mirrors/deep-person-reid
1
0
Fork 0
mirror of https://github.com/KaiyangZhou/deep-person-reid.git synced 2025-06-03 14:53:23 +08:00
Code Issues Projects Releases Wiki Activity
deep-person-reid/_modules/torchreid/models/osnet.html

644 lines
86 KiB
HTML
Raw Normal View History

update docs
2019-07-03 13:46:28 +01:00
<!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">
1.0.1
2019-08-29 17:10:16 +01:00
<title>torchreid.models.osnet &mdash; torchreid 1.0.1 documentation</title>
update docs
2019-07-03 13:46:28 +01:00
<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">
1.0.1
2019-08-29 17:10:16 +01:00
1.0.1
update docs
2019-07-03 13:46:28 +01:00
</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> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>torchreid.models.osnet</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.osnet</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">&#39;osnet_x1_0&#39;</span><span class="p">,</span> <span class="s1">&#39;osnet_x0_75&#39;</span><span class="p">,</span> <span class="s1">&#39;osnet_x0_5&#39;</span><span class="p">,</span> <span class="s1">&#39;osnet_x0_25&#39;</span><span class="p">,</span> <span class="s1">&#39;osnet_ibn_x1_0&#39;</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>
1.0.0
2019-08-26 13:27:00 +01:00
<span class="n">pretrained_urls</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;osnet_x1_0&#39;</span><span class="p">:</span> <span class="s1">&#39;https://drive.google.com/uc?id=1LaG1EJpHrxdAxKnSCJ_i0u-nbxSAeiFY&#39;</span><span class="p">,</span>
<span class="s1">&#39;osnet_x0_75&#39;</span><span class="p">:</span> <span class="s1">&#39;https://drive.google.com/uc?id=1uwA9fElHOk3ZogwbeY5GkLI6QPTX70Hq&#39;</span><span class="p">,</span>
<span class="s1">&#39;osnet_x0_5&#39;</span><span class="p">:</span> <span class="s1">&#39;https://drive.google.com/uc?id=16DGLbZukvVYgINws8u8deSaOqjybZ83i&#39;</span><span class="p">,</span>
<span class="s1">&#39;osnet_x0_25&#39;</span><span class="p">:</span> <span class="s1">&#39;https://drive.google.com/uc?id=1rb8UN5ZzPKRc_xvtHlyDh-cSz88YX9hs&#39;</span><span class="p">,</span>
<span class="s1">&#39;osnet_ibn_x1_0&#39;</span><span class="p">:</span> <span class="s1">&#39;https://drive.google.com/uc?id=1sr90V6irlYYDd4_4ISU2iruoRG8J__6l&#39;</span>
<span class="p">}</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="c1">##########</span>
<span class="c1"># Basic layers</span>
<span class="c1">##########</span>
<span class="k">class</span> <span class="nc">ConvLayer</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">&quot;&quot;&quot;Convolution layer (conv + bn + relu).&quot;&quot;&quot;</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">kernel_size</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">padding</span><span class="o">=</span><span class="mi">0</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">IN</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">ConvLayer</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">conv</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">out_channels</span><span class="p">,</span> <span class="n">kernel_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="n">padding</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="n">groups</span><span class="p">)</span>
<span class="k">if</span> <span class="n">IN</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bn</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">InstanceNorm2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">,</span> <span class="n">affine</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bn</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="bp">self</span><span class="o">.</span><span class="n">relu</span> <span class="o">=</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="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">conv</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">bn</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">relu</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<span class="k">class</span> <span class="nc">Conv1x1</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">&quot;&quot;&quot;1x1 convolution + bn + relu.&quot;&quot;&quot;</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="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="nb">super</span><span class="p">(</span><span class="n">Conv1x1</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">conv</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">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">padding</span><span class="o">=</span><span class="mi">0</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="n">groups</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bn</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="bp">self</span><span class="o">.</span><span class="n">relu</span> <span class="o">=</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="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">conv</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">bn</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">relu</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<span class="k">class</span> <span class="nc">Conv1x1Linear</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">&quot;&quot;&quot;1x1 convolution + bn (w/o non-linearity).&quot;&quot;&quot;</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="o">=</span><span class="mi">1</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">Conv1x1Linear</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">conv</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">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">padding</span><span class="o">=</span><span class="mi">0</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">bn</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="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">conv</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">bn</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<span class="k">class</span> <span class="nc">Conv3x3</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">&quot;&quot;&quot;3x3 convolution + bn + relu.&quot;&quot;&quot;</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="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="nb">super</span><span class="p">(</span><span class="n">Conv3x3</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">conv</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">out_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="n">groups</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bn</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="bp">self</span><span class="o">.</span><span class="n">relu</span> <span class="o">=</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="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">conv</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">bn</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">relu</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<span class="k">class</span> <span class="nc">LightConv3x3</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">&quot;&quot;&quot;Lightweight 3x3 convolution.</span>
