index.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 http-equiv="X-UA-Compatible" content="IE=edge">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  
  
  <link rel="shortcut icon" href="../../img/favicon.ico">
  <title>剪枝与敏感度 - PaddleSlim Docs</title>
  <link href='https://fonts.googleapis.com/css?family=Lato:400,700|Roboto+Slab:400,700|Inconsolata:400,700' rel='stylesheet' type='text/css'>

  <link rel="stylesheet" href="../../css/theme.css" type="text/css" />
  <link rel="stylesheet" href="../../css/theme_extra.css" type="text/css" />
  <link rel="stylesheet" href="//cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/github.min.css">
  
  <script>
    // Current page data
    var mkdocs_page_name = "\u526a\u679d\u4e0e\u654f\u611f\u5ea6";
    var mkdocs_page_input_path = "api/prune_api.md";
    var mkdocs_page_url = null;
  </script>
  
  <script src="../../js/jquery-2.1.1.min.js" defer></script>
  <script src="../../js/modernizr-2.8.3.min.js" defer></script>
  <script src="//cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/highlight.min.js"></script>
  <script>hljs.initHighlightingOnLoad();</script> 
  
</head>

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

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

    
    <nav data-toggle="wy-nav-shift" class="wy-nav-side stickynav">
      <div class="wy-side-nav-search">
        <a href="../.." class="icon icon-home"> PaddleSlim Docs</a>
        <div role="search">
  <form id ="rtd-search-form" class="wy-form" action="../../search.html" method="get">
    <input type="text" name="q" placeholder="Search docs" title="Type search term here" />
  </form>
</div>
      </div>

      <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
	<ul class="current">
	  
          
            <li class="toctree-l1">
		
    <a class="" href="../..">Home</a>
	    </li>
          
            <li class="toctree-l1">
		
    <a class="" href="../../model_zoo/">模型库</a>
	    </li>
          
            <li class="toctree-l1">
		
    <span class="caption-text">教程</span>
    <ul class="subnav">
                <li class="">
                    
    <a class="" href="../../tutorials/quant_post_demo/">离线量化</a>
                </li>
                <li class="">
                    
    <a class="" href="../../tutorials/quant_aware_demo/">量化训练</a>
                </li>
                <li class="">
                    
    <a class="" href="../../tutorials/quant_embedding_demo/">Embedding量化</a>
                </li>
                <li class="">
                    
    <a class="" href="../../tutorials/nas_demo/">SA搜索</a>
                </li>
                <li class="">
                    
    <a class="" href="../../tutorials/distillation_demo/">知识蒸馏</a>
                </li>
    </ul>
	    </li>
          
            <li class="toctree-l1">
		
    <span class="caption-text">API</span>
    <ul class="subnav">
                <li class="">
                    
    <a class="" href="../quantization_api/">量化</a>
                </li>
                <li class=" current">
                    
    <a class="current" href="./">剪枝与敏感度</a>
    <ul class="subnav">
            
    <li class="toctree-l3"><a href="#pruner">Pruner</a></li>
    

    <li class="toctree-l3"><a href="#sensitivity">sensitivity</a></li>
    

    <li class="toctree-l3"><a href="#merge_sensitive">merge_sensitive</a></li>
    

    <li class="toctree-l3"><a href="#load_sensitivities">load_sensitivities</a></li>
    

    <li class="toctree-l3"><a href="#get_ratios_by_loss">get_ratios_by_loss</a></li>
    

    </ul>
                </li>
                <li class="">
                    
    <a class="" href="../analysis_api/">模型分析</a>
                </li>
                <li class="">
                    
    <a class="" href="../single_distiller_api/">知识蒸馏</a>
                </li>
                <li class="">
                    
    <a class="" href="../nas_api/">SA搜索</a>
                </li>
                <li class="">
                    
    <a class="" href="../../search_space/">搜索空间</a>
                </li>
                <li class="">
                    
    <a class="" href="../../table_latency/">硬件延时评估表</a>
                </li>
    </ul>
	    </li>
          
            <li class="toctree-l1">
		
    <a class="" href="../../algo/algo/">算法原理</a>
	    </li>
          
        </ul>
      </div>
      &nbsp;
    </nav>

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

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

      
      <div class="wy-nav-content">
        <div class="rst-content">
          <div role="navigation" aria-label="breadcrumbs navigation">
  <ul class="wy-breadcrumbs">
    <li><a href="../..">Docs</a> &raquo;</li>
    
