<!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>pathflowai.losses — PathFlowAI 0.1 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"> PathFlowAI
</a>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<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">
<!-- Local TOC -->
<div class="local-toc"></div>
</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">PathFlowAI</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>pathflowai.losses</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 pathflowai.losses</h1><div class="highlight"><pre>
<span></span><span class="sd">"""</span>
<span class="sd">losses.py</span>
<span class="sd">=======================</span>
<span class="sd">Some additional loss functions that can be called using the pipeline, some of which still to be implemented.</span>
<span class="sd">"""</span>
<span class="kn">import</span> <span class="nn">torch</span><span class="o">,</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Callable</span><span class="p">,</span> <span class="n">Iterable</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Set</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">TypeVar</span><span class="p">,</span> <span class="n">Union</span>
<span class="kn">from</span> <span class="nn">torch</span> <span class="k">import</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">einsum</span>
<span class="kn">import</span> <span class="nn">torch.nn.functional</span> <span class="k">as</span> <span class="nn">F</span>
<span class="kn">from</span> <span class="nn">scipy.ndimage</span> <span class="k">import</span> <span class="n">distance_transform_edt</span> <span class="k">as</span> <span class="n">distance</span>
<span class="kn">from</span> <span class="nn">torch</span> <span class="k">import</span> <span class="n">nn</span>
<div class="viewcode-block" id="assert_"><a class="viewcode-back" href="../../index.html#pathflowai.losses.assert_">[docs]</a><span class="k">def</span> <span class="nf">assert_</span><span class="p">(</span><span class="n">condition</span><span class="p">,</span> <span class="n">message</span><span class="o">=</span><span class="s1">''</span><span class="p">,</span> <span class="n">exception_type</span><span class="o">=</span><span class="ne">AssertionError</span><span class="p">):</span>
<span class="sd">"""https://raw.githubusercontent.com/inferno-pytorch/inferno/0561e8a95cde6bfc5e10a3609841b7b0ca5b03ca/inferno/utils/exceptions.py</span>
<span class="sd"> Like assert, but with arbitrary exception types."""</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">condition</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">exception_type</span><span class="p">(</span><span class="n">message</span><span class="p">)</span></div>
<div class="viewcode-block" id="ShapeError"><a class="viewcode-back" href="../../index.html#pathflowai.losses.ShapeError">[docs]</a><span class="k">class</span> <span class="nc">ShapeError</span><span class="p">(</span><span class="ne">ValueError</span><span class="p">):</span> <span class="c1"># """https://raw.githubusercontent.com/inferno-pytorch/inferno/0561e8a95cde6bfc5e10a3609841b7b0ca5b03ca/inferno/utils/exceptions.py"""</span>
<span class="k">pass</span></div>
<div class="viewcode-block" id="flatten_samples"><a class="viewcode-back" href="../../index.html#pathflowai.losses.flatten_samples">[docs]</a><span class="k">def</span> <span class="nf">flatten_samples</span><span class="p">(</span><span class="n">input_</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> https://raw.githubusercontent.com/inferno-pytorch/inferno/0561e8a95cde6bfc5e10a3609841b7b0ca5b03ca/inferno/utils/torch_utils.py</span>
<span class="sd"> Flattens a tensor or a variable such that the channel axis is first and the sample axis</span>
<span class="sd"> is second. The shapes are transformed as follows:</span>
<span class="sd"> (N, C, H, W) --> (C, N * H * W)</span>
<span class="sd"> (N, C, D, H, W) --> (C, N * D * H * W)</span>
<span class="sd"> (N, C) --> (C, N)</span>
<span class="sd"> The input must be atleast 2d.</span>
<span class="sd"> """</span>
<span class="n">assert_</span><span class="p">(</span><span class="n">input_</span><span class="o">.</span><span class="n">dim</span><span class="p">()</span> <span class="o">>=</span> <span class="mi">2</span><span class="p">,</span>
<span class="s2">"Tensor or variable must be atleast 2D. Got one of dim </span><span class="si">{}</span><span class="s2">."</span>
<span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">input_</span><span class="o">.</span><span class="n">dim</span><span class="p">()),</span>
<span class="n">ShapeError</span><span class="p">)</span>
<span class="c1"># Get number of channels</span>
<span class="n">num_channels</span> <span class="o">=</span> <span class="n">input_</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="c1"># Permute the channel axis to first</span>
<span class="n">permute_axes</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">input_</span><span class="o">.</span><span class="n">dim</span><span class="p">()))</span>
<span class="n">permute_axes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">permute_axes</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">=</span> <span class="n">permute_axes</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">permute_axes</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="c1"># For input shape (say) NCHW, this should have the shape CNHW</span>