<span class="sd"> 1x1 (linear) + dw 3x3 (nonlinear).</span>
<span class="sd"> &quot;&quot;&quot;</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="nb">super</span><span class="p">(</span><span class="n">LightConv3x3</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">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">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="mi">1</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</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">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">out_channels</span><span class="p">,</span> <span class="n">out_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="mi">1</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="n">out_channels</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bn</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="bp">self</span><span class="o">.</span><span class="n">relu</span> <span class="o">=</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="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">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">bn</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">relu</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
<span class="c1">##########</span>
<span class="c1"># Building blocks for omni-scale feature learning</span>
<span class="c1">##########</span>
<span class="k">class</span> <span class="nc">ChannelGate</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">&quot;&quot;&quot;A mini-network that generates channel-wise gates conditioned on input tensor.&quot;&quot;&quot;</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">num_gates</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">return_gates</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">gate_activation</span><span class="o">=</span><span class="s1">&#39;sigmoid&#39;</span><span class="p">,</span> <span class="n">reduction</span><span class="o">=</span><span class="mi">16</span><span class="p">,</span> <span class="n">layer_norm</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">ChannelGate</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="k">if</span> <span class="n">num_gates</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">num_gates</span> <span class="o">=</span> <span class="n">in_channels</span>
<span class="bp">self</span><span class="o">.</span><span class="n">return_gates</span> <span class="o">=</span> <span class="n">return_gates</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="bp">self</span><span class="o">.</span><span class="n">fc1</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">in_channels</span><span class="o">//</span><span class="n">reduction</span><span class="p">,</span> <span class="n">kernel_size</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">True</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">norm1</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">layer_norm</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">norm1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">((</span><span class="n">in_channels</span><span class="o">//</span><span class="n">reduction</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="bp">self</span><span class="o">.</span><span class="n">relu</span> <span class="o">=</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="bp">self</span><span class="o">.</span><span class="n">fc2</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="o">//</span><span class="n">reduction</span><span class="p">,</span> <span class="n">num_gates</span><span class="p">,</span> <span class="n">kernel_size</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">True</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="k">if</span> <span class="n">gate_activation</span> <span class="o">==</span> <span class="s1">&#39;sigmoid&#39;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gate_activation</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sigmoid</span><span class="p">()</span>
<span class="k">elif</span> <span class="n">gate_activation</span> <span class="o">==</span> <span class="s1">&#39;relu&#39;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gate_activation</span> <span class="o">=</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="k">elif</span> <span class="n">gate_activation</span> <span class="o">==</span> <span class="s1">&#39;linear&#39;</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gate_activation</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">&quot;Unknown gate activation: </span><span class="si">{}</span><span class="s2">&quot;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">gate_activation</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="nb">input</span> <span class="o">=</span> <span class="n">x</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">fc1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">norm1</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</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">norm1</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">relu</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">fc2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">gate_activation</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</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">gate_activation</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">return_gates</span><span class="p">:</span>
<span class="k">return</span> <span class="n">x</span>
<span class="k">return</span> <span class="nb">input</span> <span class="o">*</span> <span class="n">x</span>