      
          <li>API &raquo;</li>
        
      
    <li>剪枝与敏感度</li>
    <li class="wy-breadcrumbs-aside">
      
        <a href="https://github.com/PaddlePaddle/PaddleSlim/blob/develop/docs/docs/api/prune_api.md"
          class="icon icon-github"> Edit on GitHub</a>
      
    </li>
  </ul>
  <hr/>
</div>
          <div role="main">
            <div class="section">
              
                <h2 id="pruner">Pruner<a class="headerlink" href="#pruner" title="Permanent link">#</a></h2>
<dl>
<dt>paddleslim.prune.Pruner(criterion="l1_norm")<a href="https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/pruner.py#L28">[源代码]</a></dt>
<dd>
<p>对卷积网络的通道进行一次剪裁。剪裁一个卷积层的通道，是指剪裁该卷积层输出的通道。卷积层的权重形状为<code>[output_channel, input_channel, kernel_size, kernel_size]</code>，通过剪裁该权重的第一纬度达到剪裁输出通道数的目的。</p>
</dd>
</dl>
<p><strong>参数：</strong></p>
<ul>
<li><strong>criterion</strong> - 评估一个卷积层内通道重要性所参考的指标。目前仅支持<code>l1_norm</code>。默认为<code>l1_norm</code>。</li>
</ul>
<p><strong>返回：</strong> 一个Pruner类的实例</p>
<p><strong>示例代码：</strong></p>
<table class="codehilitetable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span>1
2</pre></div></td><td class="code"><div class="codehilite"><pre><span></span><span class="kn">from</span> <span class="nn">paddleslim.prune</span> <span class="kn">import</span> <span class="n">Pruner</span>
<span class="n">pruner</span> <span class="o">=</span> <span class="n">Pruner</span><span class="p">()</span>
</pre></div>
</td></tr></table>

<dl>
<dt>paddleslim.prune.Pruner.prune(program, scope, params, ratios, place=None, lazy=False, only_graph=False, param_backup=False, param_shape_backup=False)<a href="https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/pruner.py#L36">[源代码]</a></dt>
<dd>
<p>对目标网络的一组卷积层的权重进行裁剪。</p>
</dd>
</dl>
<p><strong>参数：</strong></p>
<ul>
<li>
<p><strong>program(paddle.fluid.Program)</strong> - 要裁剪的目标网络。更多关于Program的介绍请参考：<a href="https://www.paddlepaddle.org.cn/documentation/docs/zh/api_cn/fluid_cn/Program_cn.html#program">Program概念介绍</a>。</p>
</li>
<li>
<p><strong>scope(paddle.fluid.Scope)</strong> - 要裁剪的权重所在的<code>scope</code>，Paddle中用<code>scope</code>实例存放模型参数和运行时变量的值。Scope中的参数值会被<code>inplace</code>的裁剪。更多介绍请参考<a href="">Scope概念介绍</a></p>
</li>
<li>
<p><strong>params(list<str>)</strong> - 需要被裁剪的卷积层的参数的名称列表。可以通过以下方式查看模型中所有参数的名称:
<table class="codehilitetable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span>1
2
3</pre></div></td><td class="code"><div class="codehilite"><pre><span></span><span class="k">for</span> <span class="nv">block</span> <span class="nv">in</span> <span class="nv">program</span>.<span class="nv">blocks</span>:
    <span class="k">for</span> <span class="nv">param</span> <span class="nv">in</span> <span class="nv">block</span>.<span class="nv">all_parameters</span><span class="ss">()</span>:
        <span class="nv">print</span><span class="ss">(</span><span class="s2">&quot;</span><span class="s">param: {}; shape: {}</span><span class="s2">&quot;</span>.<span class="nv">format</span><span class="ss">(</span><span class="nv">param</span>.<span class="nv">name</span>, <span class="nv">param</span>.<span class="nv">shape</span><span class="ss">))</span>
</pre></div>
</td></tr></table></p>
</li>
<li>
<p><strong>ratios(list<float>)</strong> - 用于裁剪<code>params</code>的剪切率，类型为列表。该列表长度必须与<code>params</code>的长度一致。</p>
</li>
<li>
<p><strong>place(paddle.fluid.Place)</strong> - 待裁剪参数所在的设备位置，可以是<code>CUDAPlace</code>或<code>CPUPlace</code>。<a href="">Place概念介绍</a></p>
</li>
<li>
<p><strong>lazy(bool)</strong> - <code>lazy</code>为True时，通过将指定通道的参数置零达到裁剪的目的，参数的<code>shape保持不变</code>；<code>lazy</code>为False时，直接将要裁的通道的参数删除，参数的<code>shape</code>会发生变化。</p>
</li>
<li>
<p><strong>only_graph(bool)</strong> - 是否只裁剪网络结构。在Paddle中，Program定义了网络结构，Scope存储参数的数值。一个Scope实例可以被多个Program使用，比如定义了训练网络的Program和定义了测试网络的Program是使用同一个Scope实例的。<code>only_graph</code>为True时，只对Program中定义的卷积的通道进行剪裁；<code>only_graph</code>为false时，Scope中卷积参数的数值也会被剪裁。默认为False。</p>
</li>
<li>
<p><strong>param_backup(bool)</strong> - 是否返回对参数值的备份。默认为False。</p>
</li>
<li>
<p><strong>param_shape_backup(bool)</strong> - 是否返回对参数<code>shape</code>的备份。默认为False。</p>
</li>
</ul>
<p><strong>返回：</strong></p>
<ul>
<li>
<p><strong>pruned_program(paddle.fluid.Program)</strong> - 被裁剪后的Program。</p>
</li>
<li>
<p><strong>param_backup(dict)</strong> - 对参数数值的备份，用于恢复Scope中的参数数值。</p>
</li>
<li>
<p><strong>param_shape_backup(dict)</strong> - 对参数形状的备份。</p>
</li>
</ul>
<p><strong>示例：</strong></p>
<p>点击<a href="https://aistudio.baidu.com/aistudio/projectDetail/200786">AIStudio</a>执行以下示例代码。
<table class="codehilitetable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span> 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71</pre></div></td><td class="code"><div class="codehilite"><pre><span></span><span class="kn">import</span> <span class="nn">paddle.fluid</span> <span class="kn">as</span> <span class="nn">fluid</span>
<span class="kn">from</span> <span class="nn">paddle.fluid.param_attr</span> <span class="kn">import</span> <span class="n">ParamAttr</span>
<span class="kn">from</span> <span class="nn">paddleslim.prune</span> <span class="kn">import</span> <span class="n">Pruner</span>

