422 lines
48 KiB
HTML
422 lines
48 KiB
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>torchreid.models.mlfn — torchreid 0.7.7 documentation</title>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script>
|
|
|
|
|
|
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></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/language_data.js"></script>
|
|
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
|
|
|
|
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
|
|
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
|
|
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
|
|
<link rel="index" title="Index" href="../../../genindex.html" />
|
|
<link rel="search" title="Search" href="../../../search.html" />
|
|
</head>
|
|
|
|
<body class="wy-body-for-nav">
|
|
|
|
|
|
<div class="wy-grid-for-nav">
|
|
|
|
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
|
|
<div class="wy-side-scroll">
|
|
<div class="wy-side-nav-search" >
|
|
|
|
|
|
|
|
<a href="../../../index.html" class="icon icon-home"> torchreid
|
|
|
|
|
|
|
|
</a>
|
|
|
|
|
|
|
|
|
|
<div class="version">
|
|
0.7.7
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<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 class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../user_guide.html">How-to</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../datasets.html">Datasets</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../evaluation.html">Evaluation</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Package Reference</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../pkg/data.html">torchreid.data</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../pkg/engine.html">torchreid.engine</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../pkg/losses.html">torchreid.losses</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../pkg/metrics.html">torchreid.metrics</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../pkg/models.html">torchreid.models</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../pkg/optim.html">torchreid.optim</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../pkg/utils.html">torchreid.utils</a></li>
|
|
</ul>
|
|
<p class="caption"><span class="caption-text">Resources</span></p>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../AWESOME_REID.html">Awesome-ReID</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../MODEL_ZOO.html">Model Zoo</a></li>
|
|
</ul>
|
|
|
|
|
|
|
|
</div>
|
|
</div>
|
|
</nav>
|
|
|
|
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
|
|
|
|
|
|
<nav class="wy-nav-top" aria-label="top navigation">
|
|
|
|
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
|
|
<a href="../../../index.html">torchreid</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="../../../index.html">Docs</a> »</li>
|
|
|
|
<li><a href="../../index.html">Module code</a> »</li>
|
|
|
|
<li>torchreid.models.mlfn</li>
|
|
|
|
|
|
<li class="wy-breadcrumbs-aside">
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
|
|
<hr/>
|
|
</div>
|
|
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
|
<div itemprop="articleBody">
|
|
|
|
<h1>Source code for torchreid.models.mlfn</h1><div class="highlight"><pre>
|
|
<span></span><span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span>
|
|
<span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">division</span>
|
|
|
|
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'mlfn'</span><span class="p">]</span>
|
|
|
|
<span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="kn">from</span> <span class="nn">torch</span> <span class="k">import</span> <span class="n">nn</span>
|
|
<span class="kn">from</span> <span class="nn">torch.nn</span> <span class="k">import</span> <span class="n">functional</span> <span class="k">as</span> <span class="n">F</span>
|
|
<span class="kn">import</span> <span class="nn">torchvision</span>
|
|
<span class="kn">import</span> <span class="nn">torch.utils.model_zoo</span> <span class="k">as</span> <span class="nn">model_zoo</span>
|
|
|
|
|
|
<span class="n">model_urls</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="c1"># training epoch = 5, top1 = 51.6</span>
|
|
<span class="s1">'imagenet'</span><span class="p">:</span> <span class="s1">'http://www.eecs.qmul.ac.uk/~kz303/deep-person-reid/model-zoo/imagenet-pretrained/mlfn-9cb5a267.pth.tar'</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
|
|
<span class="k">class</span> <span class="nc">MLFNBlock</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span>
|
|
|
|
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">in_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">stride</span><span class="p">,</span> <span class="n">fsm_channels</span><span class="p">,</span> <span class="n">groups</span><span class="o">=</span><span class="mi">32</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">(</span><span class="n">MLFNBlock</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">groups</span> <span class="o">=</span> <span class="n">groups</span>
|
|
<span class="n">mid_channels</span> <span class="o">=</span> <span class="n">out_channels</span> <span class="o">//</span> <span class="mi">2</span>
|
|
|
|
<span class="c1"># Factor Modules</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fm_conv1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">mid_channels</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fm_bn1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">mid_channels</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fm_conv2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">mid_channels</span><span class="p">,</span> <span class="n">mid_channels</span><span class="p">,</span> <span class="mi">3</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="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">groups</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fm_bn2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">mid_channels</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fm_conv3</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">mid_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fm_bn3</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">)</span>
|
|
|
|
<span class="c1"># Factor Selection Module</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fsm</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">AdaptiveAvgPool2d</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">fsm_channels</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="mi">1</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">fsm_channels</span><span class="p">[</span><span class="mi">0</span><span class="p">]),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(</span><span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">fsm_channels</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">fsm_channels</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="mi">1</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">fsm_channels</span><span class="p">[</span><span class="mi">1</span><span class="p">]),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(</span><span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">fsm_channels</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">,</span> <span class="mi">1</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">Sigmoid</span><span class="p">(),</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">downsample</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="k">if</span> <span class="n">in_channels</span> <span class="o">!=</span> <span class="n">out_channels</span> <span class="ow">or</span> <span class="n">stride</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">downsample</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="mi">1</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">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">),</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