<span class="k">class</span> <span class="nc">OSBlock</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">&quot;&quot;&quot;Omni-scale feature learning block.&quot;&quot;&quot;</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">IN</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">bottleneck_reduction</span><span class="o">=</span><span class="mi">4</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">OSBlock</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="n">mid_channels</span> <span class="o">=</span> <span class="n">out_channels</span> <span class="o">//</span> <span class="n">bottleneck_reduction</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conv1</span> <span class="o">=</span> <span class="n">Conv1x1</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="bp">self</span><span class="o">.</span><span class="n">conv2a</span> <span class="o">=</span> <span class="n">LightConv3x3</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="bp">self</span><span class="o">.</span><span class="n">conv2b</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">LightConv3x3</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="n">LightConv3x3</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="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conv2c</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">LightConv3x3</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="n">LightConv3x3</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="n">LightConv3x3</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="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conv2d</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">LightConv3x3</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="n">LightConv3x3</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="n">LightConv3x3</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="n">LightConv3x3</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="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gate</span> <span class="o">=</span> <span class="n">ChannelGate</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">conv3</span> <span class="o">=</span> <span class="n">Conv1x1Linear</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="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="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">downsample</span> <span class="o">=</span> <span class="n">Conv1x1Linear</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="bp">self</span><span class="o">.</span><span class="n">IN</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">if</span> <span class="n">IN</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">IN</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">InstanceNorm2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">,</span> <span class="n">affine</span><span class="o">=</span><span class="kc">True</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>
update docs
2019-08-21 23:03:13 +01:00
<span class="n">identity</span> <span class="o">=</span> <span class="n">x</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="n">x1</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">x2a</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2a</span><span class="p">(</span><span class="n">x1</span><span class="p">)</span>
<span class="n">x2b</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2b</span><span class="p">(</span><span class="n">x1</span><span class="p">)</span>
<span class="n">x2c</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2c</span><span class="p">(</span><span class="n">x1</span><span class="p">)</span>
<span class="n">x2d</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2d</span><span class="p">(</span><span class="n">x1</span><span class="p">)</span>
<span class="n">x2</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gate</span><span class="p">(</span><span class="n">x2a</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">gate</span><span class="p">(</span><span class="n">x2b</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">gate</span><span class="p">(</span><span class="n">x2c</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">gate</span><span class="p">(</span><span class="n">x2d</span><span class="p">)</span>
<span class="n">x3</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv3</span><span class="p">(</span><span class="n">x2</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>
update docs
2019-08-21 23:03:13 +01:00
<span class="n">identity</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">identity</span><span class="p">)</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">x3</span> <span class="o">+</span> <span class="n">identity</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">IN</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">out</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">IN</span><span class="p">(</span><span class="n">out</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">out</span><span class="p">)</span>
<span class="c1">##########</span>
<span class="c1"># Network architecture</span>
<span class="c1">##########</span>
<div class="viewcode-block" id="OSNet"><a class="viewcode-back" href="../../../pkg/models.html#torchreid.models.osnet.OSNet">[docs]</a><span class="k">class</span> <span class="nc">OSNet</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">&quot;&quot;&quot;Omni-Scale Network.</span>
<span class="sd"> </span>
<span class="sd"> Reference:</span>
0.9.0
2019-08-03 23:16:36 +01:00
<span class="sd"> - Zhou et al. Omni-Scale Feature Learning for Person Re-Identification. ICCV, 2019.</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="sd"> &quot;&quot;&quot;</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">blocks</span><span class="p">,</span> <span class="n">layers</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">feature_dim</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="n">IN</span><span class="o">=</span><span class="kc">False</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">OSNet</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="n">num_blocks</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">blocks</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">num_blocks</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="n">layers</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">num_blocks</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="n">channels</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</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="c1"># convolutional backbone</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conv1</span> <span class="o">=</span> <span class="n">ConvLayer</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="n">IN</span><span class="o">=</span><span class="n">IN</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="bp">self</span><span class="o">.</span><span class="n">conv2</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_make_layer</span><span class="p">(</span><span class="n">blocks</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">layers</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">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="n">reduce_spatial_size</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">IN</span><span class="o">=</span><span class="n">IN</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conv3</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_make_layer</span><span class="p">(</span><span class="n">blocks</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">layers</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="n">channels</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">reduce_spatial_size</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">conv4</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_make_layer</span><span class="p">(</span><span class="n">blocks</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">layers</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="n">channels</span><span class="p">[</span><span class="mi">3</span><span class="p">],</span> <span class="n">reduce_spatial_size</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">conv5</span> <span class="o">=</span> <span class="n">Conv1x1</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="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"># fully connected layer</span>