<span class="n">permuted</span> <span class="o">=</span> <span class="n">input_</span><span class="o">.</span><span class="n">permute</span><span class="p">(</span><span class="o">*</span><span class="n">permute_axes</span><span class="p">)</span><span class="o">.</span><span class="n">contiguous</span><span class="p">()</span>
<span class="c1"># Now flatten out all but the first axis and return</span>
<span class="n">flattened</span> <span class="o">=</span> <span class="n">permuted</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">num_channels</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">flattened</span></div>
<div class="viewcode-block" id="GeneralizedDiceLoss"><a class="viewcode-back" href="../../index.html#pathflowai.losses.GeneralizedDiceLoss">[docs]</a><span class="k">class</span> <span class="nc">GeneralizedDiceLoss</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">"""</span>
<span class="sd"> https://raw.githubusercontent.com/inferno-pytorch/inferno/0561e8a95cde6bfc5e10a3609841b7b0ca5b03ca/inferno/extensions/criteria/set_similarity_measures.py</span>
<span class="sd"> Computes the scalar Generalized Dice Loss defined in https://arxiv.org/abs/1707.03237</span>
<span class="sd"> This version works for multiple classes and expects predictions for every class (e.g. softmax output) and</span>
<span class="sd"> one-hot targets for every class.</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">weight</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">channelwise</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-6</span><span class="p">,</span> <span class="n">add_softmax</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">GeneralizedDiceLoss</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">register_buffer</span><span class="p">(</span><span class="s1">'weight'</span><span class="p">,</span> <span class="n">weight</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">channelwise</span> <span class="o">=</span> <span class="n">channelwise</span>
<span class="bp">self</span><span class="o">.</span><span class="n">eps</span> <span class="o">=</span> <span class="n">eps</span>
<span class="bp">self</span><span class="o">.</span><span class="n">add_softmax</span> <span class="o">=</span> <span class="n">add_softmax</span>
<div class="viewcode-block" id="GeneralizedDiceLoss.forward"><a class="viewcode-back" href="../../index.html#pathflowai.losses.GeneralizedDiceLoss.forward">[docs]</a> <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="nb">input</span><span class="p">,</span> <span class="n">target</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> input: torch.FloatTensor or torch.cuda.FloatTensor</span>
<span class="sd"> target: torch.FloatTensor or torch.cuda.FloatTensor</span>
<span class="sd"> Expected shape of the inputs:</span>
<span class="sd"> - if not channelwise: (batch_size, nb_classes, ...)</span>
<span class="sd"> - if channelwise: (batch_size, nb_channels, nb_classes, ...)</span>
<span class="sd"> """</span>
<span class="k">assert</span> <span class="nb">input</span><span class="o">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="n">target</span><span class="o">.</span><span class="n">size</span><span class="p">()</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">add_softmax</span><span class="p">:</span>
<span class="nb">input</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">softmax</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">channelwise</span><span class="p">:</span>
<span class="c1"># Flatten input and target to have the shape (nb_classes, N),</span>
<span class="c1"># where N is the number of samples</span>
<span class="nb">input</span> <span class="o">=</span> <span class="n">flatten_samples</span><span class="p">(</span><span class="nb">input</span><span class="p">)</span>
<span class="n">target</span> <span class="o">=</span> <span class="n">flatten_samples</span><span class="p">(</span><span class="n">target</span><span class="p">)</span><span class="o">.</span><span class="n">float</span><span class="p">()</span>
<span class="c1"># Find classes weights:</span>
<span class="n">sum_targets</span> <span class="o">=</span> <span class="n">target</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="n">class_weigths</span> <span class="o">=</span> <span class="mf">1.</span> <span class="o">/</span> <span class="p">(</span><span class="n">sum_targets</span> <span class="o">*</span> <span class="n">sum_targets</span><span class="p">)</span><span class="o">.</span><span class="n">clamp</span><span class="p">(</span><span class="nb">min</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">eps</span><span class="p">)</span>
<span class="c1"># Compute generalized Dice loss:</span>
<span class="n">numer</span> <span class="o">=</span> <span class="p">((</span><span class="nb">input</span> <span class="o">*</span> <span class="n">target</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="n">class_weigths</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