<span class="k">def</span> <span class="nf">conv_bn_layer</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span>
                  <span class="n">num_filters</span><span class="p">,</span>
                  <span class="n">filter_size</span><span class="p">,</span>
                  <span class="n">name</span><span class="p">,</span>
                  <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
                  <span class="n">groups</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">conv</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">conv2d</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">num_filters</span><span class="o">=</span><span class="n">num_filters</span><span class="p">,</span>
        <span class="n">filter_size</span><span class="o">=</span><span class="n">filter_size</span><span class="p">,</span>
        <span class="n">stride</span><span class="o">=</span><span class="n">stride</span><span class="p">,</span>
        <span class="n">padding</span><span class="o">=</span><span class="p">(</span><span class="n">filter_size</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span>
        <span class="n">groups</span><span class="o">=</span><span class="n">groups</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">param_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;_weights&quot;</span><span class="p">),</span>
        <span class="n">bias_attr</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
        <span class="n">name</span><span class="o">=</span><span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;_out&quot;</span><span class="p">)</span>
    <span class="n">bn_name</span> <span class="o">=</span> <span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;_bn&quot;</span>
    <span class="k">return</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">batch_norm</span><span class="p">(</span>
        <span class="nb">input</span><span class="o">=</span><span class="n">conv</span><span class="p">,</span>
        <span class="n">act</span><span class="o">=</span><span class="n">act</span><span class="p">,</span>
        <span class="n">name</span><span class="o">=</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_output&#39;</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">name</span><span class="o">=</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_scale&#39;</span><span class="p">),</span>
        <span class="n">bias_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_offset&#39;</span><span class="p">),</span>
        <span class="n">moving_mean_name</span><span class="o">=</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_mean&#39;</span><span class="p">,</span>
        <span class="n">moving_variance_name</span><span class="o">=</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_variance&#39;</span><span class="p">,</span> <span class="p">)</span>

