learning/annotated_deep_learning_paper_implementations
1
0
Fork 0
mirror of https://github.com/labmlai/annotated_deep_learning_paper_implementations.git synced 2025-08-16 10:51:23 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
annotated_deep_learning_pap…/docs/ja/unet/index.html
Varuna Jayasiri 2038b11d29 ja translation
2023-05-10 17:00:29 -04:00

669 lines
47 KiB
HTML
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!DOCTYPE html>
<html lang="ja">
<head>
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
<meta name="description" content="PyTorchの実装とU-Netモデルのチュートリアル。"/>
<meta name="twitter:card" content="summary"/>
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta name="twitter:title" content="ユーネット"/>
<meta name="twitter:description" content="PyTorchの実装とU-Netモデルのチュートリアル。"/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/unet/index.html"/>
<meta property="og:title" content="ユーネット"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="ユーネット"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="ユーネット"/>
<meta property="og:description" content="PyTorchの実装とU-Netモデルのチュートリアル。"/>
<title>ユーネット</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/unet/index.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.18/dist/katex.min.css" integrity="sha384-zTROYFVGOfTw7JV7KUu8udsvW2fx4lWOsCEDqhBreBwlHI4ioVRtmIvEThzJHGET" crossorigin="anonymous">
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag() {
dataLayer.push(arguments);
}
gtag('js', new Date());
gtag('config', 'G-4V3HC8HBLH');
</script>
</head>
<body>
<div id='container'>
<div id="background"></div>
<div class='section'>
<div class='docs'>
<p>
<a class="parent" href="/">home</a>
<a class="parent" href="index.html">unet</a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
<img alt="Github"
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
style="max-width:100%;"/></a>
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
<img alt="Twitter"
src="https://img.shields.io/twitter/follow/labmlai?style=social"
style="max-width:100%;"/></a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/unet/__init__.py" target="_blank">
View code on Github</a>
</p>
</div>
</div>
<div class='section' id='section-0'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-0'>#</a>
</div>
<h1>ユーネット</h1>
<p>これは、論文「U-Net<a href="https://papers.labml.ai/paper/1505.04597">: 生物医学画像セグメンテーションのための畳み込みネットワーク」のU-Netモデルの実装です</a>。</p>
<p>U-Netは収縮経路と拡張経路で構成されています。収縮経路は一連の畳み込み層とプーリング層であり、特徴マップの解像度は徐々に低下します。エクスパンシブパスとは、フィーチャマップの解像度が徐々に上がっていく一連のアップサンプリングレイヤーと畳み込みレイヤーのことです</p>。
<p>拡張パスの各ステップで、縮小パスからの対応するフィーチャマップが現在のフィーチャマップと連結されます。</p>
<p><img alt="U-Net diagram from paper" src="unet.png"></p>
<p>これは、<a href="experiment.html"><a href="carvana.html">CarvanaデータセットでU-Netをトレーニングする実験のトレーニングコードです</a></a>。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">27</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
<span class="lineno">28</span><span class="kn">import</span> <span class="nn">torchvision.transforms.functional</span>
<span class="lineno">29</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span></pre></div>
</div>
</div>
<div class='section' id='section-1'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-1'>#</a>
</div>
<h3>2 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">3</span></span></span></span></span></span> つのコンボリューションレイヤー</h3>
<p>収縮経路と膨張経路の各ステップには、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">3</span></span></span></span></span></span> 2つの畳み込み層があり、その後にReLU活性化が続きます。</p>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">0</span></span></span></span></span>U-Netの論文ではパディングを使用していましたが、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqf" style=""><span class="mord" style="">1</span></span></span></span></span></span>最終的なフィーチャマップがトリミングされないようにパディングを使用しています。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">32</span><span class="k">class</span> <span class="nc">DoubleConvolution</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-2'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-2'>#</a>
</div>
<ul><li><code class="highlight"><span></span><span class="n">in_channels</span></code>
は入力チャンネル数</li>
<li><code class="highlight"><span></span><span class="n">out_channels</span></code>
は出力チャンネル数</li></ul>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">43</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">in_channels</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-3'>
<div class='docs'>
<div class='section-link'>
<a href='#section-3'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">48</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-4'>
<div class='docs'>
<div class='section-link'>
<a href='#section-4'>#</a>
</div>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">3</span></span></span></span></span></span>最初の畳み込み層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">51</span> <span class="bp">self</span><span class="o">.</span><span class="n">first</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="lineno">52</span> <span class="bp">self</span><span class="o">.</span><span class="n">act1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-5'>
<div class='docs'>
<div class='section-link'>
<a href='#section-5'>#</a>
</div>
<p>2 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">3</span></span></span></span></span></span> 番目の畳み込み層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">54</span> <span class="bp">self</span><span class="o">.</span><span class="n">second</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
<span class="lineno">55</span> <span class="bp">self</span><span class="o">.</span><span class="n">act2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-6'>
<div class='docs'>
<div class='section-link'>
<a href='#section-6'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">57</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-7'>
<div class='docs'>
<div class='section-link'>