|
|
<span class="n">residual</span> <span class="o">=</span> <span class="n">x</span>
|
|
<span class="n">s</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fsm</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
|
|
<span class="c1"># reduce dimension</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fm_conv1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fm_bn1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
|
|
<span class="c1"># group convolution</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fm_conv2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fm_bn2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
|
|
<span class="c1"># factor selection</span>
|
|
<span class="n">b</span><span class="p">,</span> <span class="n">c</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">size</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span> <span class="n">x</span><span class="o">.</span><span class="n">size</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">n</span> <span class="o">=</span> <span class="n">c</span> <span class="o">//</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span>
|
|
<span class="n">ss</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">repeat</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">n</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> <span class="c1"># from (b, g, 1, 1) to (b, g*n=c, 1, 1)</span>
|
|
<span class="n">ss</span> <span class="o">=</span> <span class="n">ss</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">b</span><span class="p">,</span> <span class="n">n</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">ss</span> <span class="o">=</span> <span class="n">ss</span><span class="o">.</span><span class="n">permute</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">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">4</span><span class="p">)</span><span class="o">.</span><span class="n">contiguous</span><span class="p">()</span>
|
|
<span class="n">ss</span> <span class="o">=</span> <span class="n">ss</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="n">ss</span> <span class="o">*</span> <span class="n">x</span>
|
|
|
|
<span class="c1"># recover dimension</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fm_conv3</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fm_bn3</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">downsample</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">residual</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">downsample</span><span class="p">(</span><span class="n">residual</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="n">residual</span> <span class="o">+</span> <span class="n">x</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">),</span> <span class="n">s</span>
|
|
|
|
|
|
<div class="viewcode-block" id="MLFN"><a class="viewcode-back" href="../../../pkg/models.html#torchreid.models.mlfn.MLFN">[docs]</a><span class="k">class</span> <span class="nc">MLFN</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span>
|
|
<span class="sd">"""Multi-Level Factorisation Net.</span>
|
|
|
|
<span class="sd"> Reference:</span>
|
|
<span class="sd"> Chang et al. Multi-Level Factorisation Net for</span>
|
|
<span class="sd"> Person Re-Identification. CVPR 2018.</span>
|
|
|
|
<span class="sd"> Public keys:</span>
|
|
<span class="sd"> - ``mlfn``: MLFN (Multi-Level Factorisation Net).</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">num_classes</span><span class="p">,</span> <span class="n">loss</span><span class="o">=</span><span class="s1">'softmax'</span><span class="p">,</span> <span class="n">groups</span><span class="o">=</span><span class="mi">32</span><span class="p">,</span> <span class="n">channels</span><span class="o">=</span><span class="p">[</span><span class="mi">64</span><span class="p">,</span> <span class="mi">256</span><span class="p">,</span> <span class="mi">512</span><span class="p">,</span> <span class="mi">1024</span><span class="p">,</span> <span class="mi">2048</span><span class="p">],</span> <span class="n">embed_dim</span><span class="o">=</span><span class="mi">1024</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
|
<span class="nb">super</span><span class="p">(</span><span class="n">MLFN</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">loss</span> <span class="o">=</span> <span class="n">loss</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">groups</span> <span class="o">=</span> <span class="n">groups</span>
|
|
|
|
<span class="c1"># first convolutional layer</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">conv1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="n">channels</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="mi">7</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">3</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">bn1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">maxpool</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2d</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
|
|
|
|
<span class="c1"># main body</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">feature</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span>
|
|
<span class="c1"># layer 1-3</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">128</span><span class="p">,</span> <span class="mi">64</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">128</span><span class="p">,</span> <span class="mi">64</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">128</span><span class="p">,</span> <span class="mi">64</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="c1"># layer 4-7</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="mi">2</span><span class="p">,</span> <span class="p">[</span><span class="mi">256</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">256</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">256</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">256</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="c1"># layer 8-13</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="mi">2</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="c1"># layer 14-16</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">4</span><span class="p">],</span> <span class="mi">2</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">4</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">4</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="n">MLFNBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">4</span><span class="p">],</span> <span class="n">channels</span><span class="p">[</span><span class="mi">4</span><span class="p">],</span> <span class="mi">1</span><span class="p">,</span> <span class="p">[</span><span class="mi">512</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="bp">self</span><span class="o">.</span><span class="n">groups</span><span class="p">),</span>
|
|
<span class="p">])</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">global_avgpool</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">AdaptiveAvgPool2d</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
|
|
|
|
<span class="c1"># projection functions</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fc_x</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">channels</span><span class="p">[</span><span class="mi">4</span><span class="p">],</span> <span class="n">embed_dim</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">embed_dim</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(</span><span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">),</span>
|
|