<span class="bp">self</span><span class="o">.</span><span class="n">fc</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_construct_fc_layer</span><span class="p">(</span><span class="n">feature_dim</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">dropout_p</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
<span class="c1"># identity classification layer</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="bp">self</span><span class="o">.</span><span class="n">feature_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">_make_layer</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">block</span><span class="p">,</span> <span class="n">layer</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">reduce_spatial_size</span><span class="p">,</span> <span class="n">IN</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
<span class="n">layers</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">layers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">block</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">IN</span><span class="o">=</span><span class="n">IN</span><span class="p">))</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">layer</span><span class="p">):</span>
<span class="n">layers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">block</span><span class="p">(</span><span class="n">out_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">IN</span><span class="o">=</span><span class="n">IN</span><span class="p">))</span>
<span class="k">if</span> <span class="n">reduce_spatial_size</span><span class="p">:</span>
<span class="n">layers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
<span class="n">Conv1x1</span><span class="p">(</span><span class="n">out_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">),</span>
<span class="n">nn</span><span class="o">.</span><span class="n">AvgPool2d</span><span class="p">(</span><span class="mi">2</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="p">)</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span><span class="o">*</span><span class="n">layers</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_construct_fc_layer</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fc_dims</span><span class="p">,</span> <span class="n">input_dim</span><span class="p">,</span> <span class="n">dropout_p</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="k">if</span> <span class="n">fc_dims</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">fc_dims</span><span class="o">&lt;</span><span class="mi">0</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">feature_dim</span> <span class="o">=</span> <span class="n">input_dim</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">fc_dims</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
<span class="n">fc_dims</span> <span class="o">=</span> <span class="p">[</span><span class="n">fc_dims</span><span class="p">]</span>
<span class="n">layers</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">dim</span> <span class="ow">in</span> <span class="n">fc_dims</span><span class="p">:</span>
<span class="n">layers</span><span class="o">.</span><span class="n">append</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">input_dim</span><span class="p">,</span> <span class="n">dim</span><span class="p">))</span>
<span class="n">layers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm1d</span><span class="p">(</span><span class="n">dim</span><span class="p">))</span>
<span class="n">layers</span><span class="o">.</span><span class="n">append</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="k">if</span> <span class="n">dropout_p</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">layers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Dropout</span><span class="p">(</span><span class="n">p</span><span class="o">=</span><span class="n">dropout_p</span><span class="p">))</span>
<span class="n">input_dim</span> <span class="o">=</span> <span class="n">dim</span>
<span class="bp">self</span><span class="o">.</span><span class="n">feature_dim</span> <span class="o">=</span> <span class="n">fc_dims</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="k">return</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span><span class="o">*</span><span class="n">layers</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">&#39;fan_out&#39;</span><span class="p">,</span> <span class="n">nonlinearity</span><span class="o">=</span><span class="s1">&#39;relu&#39;</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">BatchNorm1d</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">featuremaps</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">maxpool</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">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">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">conv4</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">conv5</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="k">return</span> <span class="n">x</span>
update output_featuremaps_only to return_featuremaps
2019-08-05 14:04:14 +01:00
<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">return_featuremaps</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">featuremaps</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
update output_featuremaps_only to return_featuremaps
2019-08-05 14:04:14 +01:00
<span class="k">if</span> <span class="n">return_featuremaps</span><span class="p">:</span>
0.9.0
2019-08-03 23:16:36 +01:00