<span class="n">denom</span> <span class="o">=</span> <span class="p">((</span><span class="nb">input</span> <span class="o">+</span> <span class="n">target</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="n">class_weigths</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
<span class="n">loss</span> <span class="o">=</span> <span class="mf">1.</span> <span class="o">-</span> <span class="mf">2.</span> <span class="o">*</span> <span class="n">numer</span> <span class="o">/</span> <span class="n">denom</span><span class="o">.</span><span class="n">clamp</span><span class="p">(</span><span class="nb">min</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">eps</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">def</span> <span class="nf">flatten_and_preserve_channels</span><span class="p">(</span><span class="n">tensor</span><span class="p">):</span>
<span class="n">tensor_dim</span> <span class="o">=</span> <span class="n">tensor</span><span class="o">.</span><span class="n">dim</span><span class="p">()</span>
<span class="k">assert</span> <span class="n">tensor_dim</span> <span class="o">>=</span> <span class="mi">3</span>
<span class="n">num_channels</span> <span class="o">=</span> <span class="n">tensor</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">num_classes</span> <span class="o">=</span> <span class="n">tensor</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="c1"># Permute the channel axis to first</span>
<span class="n">permute_axes</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">tensor_dim</span><span class="p">))</span>
<span class="n">permute_axes</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">permute_axes</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">permute_axes</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span> <span class="o">=</span> <span class="n">permute_axes</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">permute_axes</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">permute_axes</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">permuted</span> <span class="o">=</span> <span class="n">tensor</span><span class="o">.</span><span class="n">permute</span><span class="p">(</span><span class="o">*</span><span class="n">permute_axes</span><span class="p">)</span><span class="o">.</span><span class="n">contiguous</span><span class="p">()</span>
<span class="n">flattened</span> <span class="o">=</span> <span class="n">permuted</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">num_channels</span><span class="p">,</span> <span class="n">num_classes</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">flattened</span>
<span class="c1"># Flatten input and target to have the shape (nb_channels, nb_classes, N)</span>
<span class="nb">input</span> <span class="o">=</span> <span class="n">flatten_and_preserve_channels</span><span class="p">(</span><span class="nb">input</span><span class="p">)</span>
<span class="n">target</span> <span class="o">=</span> <span class="n">flatten_and_preserve_channels</span><span class="p">(</span><span class="n">target</span><span class="p">)</span>
<span class="c1"># Find classes weights:</span>
<span class="n">sum_targets</span> <span class="o">=</span> <span class="n">target</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="n">class_weigths</span> <span class="o">=</span> <span class="mf">1.</span> <span class="o">/</span> <span class="p">(</span><span class="n">sum_targets</span> <span class="o">*</span> <span class="n">sum_targets</span><span class="p">)</span><span class="o">.</span><span class="n">clamp</span><span class="p">(</span><span class="nb">min</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">eps</span><span class="p">)</span>
<span class="c1"># Compute generalized Dice loss:</span>
<span class="n">numer</span> <span class="o">=</span> <span class="p">((</span><span class="nb">input</span> <span class="o">*</span> <span class="n">target</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="n">class_weigths</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="n">denom</span> <span class="o">=</span> <span class="p">((</span><span class="nb">input</span> <span class="o">+</span> <span class="n">target</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="n">class_weigths</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
<span class="n">channelwise_loss</span> <span class="o">=</span> <span class="mf">1.</span> <span class="o">-</span> <span class="mf">2.</span> <span class="o">*</span> <span class="n">numer</span> <span class="o">/</span> <span class="n">denom</span><span class="o">.</span><span class="n">clamp</span><span class="p">(</span><span class="nb">min</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">eps</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">channelwise_loss</span><span class="o">.</span><span class="n">dim</span><span class="p">()</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
<span class="n">channelwise_loss</span> <span class="o">=</span> <span class="n">channelwise_loss</span><span class="o">.</span><span class="n">squeeze</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight</span><span class="o">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="n">channelwise_loss</span><span class="o">.</span><span class="n">size</span><span class="p">(),</span>\