<span class="n">main_program</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">Program</span><span class="p">()</span>
<span class="n">startup_program</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">Program</span><span class="p">()</span>
<span class="c1">#   X       X              O       X              O</span>
<span class="c1"># conv1--&gt;conv2--&gt;sum1--&gt;conv3--&gt;conv4--&gt;sum2--&gt;conv5--&gt;conv6</span>
<span class="c1">#     |            ^ |                    ^</span>
<span class="c1">#     |____________| |____________________|</span>
<span class="c1">#</span>
<span class="c1"># X: prune output channels</span>
<span class="c1"># O: prune input channels</span>
<span class="k">with</span> <span class="n">fluid</span><span class="o">.</span><span class="n">program_guard</span><span class="p">(</span><span class="n">main_program</span><span class="p">,</span> <span class="n">startup_program</span><span class="p">):</span>
    <span class="nb">input</span> <span class="o">=</span> <span class="n">fluid</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="s2">&quot;image&quot;</span><span class="p">,</span> <span class="n">shape</span><span class="o">=</span><span class="p">[</span><span class="bp">None</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">16</span><span class="p">,</span> <span class="mi">16</span><span class="p">])</span>
    <span class="n">conv1</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv1&quot;</span><span class="p">)</span>
    <span class="n">conv2</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">conv1</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv2&quot;</span><span class="p">)</span>
    <span class="n">sum1</span> <span class="o">=</span> <span class="n">conv1</span> <span class="o">+</span> <span class="n">conv2</span>
    <span class="n">conv3</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">sum1</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv3&quot;</span><span class="p">)</span>
    <span class="n">conv4</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">conv3</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv4&quot;</span><span class="p">)</span>
    <span class="n">sum2</span> <span class="o">=</span> <span class="n">conv4</span> <span class="o">+</span> <span class="n">sum1</span>
    <span class="n">conv5</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">sum2</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv5&quot;</span><span class="p">)</span>
    <span class="n">conv6</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">conv5</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv6&quot;</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">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">scope</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">Scope</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">startup_program</span><span class="p">,</span> <span class="n">scope</span><span class="o">=</span><span class="n">scope</span><span class="p">)</span>
<span class="n">pruner</span> <span class="o">=</span> <span class="n">Pruner</span><span class="p">()</span>
<span class="n">main_program</span><span class="p">,</span> <span class="n">_</span><span class="p">,</span> <span class="n">_</span> <span class="o">=</span> <span class="n">pruner</span><span class="o">.</span><span class="n">prune</span><span class="p">(</span>
    <span class="n">main_program</span><span class="p">,</span>
    <span class="n">scope</span><span class="p">,</span>
    <span class="n">params</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;conv4_weights&quot;</span><span class="p">],</span>
    <span class="n">ratios</span><span class="o">=</span><span class="p">[</span><span class="mf">0.5</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">lazy</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
    <span class="n">only_graph</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
    <span class="n">param_backup</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
    <span class="n">param_shape_backup</span><span class="o">=</span><span class="bp">False</span><span class="p">)</span>

<span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="n">main_program</span><span class="o">.</span><span class="n">global_block</span><span class="p">()</span><span class="o">.</span><span class="n">all_parameters</span><span class="p">():</span>
    <span class="k">if</span> <span class="s2">&quot;weights&quot;</span> <span class="ow">in</span> <span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">:</span>
        <span class="k">print</span><span class="p">(</span><span class="s2">&quot;param name: {}; param shape: {}&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">param</span><span class="o">.</span><span class="n">shape</span><span class="p">))</span>
</pre></div>
</td></tr></table></p>
<hr />
<h2 id="sensitivity">sensitivity<a class="headerlink" href="#sensitivity" title="Permanent link">#</a></h2>
<dl>
<dt>paddleslim.prune.sensitivity(program, place, param_names, eval_func, sensitivities_file=None, pruned_ratios=None) <a href="https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/sensitive.py#L34">[源代码]</a></dt>
<dd>
<p>计算网络中每个卷积层的敏感度。每个卷积层的敏感度信息统计方法为：依次剪掉当前卷积层不同比例的输出通道数，在测试集上计算剪裁后的精度损失。得到敏感度信息后，可以通过观察或其它方式确定每层卷积的剪裁率。</p>
</dd>
</dl>
<p><strong>参数：</strong></p>
<ul>
<li>
<p><strong>program(paddle.fluid.Program)</strong> - 待评估的目标网络。更多关于Program的介绍请参考：<a href="https://www.paddlepaddle.org.cn/documentation/docs/zh/api_cn/fluid_cn/Program_cn.html#program">Program概念介绍</a>。</p>
</li>
<li>
<p><strong>place(paddle.fluid.Place)</strong> - 待分析的参数所在的设备位置，可以是<code>CUDAPlace</code>或<code>CPUPlace</code>。<a href="">Place概念介绍</a></p>
</li>
<li>
<p><strong>param_names(list<str>)</strong> - 待分析的卷积层的参数的名称列表。可以通过以下方式查看模型中所有参数的名称:</p>
</li>
</ul>
<table class="codehilitetable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span>1
2
3</pre></div></td><td class="code"><div class="codehilite"><pre><span></span><span class="k">for</span> <span class="nv">block</span> <span class="nv">in</span> <span class="nv">program</span>.<span class="nv">blocks</span>:
    <span class="k">for</span> <span class="nv">param</span> <span class="nv">in</span> <span class="nv">block</span>.<span class="nv">all_parameters</span><span class="ss">()</span>:
        <span class="nv">print</span><span class="ss">(</span><span class="s2">&quot;</span><span class="s">param: {}; shape: {}</span><span class="s2">&quot;</span>.<span class="nv">format</span><span class="ss">(</span><span class="nv">param</span>.<span class="nv">name</span>, <span class="nv">param</span>.<span class="nv">shape</span><span class="ss">))</span>
</pre></div>
</td></tr></table>