<span class="k">return</span> <span class="n">x</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="n">v</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">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="bp">self</span><span class="o">.</span><span class="n">fc</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">v</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc</span><span class="p">(</span><span class="n">v</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">&#39;softmax&#39;</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">&#39;triplet&#39;</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="s2">&quot;Unsupported loss: </span><span class="si">{}</span><span class="s2">&quot;</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>
1.0.0
2019-08-26 13:27:00 +01:00
<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">key</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Initializes model with pretrained weights.</span>
<span class="sd"> </span>
<span class="sd"> Layers that don&#39;t match with pretrained layers in name or size are kept unchanged.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">errno</span>
<span class="kn">import</span> <span class="nn">gdown</span>
<span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">OrderedDict</span>
<span class="k">def</span> <span class="nf">_get_torch_home</span><span class="p">():</span>
<span class="n">ENV_TORCH_HOME</span> <span class="o">=</span> <span class="s1">&#39;TORCH_HOME&#39;</span>
<span class="n">ENV_XDG_CACHE_HOME</span> <span class="o">=</span> <span class="s1">&#39;XDG_CACHE_HOME&#39;</span>
<span class="n">DEFAULT_CACHE_DIR</span> <span class="o">=</span> <span class="s1">&#39;~/.cache&#39;</span>
<span class="n">torch_home</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">expanduser</span><span class="p">(</span>
<span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="n">ENV_TORCH_HOME</span><span class="p">,</span>
<span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">getenv</span><span class="p">(</span><span class="n">ENV_XDG_CACHE_HOME</span><span class="p">,</span> <span class="n">DEFAULT_CACHE_DIR</span><span class="p">),</span> <span class="s1">&#39;torch&#39;</span><span class="p">)))</span>
<span class="k">return</span> <span class="n">torch_home</span>
<span class="n">torch_home</span> <span class="o">=</span> <span class="n">_get_torch_home</span><span class="p">()</span>
<span class="n">model_dir</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">torch_home</span><span class="p">,</span> <span class="s1">&#39;checkpoints&#39;</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="n">os</span><span class="o">.</span><span class="n">makedirs</span><span class="p">(</span><span class="n">model_dir</span><span class="p">)</span>
<span class="k">except</span> <span class="ne">OSError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">if</span> <span class="n">e</span><span class="o">.</span><span class="n">errno</span> <span class="o">==</span> <span class="n">errno</span><span class="o">.</span><span class="n">EEXIST</span><span class="p">:</span>
<span class="c1"># Directory already exists, ignore.</span>
<span class="k">pass</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># Unexpected OSError, re-raise.</span>
<span class="k">raise</span>
<span class="n">filename</span> <span class="o">=</span> <span class="n">key</span> <span class="o">+</span> <span class="s1">&#39;_imagenet.pth&#39;</span>
<span class="n">cached_file</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">model_dir</span><span class="p">,</span> <span class="n">filename</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">cached_file</span><span class="p">):</span>
<span class="n">gdown</span><span class="o">.</span><span class="n">download</span><span class="p">(</span><span class="n">pretrained_urls</span><span class="p">[</span><span class="n">key</span><span class="p">],</span> <span class="n">cached_file</span><span class="p">,</span> <span class="n">quiet</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="n">state_dict</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">cached_file</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">new_state_dict</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">()</span>
<span class="n">matched_layers</span><span class="p">,</span> <span class="n">discarded_layers</span> <span class="o">=</span> <span class="p">[],</span> <span class="p">[]</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">state_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="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;module.&#39;</span><span class="p">):</span>
<span class="n">k</span> <span class="o">=</span> <span class="n">k</span><span class="p">[</span><span class="mi">7</span><span class="p">:]</span> <span class="c1"># discard module.</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">new_state_dict</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="o">=</span> <span class="n">v</span>
<span class="n">matched_layers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">k</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">discarded_layers</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">k</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">new_state_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">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">matched_layers</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
<span class="s1">&#39;The pretrained weights from &quot;</span><span class="si">{}</span><span class="s1">&quot; cannot be loaded, &#39;</span>
<span class="s1">&#39;please check the key names manually &#39;</span>
<span class="s1">&#39;(** ignored and continue **)&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">cached_file</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">&#39;Successfully loaded imagenet pretrained weights from &quot;</span><span class="si">{}</span><span class="s1">&quot;&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">cached_file</span><span class="p">))</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">discarded_layers</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="nb">print</span><span class="p">(</span><span class="s1">&#39;** The following layers are discarded &#39;</span>
<span class="s1">&#39;due to unmatched keys or layer size: </span><span class="si">{}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">discarded_layers</span><span class="p">))</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="c1">##########</span>
<span class="c1"># Instantiation</span>
<span class="c1">##########</span>
1.0.0
2019-08-26 13:27:00 +01:00
<span class="k">def</span> <span class="nf">osnet_x1_0</span><span class="p">(</span><span class="n">num_classes</span><span class="o">=</span><span class="mi">1000</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="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="c1"># standard size (width x1.0)</span>