<span class="sd">"""`weight` should have shape (nb_channels, ),</span>
<span class="sd"> `target` should have shape (batch_size, nb_channels, nb_classes, ...)"""</span>
<span class="c1"># Apply channel weights:</span>
<span class="n">channelwise_loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight</span> <span class="o">*</span> <span class="n">channelwise_loss</span>
<span class="n">loss</span> <span class="o">=</span> <span class="n">channelwise_loss</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
<span class="k">return</span> <span class="n">loss</span></div></div>
<div class="viewcode-block" id="FocalLoss"><a class="viewcode-back" href="../../index.html#pathflowai.losses.FocalLoss">[docs]</a><span class="k">class</span> <span class="nc">FocalLoss</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="c1"># add boundary loss</span>
<span class="sd">"""</span>
<span class="sd"> # https://raw.githubusercontent.com/Hsuxu/Loss_ToolBox-PyTorch/master/FocalLoss/FocalLoss.py</span>
<span class="sd"> This is a implementation of Focal Loss with smooth label cross entropy supported which is proposed in</span>
<span class="sd"> 'Focal Loss for Dense Object Detection. (https://arxiv.org/abs/1708.02002)'</span>
<span class="sd"> Focal_Loss= -1*alpha*(1-pt)*log(pt)</span>
<span class="sd"> :param num_class:</span>
<span class="sd"> :param alpha: (tensor) 3D or 4D the scalar factor for this criterion</span>
<span class="sd"> :param gamma: (float,double) gamma > 0 reduces the relative loss for well-classified examples (p>0.5) putting more</span>
<span class="sd"> focus on hard misclassified example</span>
<span class="sd"> :param smooth: (float,double) smooth value when cross entropy</span>
<span class="sd"> :param balance_index: (int) balance class index, should be specific when alpha is float</span>
<span class="sd"> :param size_average: (bool, optional) By default, the losses are averaged over each loss element in the batch.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">num_class</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">gamma</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">balance_index</span><span class="o">=-</span><span class="mi">1</span><span class="p">,</span> <span class="n">smooth</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">size_average</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">FocalLoss</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">num_class</span> <span class="o">=</span> <span class="n">num_class</span>
<span class="bp">self</span><span class="o">.</span><span class="n">alpha</span> <span class="o">=</span> <span class="n">alpha</span>
<span class="bp">self</span><span class="o">.</span><span class="n">gamma</span> <span class="o">=</span> <span class="n">gamma</span>
<span class="bp">self</span><span class="o">.</span><span class="n">smooth</span> <span class="o">=</span> <span class="n">smooth</span>
<span class="bp">self</span><span class="o">.</span><span class="n">size_average</span> <span class="o">=</span> <span class="n">size_average</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">alpha</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">alpha</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">ones</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_class</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">alpha</span><span class="p">,</span> <span class="p">(</span><span class="nb">list</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)):</span>
<span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">alpha</span><span class="p">)</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_class</span>
<span class="bp">self</span><span class="o">.</span><span class="n">alpha</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">FloatTensor</span><span class="p">(</span><span class="n">alpha</span><span class="p">)</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_class</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">alpha</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">alpha</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">alpha</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">alpha</span><span class="p">,</span> <span class="nb">float</span><span class="p">):</span>
<span class="n">alpha</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">ones</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_class</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="n">alpha</span> <span class="o">=</span> <span class="n">alpha</span> <span class="o">*</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">alpha</span><span class="p">)</span>
<span class="n">alpha</span><span class="p">[</span><span class="n">balance_index</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">alpha</span>
<span class="bp">self</span><span class="o">.</span><span class="n">alpha</span> <span class="o">=</span> <span class="n">alpha</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">'Not support alpha type'</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">smooth</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">smooth</span> <span class="o"><</span> <span class="mi">0</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">smooth</span> <span class="o">></span> <span class="mf">1.0</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'smooth value should be in [0,1]'</span><span class="p">)</span>