<a href='#section-7'>#</a>
</div>
<p>2 つのコンボリューションレイヤーとアクティベーションを適用します。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">59</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">first</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="lineno">60</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="lineno">61</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">second</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
<span class="lineno">62</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">act2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-8'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-8'>#</a>
</div>
<h3>ダウンサンプル</h3>
<p>収縮パスの各ステップは、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqb" style=""><span class="mord" style="">2</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">2</span></span></span></span></span></span>最大プーリングレイヤーを使用して特徴マップをダウンサンプリングします。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">65</span><span class="k">class</span> <span class="nc">DownSample</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-9'>
<div class='docs'>
<div class='section-link'>
<a href='#section-9'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">73</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="lineno">74</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-10'>
<div class='docs'>
<div class='section-link'>
<a href='#section-10'>#</a>
</div>
<p>最大プーリング層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">76</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2d</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-11'>
<div class='docs'>
<div class='section-link'>
<a href='#section-11'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">78</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span>
<span class="lineno">79</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-12'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-12'>#</a>
</div>
<h3>アップサンプル</h3>
<p>広大な経路の各ステップは、アップコンボリューションで特徴マップをアップサンプリングします。<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqb" style=""><span class="mord" style="">2</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">2</span></span></span></span></span></span></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">82</span><span class="k">class</span> <span class="nc">UpSample</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-13'>
<div class='docs'>
<div class='section-link'>
<a href='#section-13'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">89</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">in_channels</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
<span class="lineno">90</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-14'>
<div class='docs'>
<div class='section-link'>
<a href='#section-14'>#</a>
</div>
<p>アップコンボリューション</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">93</span> <span class="bp">self</span><span class="o">.</span><span class="n">up</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ConvTranspose2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-15'>
<div class='docs'>
<div class='section-link'>
<a href='#section-15'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">95</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span>
<span class="lineno">96</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">up</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-16'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-16'>#</a>
</div>
<h3>フィーチャマップのトリミングと連結</h3>
<p>拡張パスの各ステップで、縮小パスからの対応するフィーチャマップが現在のフィーチャマップと連結されます。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">99</span><span class="k">class</span> <span class="nc">CropAndConcat</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-17'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-17'>#</a>
</div>
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
エクスパンシブパス内の現在のフィーチャマップ</li>
<li><code class="highlight"><span></span><span class="n">contracting_x</span></code>
契約経路からの対応する機能マップ</li></ul>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">106</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">contracting_x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-18'>
<div class='docs'>
<div class='section-link'>
<a href='#section-18'>#</a>
</div>
<p>フィーチャマップを縮小パスから現在のフィーチャマップのサイズにトリミングします</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">113</span> <span class="n">contracting_x</span> <span class="o">=</span> <span class="n">torchvision</span><span class="o">.</span><span class="n">transforms</span><span class="o">.</span><span class="n">functional</span><span class="o">.</span><span class="n">center_crop</span><span class="p">(</span><span class="n">contracting_x</span><span class="p">,</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">2</span><span class="p">],</span> <span class="n">x</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">3</span><span class="p">]])</span></pre></div>
</div>
</div>
<div class='section' id='section-19'>
<div class='docs'>
<div class='section-link'>
<a href='#section-19'>#</a>
</div>
<p>フィーチャマップを連結する</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">115</span> <span class="n">x</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">([</span><span class="n">x</span><span class="p">,</span> <span class="n">contracting_x</span><span class="p">],</span> <span class="n">dim</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-20'>
<div class='docs'>
<div class='section-link'>
<a href='#section-20'>#</a>
</div>
<p></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">117</span> <span class="k">return</span> <span class="n">x</span></pre></div>
</div>
</div>
<div class='section' id='section-21'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-21'>#</a>
</div>
<h2>ユーネット</h2>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">120</span><span class="k">class</span> <span class="nc">UNet</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-22'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-22'>#</a>