<ul>
<li>
<p><strong>eval_func(function)</strong> - 用于评估裁剪后模型效果的回调函数。该回调函数接受被裁剪后的<code>program</code>为参数，返回一个表示当前program的精度，用以计算当前裁剪带来的精度损失。</p>
</li>
<li>
<p><strong>sensitivities_file(str)</strong> - 保存敏感度信息的本地文件系统的文件。在敏感度计算过程中，会持续将新计算出的敏感度信息追加到该文件中。重启任务后，文件中已有敏感度信息不会被重复计算。该文件可以用<code>pickle</code>加载。</p>
</li>
<li>
<p><strong>pruned_ratios(list<float>)</strong> - 计算卷积层敏感度信息时，依次剪掉的通道数比例。默认为[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]。</p>
</li>
</ul>
<p><strong>返回：</strong></p>
<ul>
<li><strong>sensitivities(dict)</strong> - 存放敏感度信息的dict，其格式为：</li>
</ul>
<table class="codehilitetable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span>1
2
3
4
5
6
7
8
9</pre></div></td><td class="code"><div class="codehilite"><pre><span></span><span class="err">{</span><span class="ss">&quot;weight_0&quot;</span><span class="p">:</span>
   <span class="err">{</span><span class="mi">0</span><span class="p">.</span><span class="mi">1</span><span class="p">:</span> <span class="mi">0</span><span class="p">.</span><span class="mi">22</span><span class="p">,</span>
    <span class="mi">0</span><span class="p">.</span><span class="mi">2</span><span class="p">:</span> <span class="mi">0</span><span class="p">.</span><span class="mi">33</span>
   <span class="err">}</span><span class="p">,</span>
 <span class="ss">&quot;weight_1&quot;</span><span class="p">:</span>
   <span class="err">{</span><span class="mi">0</span><span class="p">.</span><span class="mi">1</span><span class="p">:</span> <span class="mi">0</span><span class="p">.</span><span class="mi">21</span><span class="p">,</span>
    <span class="mi">0</span><span class="p">.</span><span class="mi">2</span><span class="p">:</span> <span class="mi">0</span><span class="p">.</span><span class="mi">4</span>
   <span class="err">}</span>
<span class="err">}</span>
</pre></div>
</td></tr></table>

<p>其中，<code>weight_0</code>是卷积层参数的名称，sensitivities['weight_0']的<code>value</code>为剪裁比例，<code>value</code>为精度损失的比例。</p>
<p><strong>示例：</strong></p>
<p>点击<a href="https://aistudio.baidu.com/aistudio/projectdetail/201401">AIStudio</a>运行以下示例代码。</p>
<table class="codehilitetable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span> 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91</pre></div></td><td class="code"><div class="codehilite"><pre><span></span><span class="kn">import</span> <span class="nn">paddle</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="kn">as</span> <span class="nn">np</span>
<span class="kn">import</span> <span class="nn">paddle.fluid</span> <span class="kn">as</span> <span class="nn">fluid</span>
<span class="kn">from</span> <span class="nn">paddle.fluid.param_attr</span> <span class="kn">import</span> <span class="n">ParamAttr</span>
<span class="kn">from</span> <span class="nn">paddleslim.prune</span> <span class="kn">import</span> <span class="n">sensitivity</span>
<span class="kn">import</span> <span class="nn">paddle.dataset.mnist</span> <span class="kn">as</span> <span class="nn">reader</span>