<div class="viewcode-block" id="FocalLoss.forward"><a class="viewcode-back" href="../../index.html#pathflowai.losses.FocalLoss.forward">[docs]</a> <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">logit</span><span class="p">,</span> <span class="n">target</span><span class="p">):</span>
<span class="c1"># logit = F.softmax(input, dim=1)</span>
<span class="k">if</span> <span class="n">logit</span><span class="o">.</span><span class="n">dim</span><span class="p">()</span> <span class="o">></span> <span class="mi">2</span><span class="p">:</span>
<span class="c1"># N,C,d1,d2 -> N,C,m (m=d1*d2*...)</span>
<span class="n">logit</span> <span class="o">=</span> <span class="n">logit</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">logit</span><span class="o">.</span><span class="n">size</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span> <span class="n">logit</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="mi">1</span><span class="p">)</span>
<span class="n">logit</span> <span class="o">=</span> <span class="n">logit</span><span class="o">.</span><span class="n">permute</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">contiguous</span><span class="p">()</span>
<span class="n">logit</span> <span class="o">=</span> <span class="n">logit</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">logit</span><span class="o">.</span><span class="n">size</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">))</span>
<span class="n">target</span> <span class="o">=</span> <span class="n">target</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="c1"># N = input.size(0)</span>
<span class="c1"># alpha = torch.ones(N, self.num_class)</span>
<span class="c1"># alpha = alpha * (1 - self.alpha)</span>
<span class="c1"># alpha = alpha.scatter_(1, target.long(), self.alpha)</span>
<span class="n">epsilon</span> <span class="o">=</span> <span class="mf">1e-10</span>
<span class="n">alpha</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">alpha</span>
<span class="k">if</span> <span class="n">alpha</span><span class="o">.</span><span class="n">device</span> <span class="o">!=</span> <span class="nb">input</span><span class="o">.</span><span class="n">device</span><span class="p">:</span>
<span class="n">alpha</span> <span class="o">=</span> <span class="n">alpha</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="nb">input</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
<span class="n">idx</span> <span class="o">=</span> <span class="n">target</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span><span class="o">.</span><span class="n">long</span><span class="p">()</span>
<span class="n">one_hot_key</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">FloatTensor</span><span class="p">(</span><span class="n">target</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="bp">self</span><span class="o">.</span><span class="n">num_class</span><span class="p">)</span><span class="o">.</span><span class="n">zero_</span><span class="p">()</span>
<span class="n">one_hot_key</span> <span class="o">=</span> <span class="n">one_hot_key</span><span class="o">.</span><span class="n">scatter_</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">idx</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="k">if</span> <span class="n">one_hot_key</span><span class="o">.</span><span class="n">device</span> <span class="o">!=</span> <span class="n">logit</span><span class="o">.</span><span class="n">device</span><span class="p">:</span>
<span class="n">one_hot_key</span> <span class="o">=</span> <span class="n">one_hot_key</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">logit</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">smooth</span><span class="p">:</span>
<span class="n">one_hot_key</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">clamp</span><span class="p">(</span>
<span class="n">one_hot_key</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">smooth</span><span class="o">/</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_class</span><span class="o">-</span><span class="mi">1</span><span class="p">),</span> <span class="mf">1.0</span> <span class="o">-</span> <span class="bp">self</span><span class="o">.</span><span class="n">smooth</span><span class="p">)</span>
<span class="n">pt</span> <span class="o">=</span> <span class="p">(</span><span class="n">one_hot_key</span> <span class="o">*</span> <span class="n">logit</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="o">+</span> <span class="n">epsilon</span>
<span class="n">logpt</span> <span class="o">=</span> <span class="n">pt</span><span class="o">.</span><span class="n">log</span><span class="p">()</span>
<span class="n">gamma</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">gamma</span>
<span class="n">alpha</span> <span class="o">=</span> <span class="n">alpha</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span>
