487 lines
52 KiB
HTML
487 lines
52 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.data.transforms — torchreid 1.0.5 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">
|
|
1.0.5
|
|
</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.data.transforms</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.data.transforms</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="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">print_function</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">PIL</span> <span class="k">import</span> <span class="n">Image</span>
|
|
<span class="kn">import</span> <span class="nn">random</span>
|
|
<span class="kn">import</span> <span class="nn">math</span>
|
|
<span class="kn">from</span> <span class="nn">collections</span> <span class="k">import</span> <span class="n">deque</span>
|
|
|
|
<span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="kn">from</span> <span class="nn">torchvision.transforms</span> <span class="k">import</span> <span class="o">*</span>
|
|
|
|
|
|
<div class="viewcode-block" id="Random2DTranslation"><a class="viewcode-back" href="../../../pkg/data.html#torchreid.data.transforms.Random2DTranslation">[docs]</a><span class="k">class</span> <span class="nc">Random2DTranslation</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
|
|
<span class="sd">"""Randomly translates the input image with a probability.</span>
|
|
|
|
<span class="sd"> Specifically, given a predefined shape (height, width), the input is first</span>
|
|
<span class="sd"> resized with a factor of 1.125, leading to (height*1.125, width*1.125), then</span>
|
|
<span class="sd"> a random crop is performed. Such operation is done with a probability.</span>
|
|
|
|
<span class="sd"> Args:</span>
|
|
<span class="sd"> height (int): target image height.</span>
|
|
<span class="sd"> width (int): target image width.</span>
|
|
<span class="sd"> p (float, optional): probability that this operation takes place.</span>
|
|
<span class="sd"> Default is 0.5.</span>
|
|
<span class="sd"> interpolation (int, optional): desired interpolation. Default is</span>
|
|
<span class="sd"> ``PIL.Image.BILINEAR``</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">height</span><span class="p">,</span> <span class="n">width</span><span class="p">,</span> <span class="n">p</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">interpolation</span><span class="o">=</span><span class="n">Image</span><span class="o">.</span><span class="n">BILINEAR</span><span class="p">):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">height</span> <span class="o">=</span> <span class="n">height</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">width</span> <span class="o">=</span> <span class="n">width</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">p</span> <span class="o">=</span> <span class="n">p</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">interpolation</span> <span class="o">=</span> <span class="n">interpolation</span>
|
|
|
|
<span class="k">def</span> <span class="nf">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">img</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</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="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">p</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">img</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">width</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">height</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">interpolation</span><span class="p">)</span>
|
|
|
|
<span class="n">new_width</span><span class="p">,</span> <span class="n">new_height</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">width</span> <span class="o">*</span> <span class="mf">1.125</span><span class="p">)),</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">height</span> <span class="o">*</span> <span class="mf">1.125</span><span class="p">))</span>
|
|
<span class="n">resized_img</span> <span class="o">=</span> <span class="n">img</span><span class="o">.</span><span class="n">resize</span><span class="p">((</span><span class="n">new_width</span><span class="p">,</span> <span class="n">new_height</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">interpolation</span><span class="p">)</span>
|
|
<span class="n">x_maxrange</span> <span class="o">=</span> <span class="n">new_width</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">width</span>
|
|
<span class="n">y_maxrange</span> <span class="o">=</span> <span class="n">new_height</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">height</span>
|
|
<span class="n">x1</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">x_maxrange</span><span class="p">)))</span>
|
|
<span class="n">y1</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">y_maxrange</span><span class="p">)))</span>
|
|