<span class="k">def</span> <span class="nf">conv_bn_layer</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span>
                  <span class="n">num_filters</span><span class="p">,</span>
                  <span class="n">filter_size</span><span class="p">,</span>
                  <span class="n">name</span><span class="p">,</span>
                  <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
                  <span class="n">groups</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">conv</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">conv2d</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">num_filters</span><span class="o">=</span><span class="n">num_filters</span><span class="p">,</span>
        <span class="n">filter_size</span><span class="o">=</span><span class="n">filter_size</span><span class="p">,</span>
        <span class="n">stride</span><span class="o">=</span><span class="n">stride</span><span class="p">,</span>
        <span class="n">padding</span><span class="o">=</span><span class="p">(</span><span class="n">filter_size</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">//</span> <span class="mi">2</span><span class="p">,</span>
        <span class="n">groups</span><span class="o">=</span><span class="n">groups</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">param_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;_weights&quot;</span><span class="p">),</span>
        <span class="n">bias_attr</span><span class="o">=</span><span class="bp">False</span><span class="p">,</span>
        <span class="n">name</span><span class="o">=</span><span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;_out&quot;</span><span class="p">)</span>
    <span class="n">bn_name</span> <span class="o">=</span> <span class="n">name</span> <span class="o">+</span> <span class="s2">&quot;_bn&quot;</span>
    <span class="k">return</span> <span class="n">fluid</span><span class="o">.</span><span class="n">layers</span><span class="o">.</span><span class="n">batch_norm</span><span class="p">(</span>
        <span class="nb">input</span><span class="o">=</span><span class="n">conv</span><span class="p">,</span>
        <span class="n">act</span><span class="o">=</span><span class="n">act</span><span class="p">,</span>
        <span class="n">name</span><span class="o">=</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_output&#39;</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">name</span><span class="o">=</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_scale&#39;</span><span class="p">),</span>
        <span class="n">bias_attr</span><span class="o">=</span><span class="n">ParamAttr</span><span class="p">(</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_offset&#39;</span><span class="p">),</span>
        <span class="n">moving_mean_name</span><span class="o">=</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_mean&#39;</span><span class="p">,</span>
        <span class="n">moving_variance_name</span><span class="o">=</span><span class="n">bn_name</span> <span class="o">+</span> <span class="s1">&#39;_variance&#39;</span><span class="p">,</span> <span class="p">)</span>

<span class="n">main_program</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">Program</span><span class="p">()</span>
<span class="n">startup_program</span> <span class="o">=</span> <span class="n">fluid</span><span class="o">.</span><span class="n">Program</span><span class="p">()</span>
<span class="c1">#   X       X              O       X              O</span>
<span class="c1"># conv1--&gt;conv2--&gt;sum1--&gt;conv3--&gt;conv4--&gt;sum2--&gt;conv5--&gt;conv6</span>
<span class="c1">#     |            ^ |                    ^</span>
<span class="c1">#     |____________| |____________________|</span>
<span class="c1">#</span>
<span class="c1"># X: prune output channels</span>
<span class="c1"># O: prune input channels</span>
<span class="n">image_shape</span> <span class="o">=</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span><span class="mi">28</span><span class="p">,</span><span class="mi">28</span><span class="p">]</span>
<span class="k">with</span> <span class="n">fluid</span><span class="o">.</span><span class="n">program_guard</span><span class="p">(</span><span class="n">main_program</span><span class="p">,</span> <span class="n">startup_program</span><span class="p">):</span>
    <span class="n">image</span> <span class="o">=</span> <span class="n">fluid</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;image&#39;</span><span class="p">,</span> <span class="kp">shape</span><span class="o">=</span><span class="p">[</span><span class="bp">None</span><span class="p">]</span><span class="o">+</span><span class="n">image_shape</span><span class="p">,</span> <span class="kp">dtype</span><span class="o">=</span><span class="s1">&#39;float32&#39;</span><span class="p">)</span>
    <span class="n">label</span> <span class="o">=</span> <span class="n">fluid</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;label&#39;</span><span class="p">,</span> <span class="kp">shape</span><span class="o">=</span><span class="p">[</span><span class="bp">None</span><span class="p">,</span> <span class="mi">1</span><span class="p">],</span> <span class="kp">dtype</span><span class="o">=</span><span class="s1">&#39;int64&#39;</span><span class="p">)</span>  
    <span class="n">conv1</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv1&quot;</span><span class="p">)</span>
    <span class="n">conv2</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">conv1</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv2&quot;</span><span class="p">)</span>
    <span class="n">sum1</span> <span class="o">=</span> <span class="n">conv1</span> <span class="o">+</span> <span class="n">conv2</span>
    <span class="n">conv3</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">sum1</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv3&quot;</span><span class="p">)</span>
    <span class="n">conv4</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">conv3</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv4&quot;</span><span class="p">)</span>
    <span class="n">sum2</span> <span class="o">=</span> <span class="n">conv4</span> <span class="o">+</span> <span class="n">sum1</span>
    <span class="n">conv5</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">sum2</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv5&quot;</span><span class="p">)</span>
    <span class="n">conv6</span> <span class="o">=</span> <span class="n">conv_bn_layer</span><span class="p">(</span><span class="n">conv5</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="s2">&quot;conv6&quot;</span><span class="p">)</span>
    <span class="n">out</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="n">conv6</span><span class="p">,</span> <span class="kp">size</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">act</span><span class="o">=</span><span class="s2">&quot;softmax&quot;</span><span class="p">)</span>
<span class="c1">#    cost = fluid.layers.cross_entropy(input=out, label=label)</span>
<span class="c1">#    avg_cost = fluid.layers.mean(x=cost)</span>
    <span class="n">acc_top1</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">accuracy</span><span class="p">(</span><span class="nb">input</span><span class="o">=</span><span class="n">out</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="n">label</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="c1">#    acc_top5 = fluid.layers.accuracy(input=out, label=label, k=5)</span>