<span class="n">loss</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span> <span class="o">*</span> <span class="n">alpha</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">pow</span><span class="p">((</span><span class="mi">1</span> <span class="o">-</span> <span class="n">pt</span><span class="p">),</span> <span class="n">gamma</span><span class="p">)</span> <span class="o">*</span> <span class="n">logpt</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">size_average</span><span class="p">:</span>
<span class="n">loss</span> <span class="o">=</span> <span class="n">loss</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">loss</span> <span class="o">=</span> <span class="n">loss</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span>
<span class="k">return</span> <span class="n">loss</span></div></div>
<div class="viewcode-block" id="uniq"><a class="viewcode-back" href="../../index.html#pathflowai.losses.uniq">[docs]</a><span class="k">def</span> <span class="nf">uniq</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">)</span> <span class="o">-></span> <span class="n">Set</span><span class="p">:</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/utils.py"""</span>
<span class="k">return</span> <span class="nb">set</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">unique</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">cpu</span><span class="p">())</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span></div>
<div class="viewcode-block" id="sset"><a class="viewcode-back" href="../../index.html#pathflowai.losses.sset">[docs]</a><span class="k">def</span> <span class="nf">sset</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">sub</span><span class="p">:</span> <span class="n">Iterable</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/utils.py"""</span>
<span class="k">return</span> <span class="n">uniq</span><span class="p">(</span><span class="n">a</span><span class="p">)</span><span class="o">.</span><span class="n">issubset</span><span class="p">(</span><span class="n">sub</span><span class="p">)</span></div>
<div class="viewcode-block" id="eq"><a class="viewcode-back" href="../../index.html#pathflowai.losses.eq">[docs]</a><span class="k">def</span> <span class="nf">eq</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/utils.py"""</span>
<span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">eq</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">all</span><span class="p">()</span></div>
<div class="viewcode-block" id="simplex"><a class="viewcode-back" href="../../index.html#pathflowai.losses.simplex">[docs]</a><span class="k">def</span> <span class="nf">simplex</span><span class="p">(</span><span class="n">t</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/utils.py"""</span>
<span class="n">_sum</span> <span class="o">=</span> <span class="n">t</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">axis</span><span class="p">)</span><span class="o">.</span><span class="n">type</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
<span class="n">_ones</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">ones_like</span><span class="p">(</span><span class="n">_sum</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
<span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">allclose</span><span class="p">(</span><span class="n">_sum</span><span class="p">,</span> <span class="n">_ones</span><span class="p">)</span></div>
<div class="viewcode-block" id="one_hot"><a class="viewcode-back" href="../../index.html#pathflowai.losses.one_hot">[docs]</a><span class="k">def</span> <span class="nf">one_hot</span><span class="p">(</span><span class="n">t</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/utils.py"""</span>
<span class="k">return</span> <span class="n">simplex</span><span class="p">(</span><span class="n">t</span><span class="p">,</span> <span class="n">axis</span><span class="p">)</span> <span class="ow">and</span> <span class="n">sset</span><span class="p">(</span><span class="n">t</span><span class="p">,</span> <span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">])</span></div>
<div class="viewcode-block" id="class2one_hot"><a class="viewcode-back" href="../../index.html#pathflowai.losses.class2one_hot">[docs]</a><span class="k">def</span> <span class="nf">class2one_hot</span><span class="p">(</span><span class="n">seg</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">C</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tensor</span><span class="p">:</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/utils.py"""</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">seg</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span> <span class="c1"># Only w, h, used by the dataloader</span>
<span class="n">seg</span> <span class="o">=</span> <span class="n">seg</span><span class="o">.</span><span class="n">unsqueeze</span><span class="p">(</span><span class="n">dim</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">sset</span><span class="p">(</span><span class="n">seg</span><span class="p">,</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">C</span><span class="p">)))</span>