<span class="n">croped_img</span> <span class="o">=</span> <span class="n">resized_img</span><span class="o">.</span><span class="n">crop</span><span class="p">((</span><span class="n">x1</span><span class="p">,</span> <span class="n">y1</span><span class="p">,</span> <span class="n">x1</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">width</span><span class="p">,</span> <span class="n">y1</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">height</span><span class="p">))</span>
|
|
<span class="k">return</span> <span class="n">croped_img</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="RandomErasing"><a class="viewcode-back" href="../../../pkg/data.html#torchreid.data.transforms.RandomErasing">[docs]</a><span class="k">class</span> <span class="nc">RandomErasing</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
|
|
<span class="sd">"""Randomly erases an image patch.</span>
|
|
|
|
<span class="sd"> Origin: `<https://github.com/zhunzhong07/Random-Erasing>`_</span>
|
|
|
|
<span class="sd"> Reference:</span>
|
|
<span class="sd"> Zhong et al. Random Erasing Data Augmentation.</span>
|
|
|
|
<span class="sd"> Args:</span>
|
|
<span class="sd"> probability (float, optional): probability that this operation takes place.</span>
|
|
<span class="sd"> Default is 0.5.</span>
|
|
<span class="sd"> sl (float, optional): min erasing area.</span>
|
|
<span class="sd"> sh (float, optional): max erasing area.</span>
|
|
<span class="sd"> r1 (float, optional): min aspect ratio.</span>
|
|
<span class="sd"> mean (list, optional): erasing value.</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">probability</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">sl</span><span class="o">=</span><span class="mf">0.02</span><span class="p">,</span> <span class="n">sh</span><span class="o">=</span><span class="mf">0.4</span><span class="p">,</span> <span class="n">r1</span><span class="o">=</span><span class="mf">0.3</span><span class="p">,</span> <span class="n">mean</span><span class="o">=</span><span class="p">[</span><span class="mf">0.4914</span><span class="p">,</span> <span class="mf">0.4822</span><span class="p">,</span> <span class="mf">0.4465</span><span class="p">]):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">probability</span> <span class="o">=</span> <span class="n">probability</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">mean</span> <span class="o">=</span> <span class="n">mean</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">sl</span> <span class="o">=</span> <span class="n">sl</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">sh</span> <span class="o">=</span> <span class="n">sh</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">r1</span> <span class="o">=</span> <span class="n">r1</span>
|
|
|
|
<span class="k">def</span> <span class="nf">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">img</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</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="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">probability</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">img</span>
|
|
|
|
<span class="k">for</span> <span class="n">attempt</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">100</span><span class="p">):</span>
|
|
<span class="n">area</span> <span class="o">=</span> <span class="n">img</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="o">*</span> <span class="n">img</span><span class="o">.</span><span class="n">size</span><span class="p">()[</span><span class="mi">2</span><span class="p">]</span>
|
|
|
|
<span class="n">target_area</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">sl</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">sh</span><span class="p">)</span> <span class="o">*</span> <span class="n">area</span>
|
|
<span class="n">aspect_ratio</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">r1</span><span class="p">,</span> <span class="mi">1</span><span class="o">/</span><span class="bp">self</span><span class="o">.</span><span class="n">r1</span><span class="p">)</span>
|
|
|
|
<span class="n">h</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span><span class="n">target_area</span> <span class="o">*</span> <span class="n">aspect_ratio</span><span class="p">)))</span>
|
|
<span class="n">w</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span><span class="n">target_area</span> <span class="o">/</span> <span class="n">aspect_ratio</span><span class="p">)))</span>
|
|
|
|
<span class="k">if</span> <span class="n">w</span> <span class="o"><</span> <span class="n">img</span><span class="o">.</span><span class="n">size</span><span class="p">()[</span><span class="mi">2</span><span class="p">]</span> <span class="ow">and</span> <span class="n">h</span> <span class="o"><</span> <span class="n">img</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">x1</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">img</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="o">-</span> <span class="n">h</span><span class="p">)</span>
|
|
<span class="n">y1</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">img</span><span class="o">.</span><span class="n">size</span><span class="p">()[</span><span class="mi">2</span><span class="p">]</span> <span class="o">-</span> <span class="n">w</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">img</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">3</span><span class="p">:</span>