1.0.0
2019-08-26 13:27:00 +01:00
<span class="n">model</span> <span class="o">=</span> <span class="n">OSNet</span><span class="p">(</span><span class="n">num_classes</span><span class="p">,</span> <span class="n">blocks</span><span class="o">=</span><span class="p">[</span><span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">],</span> <span class="n">layers</span><span class="o">=</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="mi">2</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">384</span><span class="p">,</span> <span class="mi">512</span><span class="p">],</span> <span class="n">loss</span><span class="o">=</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">key</span><span class="o">=</span><span class="s1">&#39;osnet_x1_0&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
update docs
2019-07-03 13:46:28 +01:00
1.0.0
2019-08-26 13:27:00 +01:00
<span class="k">def</span> <span class="nf">osnet_x0_75</span><span class="p">(</span><span class="n">num_classes</span><span class="o">=</span><span class="mi">1000</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="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="c1"># medium size (width x0.75)</span>
1.0.0
2019-08-26 13:27:00 +01:00
<span class="n">model</span> <span class="o">=</span> <span class="n">OSNet</span><span class="p">(</span><span class="n">num_classes</span><span class="p">,</span> <span class="n">blocks</span><span class="o">=</span><span class="p">[</span><span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">],</span> <span class="n">layers</span><span class="o">=</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="mi">2</span><span class="p">],</span>
<span class="n">channels</span><span class="o">=</span><span class="p">[</span><span class="mi">48</span><span class="p">,</span> <span class="mi">192</span><span class="p">,</span> <span class="mi">288</span><span class="p">,</span> <span class="mi">384</span><span class="p">],</span> <span class="n">loss</span><span class="o">=</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">key</span><span class="o">=</span><span class="s1">&#39;osnet_x0_75&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
update docs
2019-07-03 13:46:28 +01:00
1.0.0
2019-08-26 13:27:00 +01:00
<span class="k">def</span> <span class="nf">osnet_x0_5</span><span class="p">(</span><span class="n">num_classes</span><span class="o">=</span><span class="mi">1000</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="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="c1"># tiny size (width x0.5)</span>
1.0.0
2019-08-26 13:27:00 +01:00
<span class="n">model</span> <span class="o">=</span> <span class="n">OSNet</span><span class="p">(</span><span class="n">num_classes</span><span class="p">,</span> <span class="n">blocks</span><span class="o">=</span><span class="p">[</span><span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">],</span> <span class="n">layers</span><span class="o">=</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="mi">2</span><span class="p">],</span>
<span class="n">channels</span><span class="o">=</span><span class="p">[</span><span class="mi">32</span><span class="p">,</span> <span class="mi">128</span><span class="p">,</span> <span class="mi">192</span><span class="p">,</span> <span class="mi">256</span><span class="p">],</span> <span class="n">loss</span><span class="o">=</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">key</span><span class="o">=</span><span class="s1">&#39;osnet_x0_5&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
update docs
2019-07-03 13:46:28 +01:00
1.0.0
2019-08-26 13:27:00 +01:00
<span class="k">def</span> <span class="nf">osnet_x0_25</span><span class="p">(</span><span class="n">num_classes</span><span class="o">=</span><span class="mi">1000</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="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="c1"># very tiny size (width x0.25)</span>
1.0.0
2019-08-26 13:27:00 +01:00
<span class="n">model</span> <span class="o">=</span> <span class="n">OSNet</span><span class="p">(</span><span class="n">num_classes</span><span class="p">,</span> <span class="n">blocks</span><span class="o">=</span><span class="p">[</span><span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">],</span> <span class="n">layers</span><span class="o">=</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="mi">2</span><span class="p">],</span>
<span class="n">channels</span><span class="o">=</span><span class="p">[</span><span class="mi">16</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="mi">96</span><span class="p">,</span> <span class="mi">128</span><span class="p">],</span> <span class="n">loss</span><span class="o">=</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">key</span><span class="o">=</span><span class="s1">&#39;osnet_x0_25&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
update docs
2019-07-03 13:46:28 +01:00
1.0.0
2019-08-26 13:27:00 +01:00
<span class="k">def</span> <span class="nf">osnet_ibn_x1_0</span><span class="p">(</span><span class="n">num_classes</span><span class="o">=</span><span class="mi">1000</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="n">loss</span><span class="o">=</span><span class="s1">&#39;softmax&#39;</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
update docs
2019-07-03 13:46:28 +01:00
<span class="c1"># standard size (width x1.0) + IBN layer</span>
<span class="c1"># Ref: Pan et al. Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net. ECCV, 2018.</span>
1.0.0
2019-08-26 13:27:00 +01:00
<span class="n">model</span> <span class="o">=</span> <span class="n">OSNet</span><span class="p">(</span><span class="n">num_classes</span><span class="p">,</span> <span class="n">blocks</span><span class="o">=</span><span class="p">[</span><span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">,</span> <span class="n">OSBlock</span><span class="p">],</span> <span class="n">layers</span><span class="o">=</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="mi">2</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">384</span><span class="p">,</span> <span class="mi">512</span><span class="p">],</span> <span class="n">loss</span><span class="o">=</span><span class="n">loss</span><span class="p">,</span> <span class="n">IN</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="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">key</span><span class="o">=</span><span class="s1">&#39;osnet_ibn_x1_0&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">model</span>
update docs
2019-07-03 13:46:28 +01:00
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; 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>
Reference in New Issue Copy Permalink