<span class="n">b</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">seg</span><span class="o">.</span><span class="n">shape</span> <span class="c1"># type: Tuple[int, int, int]</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">([</span><span class="n">seg</span> <span class="o">==</span> <span class="n">c</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">C</span><span class="p">)],</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span><span class="o">.</span><span class="n">type</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">int32</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">res</span><span class="o">.</span><span class="n">shape</span> <span class="o">==</span> <span class="p">(</span><span class="n">b</span><span class="p">,</span> <span class="n">C</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">h</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">one_hot</span><span class="p">(</span><span class="n">res</span><span class="p">)</span>
<span class="k">return</span> <span class="n">res</span></div>
<div class="viewcode-block" id="one_hot2dist"><a class="viewcode-back" href="../../index.html#pathflowai.losses.one_hot2dist">[docs]</a><span class="k">def</span> <span class="nf">one_hot2dist</span><span class="p">(</span><span class="n">seg</span><span class="p">:</span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">)</span> <span class="o">-></span> <span class="n">np</span><span class="o">.</span><span class="n">ndarray</span><span class="p">:</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/utils.py"""</span>
<span class="k">assert</span> <span class="n">one_hot</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">(</span><span class="n">seg</span><span class="p">),</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="n">C</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">seg</span><span class="p">)</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros_like</span><span class="p">(</span><span class="n">seg</span><span class="p">)</span>
<span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">C</span><span class="p">):</span>
<span class="n">posmask</span> <span class="o">=</span> <span class="n">seg</span><span class="p">[</span><span class="n">c</span><span class="p">]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">bool</span><span class="p">)</span>
<span class="k">if</span> <span class="n">posmask</span><span class="o">.</span><span class="n">any</span><span class="p">():</span>
<span class="n">negmask</span> <span class="o">=</span> <span class="o">~</span><span class="n">posmask</span>
<span class="n">res</span><span class="p">[</span><span class="n">c</span><span class="p">]</span> <span class="o">=</span> <span class="n">distance</span><span class="p">(</span><span class="n">negmask</span><span class="p">)</span> <span class="o">*</span> <span class="n">negmask</span> <span class="o">-</span> <span class="p">(</span><span class="n">distance</span><span class="p">(</span><span class="n">posmask</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="n">posmask</span>
<span class="k">return</span> <span class="n">res</span></div>
<div class="viewcode-block" id="SurfaceLoss"><a class="viewcode-back" href="../../index.html#pathflowai.losses.SurfaceLoss">[docs]</a><span class="k">class</span> <span class="nc">SurfaceLoss</span><span class="p">():</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/losses.py"""</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="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="c1"># Self.idc is used to filter out some classes of the target mask. Use fancy indexing</span>
<span class="bp">self</span><span class="o">.</span><span class="n">idc</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="n">kwargs</span><span class="p">[</span><span class="s2">"idc"</span><span class="p">]</span>
<span class="nb">print</span><span class="p">(</span><span class="n">f</span><span class="s2">"Initialized </span><span class="si">{self.__class__.__name__}</span><span class="s2"> with </span><span class="si">{kwargs}</span><span class="s2">"</span><span class="p">)</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">probs</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">dist_maps</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">_</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tensor</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">simplex</span><span class="p">(</span><span class="n">probs</span><span class="p">)</span>
<span class="k">assert</span> <span class="ow">not</span> <span class="n">one_hot</span><span class="p">(</span><span class="n">dist_maps</span><span class="p">)</span>
<span class="n">pc</span> <span class="o">=</span> <span class="n">probs</span><span class="p">[:,</span> <span class="bp">self</span><span class="o">.</span><span class="n">idc</span><span class="p">,</span> <span class="o">...</span><span class="p">]</span><span class="o">.</span><span class="n">type</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
<span class="n">dc</span> <span class="o">=</span> <span class="n">dist_maps</span><span class="p">[:,</span> <span class="bp">self</span><span class="o">.</span><span class="n">idc</span><span class="p">,</span> <span class="o">...</span><span class="p">]</span><span class="o">.</span><span class="n">type</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
<span class="n">multipled</span> <span class="o">=</span> <span class="n">einsum</span><span class="p">(</span><span class="s2">"bcwh,bcwh->bcwh"</span><span class="p">,</span> <span class="n">pc</span><span class="p">,</span> <span class="n">dc</span><span class="p">)</span>