<span class="kp">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">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="kp">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">startup_program</span><span class="p">)</span>

<span class="n">val_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">reader</span><span class="o">.</span><span class="kp">test</span><span class="p">(),</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">128</span><span class="p">)</span>
<span class="n">val_feeder</span> <span class="o">=</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="p">[</span><span class="n">image</span><span class="p">,</span> <span class="n">label</span><span class="p">],</span> <span class="kp">place</span><span class="p">,</span> <span class="n">program</span><span class="o">=</span><span class="n">main_program</span><span class="p">)</span>

<span class="k">def</span> <span class="nf">eval_func</span><span class="p">(</span><span class="n">program</span><span class="p">):</span>

    <span class="n">acc_top1_ns</span> <span class="o">=</span> <span class="p">[]</span>
    <span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">val_reader</span><span class="p">():</span>
        <span class="n">acc_top1_n</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">program</span><span class="p">,</span>
                             <span class="n">feed</span><span class="o">=</span><span class="n">val_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">acc_top1</span><span class="o">.</span><span class="n">name</span><span class="p">])</span>
        <span class="n">acc_top1_ns</span><span class="o">.</span><span class="kp">append</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="kp">mean</span><span class="p">(</span><span class="n">acc_top1_n</span><span class="p">))</span>
    <span class="k">return</span> <span class="n">np</span><span class="o">.</span><span class="kp">mean</span><span class="p">(</span><span class="n">acc_top1_ns</span><span class="p">)</span>
<span class="n">param_names</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="n">main_program</span><span class="o">.</span><span class="n">global_block</span><span class="p">()</span><span class="o">.</span><span class="n">all_parameters</span><span class="p">():</span>
    <span class="k">if</span> <span class="s2">&quot;weights&quot;</span> <span class="ow">in</span> <span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">:</span>
        <span class="n">param_names</span><span class="o">.</span><span class="kp">append</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">name</span><span class="p">)</span>
<span class="n">sensitivities</span> <span class="o">=</span> <span class="n">sensitivity</span><span class="p">(</span><span class="n">main_program</span><span class="p">,</span>
                            <span class="kp">place</span><span class="p">,</span>
                            <span class="n">param_names</span><span class="p">,</span>
                            <span class="n">eval_func</span><span class="p">,</span>
                            <span class="n">sensitivities_file</span><span class="o">=</span><span class="s2">&quot;./sensitive.data&quot;</span><span class="p">,</span>
                            <span class="n">pruned_ratios</span><span class="o">=</span><span class="p">[</span><span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.2</span><span class="p">,</span> <span class="mf">0.3</span><span class="p">])</span>
<span class="k">print</span><span class="p">(</span><span class="n">sensitivities</span><span class="p">)</span>
</pre></div>
</td></tr></table>