|
|
<span class="n">img</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="n">x1</span><span class="p">:</span><span class="n">x1</span><span class="o">+</span><span class="n">h</span><span class="p">,</span> <span class="n">y1</span><span class="p">:</span><span class="n">y1</span><span class="o">+</span><span class="n">w</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mean</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="n">img</span><span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="n">x1</span><span class="p">:</span><span class="n">x1</span><span class="o">+</span><span class="n">h</span><span class="p">,</span> <span class="n">y1</span><span class="p">:</span><span class="n">y1</span><span class="o">+</span><span class="n">w</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mean</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="n">img</span><span class="p">[</span><span class="mi">2</span><span class="p">,</span> <span class="n">x1</span><span class="p">:</span><span class="n">x1</span><span class="o">+</span><span class="n">h</span><span class="p">,</span> <span class="n">y1</span><span class="p">:</span><span class="n">y1</span><span class="o">+</span><span class="n">w</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mean</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">img</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="n">x1</span><span class="p">:</span><span class="n">x1</span><span class="o">+</span><span class="n">h</span><span class="p">,</span> <span class="n">y1</span><span class="p">:</span><span class="n">y1</span><span class="o">+</span><span class="n">w</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">mean</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="k">return</span> <span class="n">img</span>
|
|
|
|
<span class="k">return</span> <span class="n">img</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="ColorAugmentation"><a class="viewcode-back" href="../../../pkg/data.html#torchreid.data.transforms.ColorAugmentation">[docs]</a><span class="k">class</span> <span class="nc">ColorAugmentation</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
|
|
<span class="sd">"""Randomly alters the intensities of RGB channels.</span>
|
|
|
|
<span class="sd"> Reference:</span>
|
|
<span class="sd"> Krizhevsky et al. ImageNet Classification with Deep ConvolutionalNeural</span>
|
|
<span class="sd"> Networks. NIPS 2012.</span>
|
|
|
|
<span class="sd"> Args:</span>
|
|
<span class="sd"> p (float, optional): probability that this operation takes place.</span>
|
|
<span class="sd"> Default is 0.5.</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">p</span><span class="o">=</span><span class="mf">0.5</span><span class="p">):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">p</span> <span class="o">=</span> <span class="n">p</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">eig_vec</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">([</span>
|
|
<span class="p">[</span><span class="mf">0.4009</span><span class="p">,</span> <span class="mf">0.7192</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.5675</span><span class="p">],</span>
|
|
<span class="p">[</span><span class="o">-</span><span class="mf">0.8140</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.0045</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.5808</span><span class="p">],</span>
|
|
<span class="p">[</span><span class="mf">0.4203</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.6948</span><span class="p">,</span> <span class="o">-</span><span class="mf">0.5836</span><span class="p">],</span>
|
|
<span class="p">])</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">eig_val</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">([[</span><span class="mf">0.2175</span><span class="p">,</span> <span class="mf">0.0188</span><span class="p">,</span> <span class="mf">0.0045</span><span class="p">]])</span>
|
|
|
|
<span class="k">def</span> <span class="nf">_check_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tensor</span><span class="p">):</span>
|
|
<span class="k">assert</span> <span class="n">tensor</span><span class="o">.</span><span class="n">dim</span><span class="p">()</span> <span class="o">==</span> <span class="mi">3</span> <span class="ow">and</span> <span class="n">tensor</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">3</span>
|
|
|
|
<span class="k">def</span> <span class="nf">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tensor</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</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="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">p</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">tensor</span>
|
|