<span class="n">loss</span> <span class="o">=</span> <span class="n">multipled</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="k">return</span> <span class="n">loss</span></div>
<div class="viewcode-block" id="GeneralizedDice"><a class="viewcode-back" href="../../index.html#pathflowai.losses.GeneralizedDice">[docs]</a><span class="k">class</span> <span class="nc">GeneralizedDice</span><span class="p">():</span>
<span class="sd">"""https://raw.githubusercontent.com/LIVIAETS/surface-loss/master/losses.py"""</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="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="c1"># Self.idc is used to filter out some classes of the target mask. Use fancy indexing</span>
<span class="bp">self</span><span class="o">.</span><span class="n">idc</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="n">kwargs</span><span class="p">[</span><span class="s2">"idc"</span><span class="p">]</span>
<span class="nb">print</span><span class="p">(</span><span class="n">f</span><span class="s2">"Initialized </span><span class="si">{self.__class__.__name__}</span><span class="s2"> with </span><span class="si">{kwargs}</span><span class="s2">"</span><span class="p">)</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">probs</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">target</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">_</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">)</span> <span class="o">-></span> <span class="n">Tensor</span><span class="p">:</span>
<span class="k">assert</span> <span class="n">simplex</span><span class="p">(</span><span class="n">probs</span><span class="p">)</span> <span class="ow">and</span> <span class="n">simplex</span><span class="p">(</span><span class="n">target</span><span class="p">)</span>
<span class="n">pc</span> <span class="o">=</span> <span class="n">probs</span><span class="p">[:,</span> <span class="bp">self</span><span class="o">.</span><span class="n">idc</span><span class="p">,</span> <span class="o">...</span><span class="p">]</span><span class="o">.</span><span class="n">type</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
<span class="n">tc</span> <span class="o">=</span> <span class="n">target</span><span class="p">[:,</span> <span class="bp">self</span><span class="o">.</span><span class="n">idc</span><span class="p">,</span> <span class="o">...</span><span class="p">]</span><span class="o">.</span><span class="n">type</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span>
<span class="n">w</span><span class="p">:</span> <span class="n">Tensor</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">/</span> <span class="p">((</span><span class="n">einsum</span><span class="p">(</span><span class="s2">"bcwh->bc"</span><span class="p">,</span> <span class="n">tc</span><span class="p">)</span><span class="o">.</span><span class="n">type</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float32</span><span class="p">)</span> <span class="o">+</span> <span class="mf">1e-10</span><span class="p">)</span> <span class="o">**</span> <span class="mi">2</span><span class="p">)</span>
<span class="n">intersection</span><span class="p">:</span> <span class="n">Tensor</span> <span class="o">=</span> <span class="n">w</span> <span class="o">*</span> <span class="n">einsum</span><span class="p">(</span><span class="s2">"bcwh,bcwh->bc"</span><span class="p">,</span> <span class="n">pc</span><span class="p">,</span> <span class="n">tc</span><span class="p">)</span>
<span class="n">union</span><span class="p">:</span> <span class="n">Tensor</span> <span class="o">=</span> <span class="n">w</span> <span class="o">*</span> <span class="p">(</span><span class="n">einsum</span><span class="p">(</span><span class="s2">"bcwh->bc"</span><span class="p">,</span> <span class="n">pc</span><span class="p">)</span> <span class="o">+</span> <span class="n">einsum</span><span class="p">(</span><span class="s2">"bcwh->bc"</span><span class="p">,</span> <span class="n">tc</span><span class="p">))</span>
<span class="n">divided</span><span class="p">:</span> <span class="n">Tensor</span> <span class="o">=</span> <span class="mi">1</span> <span class="o">-</span> <span class="mi">2</span> <span class="o">*</span> <span class="p">(</span><span class="n">einsum</span><span class="p">(</span><span class="s2">"bc->b"</span><span class="p">,</span> <span class="n">intersection</span><span class="p">)</span> <span class="o">+</span> <span class="mf">1e-10</span><span class="p">)</span> <span class="o">/</span> <span class="p">(</span><span class="n">einsum</span><span class="p">(</span><span class="s2">"bc->b"</span><span class="p">,</span> <span class="n">union</span><span class="p">)</span> <span class="o">+</span> <span class="mf">1e-10</span><span class="p">)</span>
<span class="n">loss</span> <span class="o">=</span> <span class="n">divided</span><span class="o">.</span><span class="n">mean</span><span class="p">()</span>
<span class="k">return</span> <span class="n">loss</span></div>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
© Copyright 2019, Joshua Levy
</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>
Datasets
Models
