\ \tau_t &= \tau_{t-1} + \beta_t / \alpha_t\end{split}\]</div> <p>where <span class="math">\(k\)</span> is momentum, <span class="math">\(\lambda\)</span> is decay rate, <span class="math">\(\gamma_t\)</span> is learning rate at the t’th iteration.</p> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name" /> <col class="field-body" /> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple"> <li><strong>momentum</strong> (<em>float</em>) – the momentum factor.</li> <li><strong>sparse</strong> (<em>bool</em>) – with sparse support or not, False by default.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> </div> <div class="section" id="adam"> <h2>Adam<a class="headerlink" href="#adam" title="永久链接至标题">¶</a></h2> <dl class="class"> <dt> <em class="property">class </em><code class="descclassname">paddle.v2.optimizer.</code><code class="descname">Adam</code><span class="sig-paren">(</span><em>beta1=0.9</em>, <em>beta2=0.999</em>, <em>epsilon=1e-08</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt> <dd><p>Adam optimizer. The details of please refer <a class="reference external" href="https://arxiv.org/abs/1412.6980">Adam: A Method for Stochastic Optimization</a></p> <div class="math"> \[\begin{split}m(w, t) & = \beta_1 m(w, t-1) + (1 - \beta_1) \nabla Q_i(w) \\ v(w, t) & = \beta_2 v(w, t-1) + (1 - \beta_2)(\nabla Q_i(w)) ^2 \\ w & = w - \frac{\eta m(w, t)}{\sqrt{v(w,t) + \epsilon}}\end{split}\]</div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name" /> <col class="field-body" /> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple"> <li><strong>beta1</strong> (<em>float</em>) – the <span class="math">\(\beta_1\)</span> in equation.</li> <li><strong>beta2</strong> (<em>float</em>) – the <span class="math">\(\beta_2\)</span> in equation.</li> <li><strong>epsilon</strong> (<em>float</em>) – the <span class="math">\(\epsilon\)</span> in equation. It is used to prevent divided by zero.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> </div> <div class="section" id="adamax"> <h2>Adamax<a class="headerlink" href="#adamax" title="永久链接至标题">¶</a></h2> <dl class="class"> <dt> <em class="property">class </em><code class="descclassname">paddle.v2.optimizer.</code><code class="descname">Adamax</code><span class="sig-paren">(</span><em>beta1=0.9</em>, <em>beta2=0.999</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt> <dd><p>Adamax optimizer.</p> <p>The details of please refer this <a class="reference external" href="https://arxiv.org/abs/1412.6980">Adam: A Method for Stochastic Optimization</a></p> <div class="math"> \[\begin{split}m_t & = \beta_1 * m_{t-1} + (1-\beta_1)* \nabla Q_i(w) \\ u_t & = max(\beta_2*u_{t-1}, abs(\nabla Q_i(w))) \\ w_t & = w_{t-1} - (\eta/(1-\beta_1^t))*m_t/u_t\end{split}\]</div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name" /> <col class="field-body" /> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple"> <li><strong>beta1</strong> (<em>float</em>) – the <span class="math">\(\beta_1\)</span> in the equation.</li> <li><strong>beta2</strong> (<em>float</em>) – the <span class="math">\(\beta_2\)</span> in the equation.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> </div> <div class="section" id="adagrad"> <h2>AdaGrad<a class="headerlink" href="#adagrad" title="永久链接至标题">¶</a></h2> <dl class="class"> <dt> <em class="property">class </em><code class="descclassname">paddle.v2.optimizer.</code><code class="descname">AdaGrad</code><span class="sig-paren">(</span><em>**kwargs</em><span class="sig-paren">)</span></dt> <dd><p>Adagrad(for ADAptive GRAdient algorithm) optimizer.</p> <p>For details please refer this <a class="reference external" href="http://www.magicbroom.info/Papers/DuchiHaSi10.pdf">Adaptive Subgradient Methods for Online Learning and Stochastic Optimization</a>.</p> <div class="math"> \[\begin{split}G &= \sum_{\tau=1}^{t} g_{\tau} g_{\tau}^T \\ w & = w - \eta diag(G)^{-\frac{1}{2}} \circ g\end{split}\]</div> </dd></dl> </div> <div class="section" id="decayedadagrad"> <h2>DecayedAdaGrad<a class="headerlink" href="#decayedadagrad" title="永久链接至标题">¶</a></h2> <dl class="class"> <dt> <em class="property">class </em><code class="descclassname">paddle.v2.optimizer.