<span class="n">alpha</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">normal</span><span class="p">(</span><span class="n">mean</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">zeros_like</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">eig_val</span><span class="p">))</span> <span class="o">*</span> <span class="mf">0.1</span>
|
|
<span class="n">quatity</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">mm</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">eig_val</span> <span class="o">*</span> <span class="n">alpha</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">eig_vec</span><span class="p">)</span>
|
|
<span class="n">tensor</span> <span class="o">=</span> <span class="n">tensor</span> <span class="o">+</span> <span class="n">quatity</span><span class="o">.</span><span class="n">view</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="mi">1</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">tensor</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="RandomPatch"><a class="viewcode-back" href="../../../pkg/data.html#torchreid.data.transforms.RandomPatch">[docs]</a><span class="k">class</span> <span class="nc">RandomPatch</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
|
|
<span class="sd">"""Random patch data augmentation.</span>
|
|
|
|
<span class="sd"> There is a patch pool that stores randomly extracted pathces from person images.</span>
|
|
<span class="sd"> </span>
|
|
<span class="sd"> For each input image, RandomPatch</span>
|
|
<span class="sd"> 1) extracts a random patch and stores the patch in the patch pool;</span>
|
|
<span class="sd"> 2) randomly selects a patch from the patch pool and pastes it on the</span>
|
|
<span class="sd"> input (at random position) to simulate occlusion.</span>
|
|
|
|
<span class="sd"> Reference:</span>
|
|
<span class="sd"> - Zhou et al. Omni-Scale Feature Learning for Person Re-Identification. ICCV, 2019.</span>
|
|
<span class="sd"> - Zhou et al. Learning Generalisable Omni-Scale Representations</span>
|
|
<span class="sd"> for Person Re-Identification. arXiv preprint, 2019.</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">prob_happen</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">pool_capacity</span><span class="o">=</span><span class="mi">50000</span><span class="p">,</span> <span class="n">min_sample_size</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span>
|
|
<span class="n">patch_min_area</span><span class="o">=</span><span class="mf">0.01</span><span class="p">,</span> <span class="n">patch_max_area</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">patch_min_ratio</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span>
|
|
<span class="n">prob_rotate</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span> <span class="n">prob_flip_leftright</span><span class="o">=</span><span class="mf">0.5</span><span class="p">,</span>
|
|
<span class="p">):</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">prob_happen</span> <span class="o">=</span> <span class="n">prob_happen</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">patch_min_area</span> <span class="o">=</span> <span class="n">patch_min_area</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">patch_max_area</span> <span class="o">=</span> <span class="n">patch_max_area</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">patch_min_ratio</span> <span class="o">=</span> <span class="n">patch_min_ratio</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">prob_rotate</span> <span class="o">=</span> <span class="n">prob_rotate</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">prob_flip_leftright</span> <span class="o">=</span> <span class="n">prob_flip_leftright</span>
|
|
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">patchpool</span> <span class="o">=</span> <span class="n">deque</span><span class="p">(</span><span class="n">maxlen</span><span class="o">=</span><span class="n">pool_capacity</span><span class="p">)</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">min_sample_size</span> <span class="o">=</span> <span class="n">min_sample_size</span>
|
|
|
|
<span class="k">def</span> <span class="nf">generate_wh</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">W</span><span class="p">,</span> <span class="n">H</span><span class="p">):</span>
|
|
<span class="n">area</span> <span class="o">=</span> <span class="n">W</span> <span class="o">*</span> <span class="n">H</span>
|
|
<span class="k">for</span> <span class="n">attempt</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">100</span><span class="p">):</span>
|
|
<span class="n">target_area</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">patch_min_area</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">patch_max_area</span><span class="p">)</span> <span class="o">*</span> <span class="n">area</span>
|
|
<span class="n">aspect_ratio</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">patch_min_ratio</span><span class="p">,</span> <span class="mf">1.</span><span class="o">/</span><span class="bp">self</span><span class="o">.</span><span class="n">patch_min_ratio</span><span class="p">)</span>
|
|