</div>
<ul><li><code class="highlight"><span></span><span class="n">in_channels</span></code>
入力画像のチャンネル数</li>
<li><code class="highlight"><span></span><span class="n">out_channels</span></code>
結果フィーチャマップのチャネル数</li></ul>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">124</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">in_channels</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-23'>
<div class='docs'>
<div class='section-link'>
<a href='#section-23'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">129</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-24'>
<div class='docs'>
<div class='section-link'>
<a href='#section-24'>#</a>
</div>
<p>収縮経路用の二重畳み込み層。<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">64</span></span></span></span></span>から始まる各ステップで機能の数が 2 倍になります</p>。
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">133</span> <span class="bp">self</span><span class="o">.</span><span class="n">down_conv</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span><span class="n">DoubleConvolution</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">o</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">o</span> <span class="ow">in</span>
<span class="lineno">134</span> <span class="p">[(</span><span class="n">in_channels</span><span class="p">,</span> <span class="mi">64</span><span class="p">),</span> <span class="p">(</span><span class="mi">64</span><span class="p">,</span> <span class="mi">128</span><span class="p">),</span> <span class="p">(</span><span class="mi">128</span><span class="p">,</span> <span class="mi">256</span><span class="p">),</span> <span class="p">(</span><span class="mi">256</span><span class="p">,</span> <span class="mi">512</span><span class="p">)]])</span></pre></div>
</div>
</div>
<div class='section' id='section-25'>
<div class='docs'>
<div class='section-link'>
<a href='#section-25'>#</a>
</div>
<p>収縮経路用のダウンサンプリング層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">136</span> <span class="bp">self</span><span class="o">.</span><span class="n">down_sample</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span><span class="n">DownSample</span><span class="p">()</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">)])</span></pre></div>
</div>
</div>
<div class='section' id='section-26'>
<div class='docs'>
<div class='section-link'>
<a href='#section-26'>#</a>
</div>
<p>最も低い解像度の 2 つの畳み込み層 (U の下部)。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">139</span> <span class="bp">self</span><span class="o">.</span><span class="n">middle_conv</span> <span class="o">=</span> <span class="n">DoubleConvolution</span><span class="p">(</span><span class="mi">512</span><span class="p">,</span> <span class="mi">1024</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-27'>
<div class='docs'>
<div class='section-link'>
<a href='#section-27'>#</a>
</div>
<p>広大な経路のサンプリングレイヤーをアップサンプリング。アップサンプリングを行うと、機能の数は半分になります</p>。
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">143</span> <span class="bp">self</span><span class="o">.</span><span class="n">up_sample</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span><span class="n">UpSample</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">o</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">o</span> <span class="ow">in</span>
<span class="lineno">144</span> <span class="p">[(</span><span class="mi">1024</span><span class="p">,</span> <span class="mi">512</span><span class="p">),</span> <span class="p">(</span><span class="mi">512</span><span class="p">,</span> <span class="mi">256</span><span class="p">),</span> <span class="p">(</span><span class="mi">256</span><span class="p">,</span> <span class="mi">128</span><span class="p">),</span> <span class="p">(</span><span class="mi">128</span><span class="p">,</span> <span class="mi">64</span><span class="p">)]])</span></pre></div>
</div>
</div>
<div class='section' id='section-28'>
<div class='docs'>
<div class='section-link'>
<a href='#section-28'>#</a>
</div>
<p>膨張経路用の二重畳み込み層。それらの入力は、現在のフィーチャマップと縮小パスからのフィーチャマップを連結したものです。したがって、入力フィーチャの数は、アップサンプリングによるフィーチャ数の2倍になります</p>。
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">149</span> <span class="bp">self</span><span class="o">.</span><span class="n">up_conv</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span><span class="n">DoubleConvolution</span><span class="p">(</span><span class="n">i</span><span class="p">,</span> <span class="n">o</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">o</span> <span class="ow">in</span>
<span class="lineno">150</span> <span class="p">[(</span><span class="mi">1024</span><span class="p">,</span> <span class="mi">512</span><span class="p">),</span> <span class="p">(</span><span class="mi">512</span><span class="p">,</span> <span class="mi">256</span><span class="p">),</span> <span class="p">(</span><span class="mi">256</span><span class="p">,</span> <span class="mi">128</span><span class="p">),</span> <span class="p">(</span><span class="mi">128</span><span class="p">,</span> <span class="mi">64</span><span class="p">)]])</span></pre></div>
</div>
</div>
<div class='section' id='section-29'>
<div class='docs'>
<div class='section-link'>
<a href='#section-29'>#</a>
</div>
<p>レイヤーをトリミングして連結すると、広大なパスが作れます。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">152</span> <span class="bp">self</span><span class="o">.</span><span class="n">concat</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span><span class="n">CropAndConcat</span><span class="p">()</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">)])</span></pre></div>
</div>
</div>
<div class='section' id='section-30'>
<div class='docs'>
<div class='section-link'>
<a href='#section-30'>#</a>