<span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">fc_s</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">groups</span> <span class="o">*</span> <span class="mi">16</span><span class="p">,</span> <span class="n">embed_dim</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">embed_dim</span><span class="p">),</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(</span><span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">),</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">classifier</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">embed_dim</span><span class="p">,</span> <span class="n">num_classes</span><span class="p">)</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">init_params</span><span class="p">()</span>
|
|
|
|
<span class="k">def</span> <span class="nf">init_params</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">modules</span><span class="p">():</span>
|
|
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">m</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">):</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">kaiming_normal_</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">weight</span><span class="p">,</span> <span class="n">mode</span><span class="o">=</span><span class="s1">'fan_out'</span><span class="p">,</span> <span class="n">nonlinearity</span><span class="o">=</span><span class="s1">'relu'</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">m</span><span class="o">.</span><span class="n">bias</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">constant_</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">bias</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
|
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">m</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">):</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">constant_</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">weight</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">constant_</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">bias</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
|
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">m</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">):</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">normal_</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">weight</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mf">0.01</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">m</span><span class="o">.</span><span class="n">bias</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">nn</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">constant_</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">bias</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
|
|
|
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">maxpool</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
|
|
<span class="n">s_hat</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="k">for</span> <span class="n">block</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature</span><span class="p">:</span>
|
|
<span class="n">x</span><span class="p">,</span> <span class="n">s</span> <span class="o">=</span> <span class="n">block</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">s_hat</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">s</span><span class="p">)</span>
|
|
<span class="n">s_hat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">(</span><span class="n">s_hat</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">global_avgpool</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc_x</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="n">s_hat</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc_s</span><span class="p">(</span><span class="n">s_hat</span><span class="p">)</span>
|
|
|
|
<span class="n">v</span> <span class="o">=</span> <span class="p">(</span><span class="n">x</span> <span class="o">+</span> <span class="n">s_hat</span><span class="p">)</span> <span class="o">*</span> <span class="mf">0.5</span>
|
|
<span class="n">v</span> <span class="o">=</span> <span class="n">v</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">v</span><span class="o">.</span><span class="n">size</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">training</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">v</span>
|
|
|
|
<span class="n">y</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">classifier</span><span class="p">(</span><span class="n">v</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss</span> <span class="o">==</span> <span class="s1">'softmax'</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">y</span>
|
|
<span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss</span> <span class="o">==</span> <span class="s1">'triplet'</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">y</span><span class="p">,</span> <span class="n">v</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="k">raise</span> <span class="ne">KeyError</span><span class="p">(</span><span class="s1">'Unsupported loss: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">loss</span><span class="p">))</span></div>
|
|
|
|
|
|
<span class="k">def</span> <span class="nf">init_pretrained_weights</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">model_url</span><span class="p">):</span>
|
|
<span class="sd">"""Initializes model with pretrained weights.</span>
|
|
<span class="sd"> </span>
|
|
<span class="sd"> Layers that don't match with pretrained layers in name or size are kept unchanged.</span>
|
|
<span class="sd"> """</span>
|
|
<span class="n">pretrain_dict</span> <span class="o">=</span> <span class="n">model_zoo</span><span class="o">.</span><span class="n">load_url</span><span class="p">(</span><span class="n">model_url</span><span class="p">)</span>
|
|
<span class="n">model_dict</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">state_dict</span><span class="p">()</span>
|
|
<span class="n">pretrain_dict</span> <span class="o">=</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">pretrain_dict</span><span class="o">.</span><span class="n">items</span><span class="p">()</span> <span class="k">if</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">model_dict</span> <span class="ow">and</span> <span class="n">model_dict</span><span class="p">[</span><span class="n">k</span><span class="p">]</span><span class="o">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="n">v</span><span class="o">.</span><span class="n">size</span><span class="p">()}</span>
|
|
<span class="n">model_dict</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">pretrain_dict</span><span class="p">)</span>
|
|
<span class="n">model</span><span class="o">.</span><span class="n">load_state_dict</span><span class="p">(</span><span class="n">model_dict</span><span class="p">)</span>
|
|
|
|
|
|
<span class="k">def</span> <span class="nf">mlfn</span><span class="p">(</span><span class="n">num_classes</span><span class="p">,</span> <span class="n">loss</span><span class="o">=</span><span class="s1">'softmax'</span><span class="p">,</span> <span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
|
<span class="n">model</span> <span class="o">=</span> <span class="n">MLFN</span><span class="p">(</span><span class="n">num_classes</span><span class="p">,</span> <span class="n">loss</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">pretrained</span><span class="p">:</span>
|
|
<span class="n">init_pretrained_weights</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">model_urls</span><span class="p">[</span><span class="s1">'imagenet'</span><span class="p">])</span>
|
|
<span class="k">return</span> <span class="n">model</span>
|
|
</pre></div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
<footer>
|
|
|
|
|
|
<hr/>
|
|
|
|
<div role="contentinfo">
|
|
<p>
|
|
© Copyright 2019, Kaiyang Zhou
|
|
|
|
</p>
|
|
</div>
|
|
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/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">
|
|
jQuery(function () {
|
|
SphinxRtdTheme.Navigation.enable(true);
|
|
});
|
|
</script>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</body>
|
|
</html> |