<span class="n">h</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span><span class="n">target_area</span> <span class="o">*</span> <span class="n">aspect_ratio</span><span class="p">)))</span>
|
|
<span class="n">w</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">sqrt</span><span class="p">(</span><span class="n">target_area</span> <span class="o">/</span> <span class="n">aspect_ratio</span><span class="p">)))</span>
|
|
<span class="k">if</span> <span class="n">w</span> <span class="o"><</span> <span class="n">W</span> <span class="ow">and</span> <span class="n">h</span> <span class="o"><</span> <span class="n">H</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span>
|
|
<span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span>
|
|
|
|
<span class="k">def</span> <span class="nf">transform_patch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">patch</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</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="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">prob_flip_leftright</span><span class="p">:</span>
|
|
<span class="n">patch</span> <span class="o">=</span> <span class="n">patch</span><span class="o">.</span><span class="n">transpose</span><span class="p">(</span><span class="n">Image</span><span class="o">.</span><span class="n">FLIP_LEFT_RIGHT</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</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="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">prob_rotate</span><span class="p">:</span>
|
|
<span class="n">patch</span> <span class="o">=</span> <span class="n">patch</span><span class="o">.</span><span class="n">rotate</span><span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="o">-</span><span class="mi">10</span><span class="p">,</span> <span class="mi">10</span><span class="p">))</span>
|
|
<span class="k">return</span> <span class="n">patch</span>
|
|
|
|
<span class="k">def</span> <span class="nf">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">img</span><span class="p">):</span>
|
|
<span class="n">W</span><span class="p">,</span> <span class="n">H</span> <span class="o">=</span> <span class="n">img</span><span class="o">.</span><span class="n">size</span> <span class="c1"># original image size</span>
|
|
|
|
<span class="c1"># collect new patch</span>
|
|
<span class="n">w</span><span class="p">,</span> <span class="n">h</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">generate_wh</span><span class="p">(</span><span class="n">W</span><span class="p">,</span> <span class="n">H</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">w</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">h</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">x1</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">W</span> <span class="o">-</span> <span class="n">w</span><span class="p">)</span>
|
|
<span class="n">y1</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">H</span> <span class="o">-</span> <span class="n">h</span><span class="p">)</span>
|
|
<span class="n">new_patch</span> <span class="o">=</span> <span class="n">img</span><span class="o">.</span><span class="n">crop</span><span class="p">((</span><span class="n">x1</span><span class="p">,</span> <span class="n">y1</span><span class="p">,</span> <span class="n">x1</span> <span class="o">+</span> <span class="n">w</span><span class="p">,</span> <span class="n">y1</span> <span class="o">+</span> <span class="n">h</span><span class="p">))</span>
|
|
<span class="bp">self</span><span class="o">.</span><span class="n">patchpool</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">new_patch</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">patchpool</span><span class="p">)</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">min_sample_size</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">img</span>
|
|
|
|
<span class="k">if</span> <span class="n">random</span><span class="o">.</span><span class="n">uniform</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="o">></span> <span class="bp">self</span><span class="o">.</span><span class="n">prob_happen</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">img</span>
|
|
|
|
<span class="c1"># paste a randomly selected patch on a random position</span>
|
|
<span class="n">patch</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">sample</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">patchpool</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="n">patchW</span><span class="p">,</span> <span class="n">patchH</span> <span class="o">=</span> <span class="n">patch</span><span class="o">.</span><span class="n">size</span>
|
|
<span class="n">x1</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">W</span> <span class="o">-</span> <span class="n">patchW</span><span class="p">)</span>
|
|
<span class="n">y1</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">H</span> <span class="o">-</span> <span class="n">patchH</span><span class="p">)</span>
|
|
<span class="n">patch</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">transform_patch</span><span class="p">(</span><span class="n">patch</span><span class="p">)</span>