</code><code class="descname">DecayedAdaGrad</code><span class="sig-paren">(</span><em>rho=0.95</em>, <em>epsilon=1e-06</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt> <dd><p>AdaGrad method with decayed sum gradients. The equations of this method show as follow.</p> <div class="math"> \[\begin{split}E(g_t^2) &= \rho * E(g_{t-1}^2) + (1-\rho) * g^2 \\ learning\_rate &= 1/sqrt( ( E(g_t^2) + \epsilon )\end{split}\]</div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name" /> <col class="field-body" /> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple"> <li><strong>rho</strong> (<em>float</em>) – The <span class="math">\(\rho\)</span> parameter in that equation</li> <li><strong>epsilon</strong> (<em>float</em>) – The <span class="math">\(\epsilon\)</span> parameter in that equation.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> </div> <div class="section" id="adadelta"> <h2>AdaDelta<a class="headerlink" href="#adadelta" title="永久链接至标题">¶</a></h2> <dl class="class"> <dt> <em class="property">class </em><code class="descclassname">paddle.v2.optimizer.</code><code class="descname">AdaDelta</code><span class="sig-paren">(</span><em>rho=0.95</em>, <em>epsilon=1e-06</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt> <dd><p>AdaDelta method. The details of adadelta please refer to this <a class="reference external" href="http://www.matthewzeiler.com/pubs/googleTR2012/googleTR2012.pdf">ADADELTA: AN ADAPTIVE LEARNING RATE METHOD</a>.</p> <div class="math"> \[\begin{split}E(g_t^2) &= \rho * E(g_{t-1}^2) + (1-\rho) * g^2 \\ learning\_rate &= sqrt( ( E(dx_{t-1}^2) + \epsilon ) / ( \ E(g_t^2) + \epsilon ) ) \\ E(dx_t^2) &= \rho * E(dx_{t-1}^2) + (1-\rho) * (-g*learning\_rate)^2\end{split}\]</div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name" /> <col class="field-body" /> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple"> <li><strong>rho</strong> (<em>float</em>) – <span class="math">\(\rho\)</span> in equation</li> <li><strong>epsilon</strong> (<em>float</em>) – <span class="math">\(\rho\)</span> in equation</li> </ul> </td> </tr> </tbody> </table> </dd></dl> </div> <div class="section" id="rmsprop"> <h2>RMSProp<a class="headerlink" href="#rmsprop" title="永久链接至标题">¶</a></h2> <dl class="class"> <dt> <em class="property">class </em><code class="descclassname">paddle.v2.optimizer.</code><code class="descname">RMSProp</code><span class="sig-paren">(</span><em>rho=0.95</em>, <em>epsilon=1e-06</em>, <em>**kwargs</em><span class="sig-paren">)</span></dt> <dd><p>RMSProp(for Root Mean Square Propagation) optimizer. For details please refer this <a class="reference external" href="http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf">slide</a>.</p> <p>The equations of this method as follows:</p> <div class="math"> \[\begin{split}v(w, t) & = \rho v(w, t-1) + (1 - \rho)(\nabla Q_{i}(w))^2 \\ w & = w - \frac{\eta} {\sqrt{v(w,t) + \epsilon}} \nabla Q_{i}(w)\end{split}\]</div> <table class="docutils field-list" frame="void" rules="none"> <col class="field-name" /> <col class="field-body" /> <tbody valign="top"> <tr class="field-odd field"><th class="field-name">参数:</th><td class="field-body"><ul class="first last simple"> <li><strong>rho</strong> (<em>float</em>) – the <span class="math">\(\rho\)</span> in the equation. The forgetting factor.</li> <li><strong>epsilon</strong> (<em>float</em>) – the <span class="math">\(\epsilon\)</span> in the equation.</li> </ul> </td> </tr> </tbody> </table> </dd></dl> </div> </div> </div> </div> <footer> <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> <a href="pooling.html" class="btn btn-neutral float-right" title="Pooling" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a> <a href="evaluators.html" class="btn btn-neutral" title="Evaluators" 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>