<h2 id="merge_sensitive">merge_sensitive<a class="headerlink" href="#merge_sensitive" title="Permanent link">#</a></h2>
<dl>
<dt>paddleslim.prune.merge_sensitive(sensitivities)<a href="https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/sensitive.py#L161">[源代码]</a></dt>
<dd>
<p>合并多个敏感度信息。</p>
</dd>
</dl>
<p>参数：</p>
<ul>
<li><strong>sensitivities(list<dict> | list<str>)</strong> - 待合并的敏感度信息，可以是字典的列表，或者是存放敏感度信息的文件的路径列表。</li>
</ul>
<p>返回：</p>
<ul>
<li><strong>sensitivities(dict)</strong> - 合并后的敏感度信息。其格式为：</li>
</ul>
<table class="codehilitetable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span>1
2
3
4
5
6
7
8
9</pre></div></td><td class="code"><div class="codehilite"><pre><span></span><span class="err">{</span><span class="ss">&quot;weight_0&quot;</span><span class="p">:</span>
   <span class="err">{</span><span class="mi">0</span><span class="p">.</span><span class="mi">1</span><span class="p">:</span> <span class="mi">0</span><span class="p">.</span><span class="mi">22</span><span class="p">,</span>
    <span class="mi">0</span><span class="p">.</span><span class="mi">2</span><span class="p">:</span> <span class="mi">0</span><span class="p">.</span><span class="mi">33</span>
   <span class="err">}</span><span class="p">,</span>
 <span class="ss">&quot;weight_1&quot;</span><span class="p">:</span>
   <span class="err">{</span><span class="mi">0</span><span class="p">.</span><span class="mi">1</span><span class="p">:</span> <span class="mi">0</span><span class="p">.</span><span class="mi">21</span><span class="p">,</span>
    <span class="mi">0</span><span class="p">.</span><span class="mi">2</span><span class="p">:</span> <span class="mi">0</span><span class="p">.</span><span class="mi">4</span>
   <span class="err">}</span>
<span class="err">}</span>
</pre></div>
</td></tr></table>

<p>其中，<code>weight_0</code>是卷积层参数的名称，sensitivities['weight_0']的<code>value</code>为剪裁比例，<code>value</code>为精度损失的比例。</p>
<p>示例：</p>
<h2 id="load_sensitivities">load_sensitivities<a class="headerlink" href="#load_sensitivities" title="Permanent link">#</a></h2>
<dl>
<dt>paddleslim.prune.load_sensitivities(sensitivities_file)<a href="https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/sensitive.py#L184">[源代码]</a></dt>
<dd>
<p>从文件中加载敏感度信息。</p>
</dd>
</dl>
<p>参数：</p>
<ul>
<li><strong>sensitivities_file(str)</strong> - 存放敏感度信息的本地文件.</li>
</ul>
<p>返回：</p>
<ul>
<li><strong>sensitivities(dict)</strong> - 敏感度信息。</li>
</ul>
<p>示例：</p>
<h2 id="get_ratios_by_loss">get_ratios_by_loss<a class="headerlink" href="#get_ratios_by_loss" title="Permanent link">#</a></h2>
<dl>
<dt>paddleslim.prune.get_ratios_by_loss(sensitivities, loss)<a href="https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/sensitive.py#L206">[源代码]</a></dt>
<dd>
<p>根据敏感度和精度损失阈值计算出一组剪切率。对于参数<code>w</code>, 其剪裁率为使精度损失低于<code>loss</code>的最大剪裁率。</p>
</dd>
</dl>
<p>参数：</p>
<ul>
<li>
<p><strong>sensitivities(dict)</strong> - 敏感度信息。</p>
</li>
<li>
<p><strong>loss</strong> - 精度损失阈值。</p>
</li>
</ul>
<p>返回：</p>
<ul>
<li><strong>ratios(dict)</strong> - 一组剪切率。<code>key</code>是待剪裁参数的名称。<code>value</code>是对应参数的剪裁率。</li>
</ul>
              
            </div>
          </div>
          <footer>
  
    <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
      
        <a href="../analysis_api/" class="btn btn-neutral float-right" title="模型分析">Next <span class="icon icon-circle-arrow-right"></span></a>
      
      
        <a href="../quantization_api/" class="btn btn-neutral" title="量化"><span class="icon icon-circle-arrow-left"></span> Previous</a>
      
    </div>
  

  <hr/>

  <div role="contentinfo">
    <!-- Copyright etc -->
    
  </div>

  Built with <a href="http://www.mkdocs.org">MkDocs</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>

  <div class="rst-versions" role="note" style="cursor: pointer">
    <span class="rst-current-version" data-toggle="rst-current-version">
      
          <a href="https://github.com/PaddlePaddle/PaddleSlim/" class="fa fa-github" style="float: left; color: #fcfcfc"> GitHub</a>
      
      
        <span><a href="../quantization_api/" style="color: #fcfcfc;">&laquo; Previous</a></span>
      
      
        <span style="margin-left: 15px"><a href="../analysis_api/" style="color: #fcfcfc">Next &raquo;</a></span>
      
    </span>
</div>
    <script>var base_url = '../..';</script>
    <script src="../../js/theme.js" defer></script>
      <script src="../../mathjax-config.js" defer></script>
      <script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML" defer></script>
      <script src="../../search/main.js" defer></script>

</body>
</html>