|
|
<span class="n">img</span><span class="o">.</span><span class="n">paste</span><span class="p">(</span><span class="n">patch</span><span class="p">,</span> <span class="p">(</span><span class="n">x1</span><span class="p">,</span> <span class="n">y1</span><span class="p">))</span>
|
|
|
|
<span class="k">return</span> <span class="n">img</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="build_transforms"><a class="viewcode-back" href="../../../pkg/data.html#torchreid.data.transforms.build_transforms">[docs]</a><span class="k">def</span> <span class="nf">build_transforms</span><span class="p">(</span><span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">,</span> <span class="n">transforms</span><span class="o">=</span><span class="s1">'random_flip'</span><span class="p">,</span> <span class="n">norm_mean</span><span class="o">=</span><span class="p">[</span><span class="mf">0.485</span><span class="p">,</span> <span class="mf">0.456</span><span class="p">,</span> <span class="mf">0.406</span><span class="p">],</span>
|
|
<span class="n">norm_std</span><span class="o">=</span><span class="p">[</span><span class="mf">0.229</span><span class="p">,</span> <span class="mf">0.224</span><span class="p">,</span> <span class="mf">0.225</span><span class="p">],</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
|
|
<span class="sd">"""Builds train and test transform functions.</span>
|
|
|
|
<span class="sd"> Args:</span>
|
|
<span class="sd"> height (int): target image height.</span>
|
|
<span class="sd"> width (int): target image width.</span>
|
|
<span class="sd"> transforms (str or list of str, optional): transformations applied to model training.</span>
|
|
<span class="sd"> Default is 'random_flip'.</span>
|
|
<span class="sd"> norm_mean (list or None, optional): normalization mean values. Default is ImageNet means.</span>
|
|
<span class="sd"> norm_std (list or None, optional): normalization standard deviation values. Default is</span>
|
|
<span class="sd"> ImageNet standard deviation values.</span>
|
|
<span class="sd"> """</span>
|
|
<span class="k">if</span> <span class="n">transforms</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">transforms</span> <span class="o">=</span> <span class="p">[]</span>
|
|
|
|
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">transforms</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
|
|
<span class="n">transforms</span> <span class="o">=</span> <span class="p">[</span><span class="n">transforms</span><span class="p">]</span>
|
|
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">transforms</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
|
|
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'transforms must be a list of strings, but found to be </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">transforms</span><span class="p">)))</span>
|
|
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">transforms</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="n">transforms</span> <span class="o">=</span> <span class="p">[</span><span class="n">t</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="n">transforms</span><span class="p">]</span>
|
|
|
|
<span class="k">if</span> <span class="n">norm_mean</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">norm_std</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">norm_mean</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.485</span><span class="p">,</span> <span class="mf">0.456</span><span class="p">,</span> <span class="mf">0.406</span><span class="p">]</span> <span class="c1"># imagenet mean</span>
|
|
<span class="n">norm_std</span> <span class="o">=</span> <span class="p">[</span><span class="mf">0.229</span><span class="p">,</span> <span class="mf">0.224</span><span class="p">,</span> <span class="mf">0.225</span><span class="p">]</span> <span class="c1"># imagenet std</span>
|
|
<span class="n">normalize</span> <span class="o">=</span> <span class="n">Normalize</span><span class="p">(</span><span class="n">mean</span><span class="o">=</span><span class="n">norm_mean</span><span class="p">,</span> <span class="n">std</span><span class="o">=</span><span class="n">norm_std</span><span class="p">)</span>
|
|
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'Building train transforms ...'</span><span class="p">)</span>
|
|
<span class="n">transform_tr</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="n">transform_tr</span> <span class="o">+=</span> <span class="p">[</span><span class="n">Resize</span><span class="p">((</span><span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">))]</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ resize to </span><span class="si">{}</span><span class="s1">x</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">))</span>
|
|
<span class="k">if</span> <span class="s1">'random_flip'</span> <span class="ow">in</span> <span class="n">transforms</span><span class="p">:</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ random flip'</span><span class="p">)</span>
|
|
<span class="n">transform_tr</span> <span class="o">+=</span> <span class="p">[</span><span class="n">RandomHorizontalFlip</span><span class="p">()]</span>
|
|
<span class="k">if</span> <span class="s1">'random_crop'</span> <span class="ow">in</span> <span class="n">transforms</span><span class="p">:</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ random crop (enlarge to </span><span class="si">{}</span><span class="s1">x</span><span class="si">{}</span><span class="s1"> and '</span> \
|
|
<span class="s1">'crop </span><span class="si">{}</span><span class="s1">x</span><span class="si">{}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">height</span><span class="o">*</span><span class="mf">1.125</span><span class="p">)),</span> <span class="nb">int</span><span class="p">(</span><span class="nb">round</span><span class="p">(</span><span class="n">width</span><span class="o">*</span><span class="mf">1.125</span><span class="p">)),</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">))</span>
|
|
<span class="n">transform_tr</span> <span class="o">+=</span> <span class="p">[</span><span class="n">Random2DTranslation</span><span class="p">(</span><span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">)]</span>
|
|
<span class="k">if</span> <span class="s1">'random_patch'</span> <span class="ow">in</span> <span class="n">transforms</span><span class="p">:</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ random patch'</span><span class="p">)</span>
|
|
<span class="n">transform_tr</span> <span class="o">+=</span> <span class="p">[</span><span class="n">RandomPatch</span><span class="p">()]</span>
|
|
<span class="k">if</span> <span class="s1">'color_jitter'</span> <span class="ow">in</span> <span class="n">transforms</span><span class="p">:</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ color jitter'</span><span class="p">)</span>
|
|
<span class="n">transform_tr</span> <span class="o">+=</span> <span class="p">[</span><span class="n">ColorJitter</span><span class="p">(</span><span class="n">brightness</span><span class="o">=</span><span class="mf">0.2</span><span class="p">,</span> <span class="n">contrast</span><span class="o">=</span><span class="mf">0.15</span><span class="p">,</span> <span class="n">saturation</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">hue</span><span class="o">=</span><span class="mi">0</span><span class="p">)]</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ to torch tensor of range [0, 1]'</span><span class="p">)</span>
|
|
<span class="n">transform_tr</span> <span class="o">+=</span> <span class="p">[</span><span class="n">ToTensor</span><span class="p">()]</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ normalization (mean=</span><span class="si">{}</span><span class="s1">, std=</span><span class="si">{}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">norm_mean</span><span class="p">,</span> <span class="n">norm_std</span><span class="p">))</span>
|
|
<span class="n">transform_tr</span> <span class="o">+=</span> <span class="p">[</span><span class="n">normalize</span><span class="p">]</span>
|
|
<span class="k">if</span> <span class="s1">'random_erase'</span> <span class="ow">in</span> <span class="n">transforms</span><span class="p">:</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ random erase'</span><span class="p">)</span>
|
|
<span class="n">transform_tr</span> <span class="o">+=</span> <span class="p">[</span><span class="n">RandomErasing</span><span class="p">()]</span>
|
|
<span class="n">transform_tr</span> <span class="o">=</span> <span class="n">Compose</span><span class="p">(</span><span class="n">transform_tr</span><span class="p">)</span>
|
|
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'Building test transforms ...'</span><span class="p">)</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ resize to </span><span class="si">{}</span><span class="s1">x</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">))</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ to torch tensor of range [0, 1]'</span><span class="p">)</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s1">'+ normalization (mean=</span><span class="si">{}</span><span class="s1">, std=</span><span class="si">{}</span><span class="s1">)'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">norm_mean</span><span class="p">,</span> <span class="n">norm_std</span><span class="p">))</span>
|
|
<span class="n">transform_te</span> <span class="o">=</span> <span class="n">Compose</span><span class="p">([</span>
|
|
<span class="n">Resize</span><span class="p">((</span><span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">)),</span>
|
|
<span class="n">ToTensor</span><span class="p">(),</span>
|
|
<span class="n">normalize</span><span class="p">,</span>
|
|
<span class="p">])</span>
|
|
|
|
<span class="k">return</span> <span class="n">transform_tr</span><span class="p">,</span> <span class="n">transform_te</span></div>
|
|
</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> |