</div>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord coloredeq eqf" style="">1</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style=""><span class="mord coloredeq eqf" style="">1</span></span></span></span></span></span></span>出力を生成する最後の畳み込み層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">154</span> <span class="bp">self</span><span class="o">.</span><span class="n">final_conv</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">64</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-31'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-31'>#</a>
</div>
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
入力画像</li></ul>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">156</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-32'>
<div class='docs'>
<div class='section-link'>
<a href='#section-32'>#</a>
</div>
<p>縮小パスの出力を収集して、後で拡張パスと連結できるようにします。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">161</span> <span class="n">pass_through</span> <span class="o">=</span> <span class="p">[]</span></pre></div>
</div>
</div>
<div class='section' id='section-33'>
<div class='docs'>
<div class='section-link'>
<a href='#section-33'>#</a>
</div>
<p>契約経路</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">163</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">down_conv</span><span class="p">)):</span></pre></div>
</div>
</div>
<div class='section' id='section-34'>
<div class='docs'>
<div class='section-link'>
<a href='#section-34'>#</a>
</div>
<p>2 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">3</span></span></span></span></span></span> つの畳み込み層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">165</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">down_conv</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-35'>
<div class='docs'>
<div class='section-link'>
<a href='#section-35'>#</a>
</div>
<p>アウトプットを収集</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">167</span> <span class="n">pass_through</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-36'>
<div class='docs'>
<div class='section-link'>
<a href='#section-36'>#</a>
</div>
<p>ダウンサンプル</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">169</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">down_sample</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-37'>
<div class='docs'>
<div class='section-link'>
<a href='#section-37'>#</a>
</div>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">3</span></span></span></span></span></span>U-Netの下部にある2つの畳み込み層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">172</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">middle_conv</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-38'>
<div class='docs'>
<div class='section-link'>
<a href='#section-38'>#</a>
</div>
<p>広大な道</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">175</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">up_conv</span><span class="p">)):</span></pre></div>
</div>
</div>
<div class='section' id='section-39'>
<div class='docs'>
<div class='section-link'>
<a href='#section-39'>#</a>
</div>
<p>アップサンプル</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">177</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">up_sample</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-40'>
<div class='docs'>
<div class='section-link'>
<a href='#section-40'>#</a>
</div>
<p>コントラクトパスの出力を連結する</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">179</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">concat</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">x</span><span class="p">,</span> <span class="n">pass_through</span><span class="o">.</span><span class="n">pop</span><span class="p">())</span></pre></div>
</div>
</div>
<div class='section' id='section-41'>
<div class='docs'>
<div class='section-link'>
<a href='#section-41'>#</a>
</div>
<p>2 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style="">3</span></span></span></span></span></span> つの畳み込み層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">181</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">up_conv</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-42'>
<div class='docs'>
<div class='section-link'>
<a href='#section-42'>#</a>
</div>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord coloredeq eqf" style="">1</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin" style="">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord" style=""><span class="mord coloredeq eqf" style="">1</span></span></span></span></span></span></span>最終畳み込み層</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">184</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">final_conv</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-43'>
<div class='docs'>
<div class='section-link'>
<a href='#section-43'>#</a>
</div>
<p></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">187</span> <span class="k">return</span> <span class="n">x</span></pre></div>
</div>
</div>
<div class='footer'>
<a href="https://papers.labml.ai">Trending Research Papers</a>
<a href="https://labml.ai">labml.ai</a>
</div>
</div>
<script src=../interactive.js?v=1"></script>
<script>
function handleImages() {
var images = document.querySelectorAll('p>img')
for (var i = 0; i < images.length; ++i) {
handleImage(images[i])
}
}
function handleImage(img) {
img.parentElement.style.textAlign = 'center'
var modal = document.createElement('div')
modal.id = 'modal'
var modalContent = document.createElement('div')
modal.appendChild(modalContent)
var modalImage = document.createElement('img')
modalContent.appendChild(modalImage)
var span = document.createElement('span')
span.classList.add('close')
span.textContent = 'x'
modal.appendChild(span)
img.onclick = function () {
console.log('clicked')
document.body.appendChild(modal)
modalImage.src = img.src
}
span.onclick = function () {
document.body.removeChild(modal)
}
}
handleImages()
</script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink