mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-10-30 10:18:50 +08:00
1047 lines
98 KiB
HTML
1047 lines
98 KiB
HTML
<!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="画像認識(ResNet)のための深層残差学習(ResNet)のPyTorch実装/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&v=4"/>
|
||
<meta name="twitter:title" content="画像認識のための深層残差学習 (ResNet)"/>
|
||
<meta name="twitter:description" content="画像認識(ResNet)のための深層残差学習(ResNet)のPyTorch実装/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/resnet/index.html"/>
|
||
<meta property="og:title" content="画像認識のための深層残差学習 (ResNet)"/>
|
||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||
<meta property="og:site_name" content="画像認識のための深層残差学習 (ResNet)"/>
|
||
<meta property="og:type" content="object"/>
|
||
<meta property="og:title" content="画像認識のための深層残差学習 (ResNet)"/>
|
||
<meta property="og:description" content="画像認識(ResNet)のための深層残差学習(ResNet)のPyTorch実装/チュートリアル。"/>
|
||
|
||
<title>画像認識のための深層残差学習 (ResNet)</title>
|
||
<link rel="shortcut icon" href="/icon.png"/>
|
||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||
<link rel="canonical" href="https://nn.labml.ai/resnet/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">resnet</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/resnet/__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>画像認識のための深層残差学習 (ResNet)</h1>
|
||
<p>これは、「<a href="https://papers.labml.ai/paper/1512.03385">画像認識のための深層残差学習</a>」<a href="https://pytorch.org">という論文をPyTorchで実装したものです</a>。</p>
|
||
<p><em>ResNetは劣化の問題を克服するために層を残差関数として学習させます</em>。劣化の問題は、層の数が非常に多くなると、ディープニューラルネットワークの精度が低下することです。レイヤーの数が増えると精度が上がり、飽和し、劣化が始まります</p>。
|
||
<p>この論文では、余分な層はアイデンティティマッピングの実行方法を学習するだけでよいため、より深いモデルは少なくとも浅いモデルと同様に機能すべきだと主張しています。</p>
|
||
<h2>残余学習</h2>
|
||
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqh" style=""><span class="mord mathcal" style="margin-right:0.00965em">H</span><span class="mopen" style="">(</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mclose" style="">)</span></span></span></span></span></span>数層で学習する必要があるマッピングであれば、残差関数をトレーニングします</p>
|
||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqg" style=""><span class="mord" style=""><span class="mord coloredeq eqj" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span><span class="mopen" style="">(</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mclose" style="">)</span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqh" style=""><span class="mord mathcal" style="margin-right:0.00965em">H</span><span class="mopen" style="">(</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mclose" style="">)</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">−</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span></span></p>
|
||
<p>代わりに。そして本来の機能は次のようになります<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqg" style=""><span class="mord" style=""><span class="mord coloredeq eqj" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span><span class="mopen" style="">(</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mclose" style="">)</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span>。</p>
|
||
<p>この場合、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqh" style=""><span class="mord mathcal" style="margin-right:0.00965em">H</span><span class="mopen" style="">(</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mclose" style="">)</span></span></span></span></span></span>アイデンティティマッピングの学習は、「<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqg" style=""><span class="mord" style=""><span class="mord coloredeq eqj" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span><span class="mopen" style="">(</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mclose" style="">)</span></span></span></span></span></span>なりたい」ことを学ぶことと同じで<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>、学習しやすくなります。</p>
|
||
<p>パラメータ化された形式では、次のように記述できます。</p>
|
||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord coloredeq eqj" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span><span class="mopen" style="">(</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mpunct" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mopen" style="">{</span><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.31166399999999994em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">i</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose" style="">})</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span></span></p>
|
||
<p>また、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqj" style=""><span class="mord" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span><span class="mopen">(</span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="mord"><span class="mord mathnormal" style="margin-right:0.13889em;">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.31166399999999994em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">i</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span>特徴マップのサイズとが異なる場合は、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.83333em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqn" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">s</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span></span>学習した重みを使用して線形投影を行うことを提案しています。</p>
|
||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqb" style=""><span class="mord" style=""><span class="mord coloredeq eqd" style=""><span class="mord coloredeq eqj" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span><span class="mopen coloredeq eqd" style="">(</span><span class="mord coloredeq eqd" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mpunct coloredeq eqd" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mopen coloredeq eqd" style="">{</span><span class="mord coloredeq eqd" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.31166399999999994em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">i</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose coloredeq eqd" style="">})</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 eqm" style=""><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">s</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span><span class="mord coloredeq eqm" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span></span></span></span></span></span></span></span></p>
|
||
<p>Paper では、線形投影の代わりにゼロパディングを試したところ、線形投影の方が効果的であることがわかりました。また、フィーチャマップのサイズが一致する場合、線形投影よりもアイデンティティマッピングの方が優れていることがわかりました</p>。
|
||
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.68333em;vertical-align:0em;"></span><span class="mord coloredeq eqj" style=""><span class="mord" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span></span></span></span></span>複数のレイヤーが必要です。そうでない場合、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqb" style=""><span class="mord" style=""><span class="mord coloredeq eqd" style=""><span class="mord coloredeq eqj" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span><span class="mopen coloredeq eqd" style="">(</span><span class="mord coloredeq eqd" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mpunct coloredeq eqd" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mopen coloredeq eqd" style="">{</span><span class="mord coloredeq eqd" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.31166399999999994em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">i</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose coloredeq eqd" style="">})</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 eqm" style=""><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">s</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span><span class="mord coloredeq eqm" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span></span></span></span></span></span></span>合計にも非線形性がなく、線形レイヤーのようになります。</p>
|
||
<p><a href="experiment.html">CIFAR-10でResNetをトレーニングするためのトレーニングコードは次のとおりです</a>。</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">55</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span><span class="p">,</span> <span class="n">Optional</span>
|
||
<span class="lineno">56</span>
|
||
<span class="lineno">57</span><span class="kn">import</span> <span class="nn">torch</span>
|
||
<span class="lineno">58</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||
<span class="lineno">59</span>
|
||
<span class="lineno">60</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</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>
|
||
<h2>ショートカット接続用の線形投影</h2>
|
||
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.83333em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqm" style=""><span class="mord" style=""><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">s</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span></span></span></span></span></span>これは上記の投影を行います。</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">63</span><span class="k">class</span> <span class="nc">ShortcutProjection</span><span class="p">(</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>
|
||
は内のチャンネル数 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span></li>
|
||
<li><code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
は内のチャンネル数 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord coloredeq eqj" style=""><span class="mord mathcal coloredeq eqr" style="margin-right:0.09931em">F</span></span></span><span class="mopen" style="">(</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span><span class="mpunct" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mopen" style="">{</span><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.31166399999999994em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">i</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose" style="">})</span></span></span></span></span></span></li>
|
||
<li><code class="highlight"><span></span><span class="n">stride</span></code>
|
||
はの畳み込み演算におけるストライドの長さです。<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.68333em;vertical-align:0em;"></span><span class="mord coloredeq eqr" style=""><span class="mord mathnormal" style="margin-right:0.13889em">F</span></span></span></span></span></span>フィーチャマップのサイズに合わせて、ショートカット接続でも同じ手順を実行します</li></ul>。
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">70</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="n">stride</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">77</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>線形投影用のコンボリューションレイヤー <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.83333em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqm" style=""><span class="mord" style=""><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">s</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span></span></span></span></span></span></p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">80</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="n">stride</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-5'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-5'>#</a>
|
||
</div>
|
||
<p>論文では、各畳み込み演算の後にバッチ正規化を追加することを提案しています</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">82</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">)</span></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">84</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>コンボリューションとバッチ正規化</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">86</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv</span><span class="p">(</span><span class="n">x</span><span class="p">))</span></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>
|
||
<p><a id="residual_block"></a></p>
|
||
<h2>残余ブロック</h2>
|
||
<p>これは、論文で説明した残留ブロックを実装したものです。<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 eql" 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>畳み込み層が 2 つあります</p>。
|
||
<p><img alt="Residual Block" src="residual_block.svg"></p>
|
||
<p><code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
最初の畳み込み層は<code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
、<code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
からにマッピングされます。この方が、<code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
特徴マップのサイズを小さくしてストライドの長さがより大きくなる場合よりも大きくなります。<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 eqp" style=""><span class="mord" style="">1</span></span></span></span></span></span></p>
|
||
<p>2 <code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
<code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
番目の畳み込み層はからにマップされ、ストライドの長さは常に 1 です。</p>
|
||
<p>両方の畳み込み層の後にバッチ正規化が行われます。</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">89</span><span class="k">class</span> <span class="nc">ResidualBlock</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-9'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-9'>#</a>
|
||
</div>
|
||
<ul><li><code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
は内のチャンネル数 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span></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><li><code class="highlight"><span></span><span class="n">stride</span></code>
|
||
はコンボリューション演算のストライドの長さです。</li>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">110</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="n">stride</span><span class="p">:</span> <span class="nb">int</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>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">116</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-11'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-11'>#</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 eql" 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>最初の畳み込みレイヤー、これは次のようにマッピングされます <code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">119</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="n">stride</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-12'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-12'>#</a>
|
||
</div>
|
||
<p>最初の畳み込み後のバッチ正規化</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">121</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">out_channels</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>
|
||
<p>最初のアクティベーション機能 (ReLU)</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">123</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-14'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-14'>#</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 eql" 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">126</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-15'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-15'>#</a>
|
||
</div>
|
||
<p>2 回目の畳み込み後のバッチ正規化</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">128</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-16'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-16'>#</a>
|
||
</div>
|
||
<p>ショートカットの接続は、ストライドの長さが合わない場合はプロジェクションにしてください。<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 eqp" style=""><span class="mord" style="">1</span></span></span></span></span></span>チャンネル数が変わると</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">132</span> <span class="k">if</span> <span class="n">stride</span> <span class="o">!=</span> <span class="mi">1</span> <span class="ow">or</span> <span class="n">in_channels</span> <span class="o">!=</span> <span class="n">out_channels</span><span class="p">:</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-17'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-17'>#</a>
|
||
</div>
|
||
<p>プロジェクション <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.83333em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqm" style=""><span class="mord" style=""><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">s</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span></span></span></span></span></span></p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">134</span> <span class="bp">self</span><span class="o">.</span><span class="n">shortcut</span> <span class="o">=</span> <span class="n">ShortcutProjection</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">stride</span><span class="p">)</span>
|
||
<span class="lineno">135</span> <span class="k">else</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>アイデンティティ <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span></p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">137</span> <span class="bp">self</span><span class="o">.</span><span class="n">shortcut</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Identity</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>2 回目の起動機能 (ReLU) (ショートカット追加後)</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">140</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-20'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-20'>#</a>
|
||
</div>
|
||
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
|
||
形状の入力です <code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">in_channels</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">]</span></code>
|
||
</li></ul>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">142</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-21'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-21'>#</a>
|
||
</div>
|
||
<p>ショートカット接続を取得</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">147</span> <span class="n">shortcut</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">shortcut</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-22'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-22'>#</a>
|
||
</div>
|
||
<p>最初のコンボリューションとアクティベーション</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">149</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="bp">self</span><span class="o">.</span><span class="n">bn1</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv1</span><span class="p">(</span><span class="n">x</span><span class="p">)))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-23'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-23'>#</a>
|
||
</div>
|
||
<p>2 回目の畳み込み</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">151</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn2</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv2</span><span class="p">(</span><span class="n">x</span><span class="p">))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-24'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-24'>#</a>
|
||
</div>
|
||
<p>ショートカット追加後のアクティベーション機能</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">153</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="o">+</span> <span class="n">shortcut</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-25'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-25'>#</a>
|
||
</div>
|
||
<p><a id="bottleneck_residual_block"></a></p>
|
||
<h2>ボトルネック残留ブロック</h2>
|
||
<p>これにより、論文で説明されているボトルネックブロックが実装されます。<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 eqk" style=""><span class="mord" style=""><span class="mord coloredeq eqp" 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 eqp" style="">1</span></span></span></span></span></span></span>、<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 eql" 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>、<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 eqk" style=""><span class="mord" style=""><span class="mord coloredeq eqp" 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 eqp" style="">1</span></span></span></span></span></span></span>および畳み込み層があります</p>。
|
||
<p><img alt="Bottlenext Block" src="bottleneck_block.svg"></p>
|
||
<p>最初の畳み込み層は、<code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
<code class="highlight"><span></span><span class="n">bottleneck_channels</span></code>
|
||
<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 eqk" style=""><span class="mord" style=""><span class="mord coloredeq eqp" 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 eqp" style="">1</span></span></span></span></span></span></span>からへの畳み込みでマッピングされます。ここで、<code class="highlight"><span></span><span class="n">bottleneck_channels</span></code>
|
||
はよりも低くなります。<code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
</p>
|
||
<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 eql" 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> <code class="highlight"><span></span><span class="n">bottleneck_channels</span></code>
|
||
番目の畳み込み層はからにマップされます。<code class="highlight"><span></span><span class="n">bottleneck_channels</span></code>
|
||
これにより、<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 eqp" style=""><span class="mord" style="">1</span></span></span></span></span></span>フィーチャマップのサイズを圧縮したい場合よりもストライドの長さが大きくなる可能性があります</p>。
|
||
<p>3 <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 eqk" style=""><span class="mord" style=""><span class="mord coloredeq eqp" 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 eqp" style="">1</span></span></span></span></span></span></span> 番目の最後の畳み込み層はにマッピングされます。<code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
<code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
<code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
ストライドの長さがより大きい場合よりも大きく、<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 eqp" style=""><span class="mord" style="">1</span></span></span></span></span></span><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.84444em;vertical-align:-0.15em;"></span><span class="mord mathnormal">o</span><span class="mord mathnormal">u</span><span class="mord"><span class="mord mathnormal">t</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">c</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mord mathnormal">hann</span><span class="mord mathnormal">e</span><span class="mord mathnormal" style="margin-right:0.01968em;">l</span><span class="mord mathnormal">s</span></span></span></span></span>それ以外の場合はと等しい</p>。<code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
|
||
<p><code class="highlight"><span></span><span class="n">bottleneck_channels</span></code>
|
||
<code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
がよりも小さく、<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 eql" 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>畳み込みがこの縮小されたスペースで実行されます(したがってボトルネックになります)。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 eqk" style=""><span class="mord" style=""><span class="mord coloredeq eqp" 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 eqp" style="">1</span></span></span></span></span></span></span> つの畳み込みによってチャネル数が減少し、増加します</p>。
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">156</span><span class="k">class</span> <span class="nc">BottleneckResidualBlock</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-26'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-26'>#</a>
|
||
</div>
|
||
<ul><li><code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||
は内のチャンネル数 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span></li>
|
||
<li><code class="highlight"><span></span><span class="n">bottleneck_channels</span></code>
|
||
<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 eql" 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>はコンボリューションのチャネル数です</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><li><code class="highlight"><span></span><span class="n">stride</span></code>
|
||
<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 eql" 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>はコンボリューション演算のストライドの長さです。</li>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">184</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">bottleneck_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="n">stride</span><span class="p">:</span> <span class="nb">int</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>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">191</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-28'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-28'>#</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 eqk" style=""><span class="mord" style=""><span class="mord coloredeq eqp" 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 eqp" style="">1</span></span></span></span></span></span></span>最初の畳み込みレイヤー、これは次のようにマッピングされます <code class="highlight"><span></span><span class="n">bottleneck_channels</span></code>
|
||
</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">194</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">bottleneck_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> <span class="n">stride</span><span class="o">=</span><span class="mi">1</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>最初の畳み込み後のバッチ正規化</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">196</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">bottleneck_channels</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>最初のアクティベーション機能 (ReLU)</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">198</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-31'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-31'>#</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 eql" 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">201</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">bottleneck_channels</span><span class="p">,</span> <span class="n">bottleneck_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">stride</span><span class="o">=</span><span class="n">stride</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-32'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-32'>#</a>
|
||
</div>
|
||
<p>2 回目の畳み込み後のバッチ正規化</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">203</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">bottleneck_channels</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>2 番目のアクティベーション機能 (ReLU)</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">205</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-34'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-34'>#</a>
|
||
</div>
|
||
<p>3 <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 eqk" style=""><span class="mord" style=""><span class="mord coloredeq eqp" 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 eqp" style="">1</span></span></span></span></span></span></span> 番目の畳み込み層、これはにマップされます。<code class="highlight"><span></span><span class="n">out_channels</span></code>
|
||
</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">208</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv3</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">bottleneck_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">1</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</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>2 回目の畳み込み後のバッチ正規化</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">210</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn3</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">out_channels</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-36'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-36'>#</a>
|
||
</div>
|
||
<p>ショートカットの接続は、ストライドの長さが合わない場合はプロジェクションにしてください。<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 eqp" style=""><span class="mord" style="">1</span></span></span></span></span></span>チャンネル数が変わると</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">214</span> <span class="k">if</span> <span class="n">stride</span> <span class="o">!=</span> <span class="mi">1</span> <span class="ow">or</span> <span class="n">in_channels</span> <span class="o">!=</span> <span class="n">out_channels</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>プロジェクション <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.83333em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqm" style=""><span class="mord" style=""><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.13889em">W</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.13889em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">s</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span><span class="mord" style=""><span class="mord mathnormal coloredeq eqs" style="">x</span></span></span></span></span></span></span></p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">216</span> <span class="bp">self</span><span class="o">.</span><span class="n">shortcut</span> <span class="o">=</span> <span class="n">ShortcutProjection</span><span class="p">(</span><span class="n">in_channels</span><span class="p">,</span> <span class="n">out_channels</span><span class="p">,</span> <span class="n">stride</span><span class="p">)</span>
|
||
<span class="lineno">217</span> <span class="k">else</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>アイデンティティ <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqs" style=""><span class="mord mathnormal" style="">x</span></span></span></span></span></span></p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">219</span> <span class="bp">self</span><span class="o">.</span><span class="n">shortcut</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Identity</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>2 回目の起動機能 (ReLU) (ショートカット追加後)</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">222</span> <span class="bp">self</span><span class="o">.</span><span class="n">act3</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-40'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-40'>#</a>
|
||
</div>
|
||
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
|
||
形状の入力です <code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">in_channels</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">]</span></code>
|
||
</li></ul>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">224</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-41'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-41'>#</a>
|
||
</div>
|
||
<p>ショートカット接続を取得</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">229</span> <span class="n">shortcut</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">shortcut</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>最初のコンボリューションとアクティベーション</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">231</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="bp">self</span><span class="o">.</span><span class="n">bn1</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv1</span><span class="p">(</span><span class="n">x</span><span class="p">)))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-43'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-43'>#</a>
|
||
</div>
|
||
<p>2 回目のコンボリューションとアクティベーション</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">233</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act2</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bn2</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv2</span><span class="p">(</span><span class="n">x</span><span class="p">)))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-44'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-44'>#</a>
|
||
</div>
|
||
<p>3 番目の畳み込み</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">235</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn3</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv3</span><span class="p">(</span><span class="n">x</span><span class="p">))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-45'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-45'>#</a>
|
||
</div>
|
||
<p>ショートカット追加後のアクティベーション機能</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">237</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">act3</span><span class="p">(</span><span class="n">x</span> <span class="o">+</span> <span class="n">shortcut</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-46'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-46'>#</a>
|
||
</div>
|
||
<h2>リネットモデル</h2>
|
||
<p>これは最後の線形層と分類用のソフトマックスを含まないresnetモデルの基本です。</p>
|
||
<p>再ネットは、<a href="#residual_block"><a href="#bottleneck_residual_block">積み重ねられた残留ブロックまたはボトルネックの残留ブロックで構成されています</a></a>。フィーチャマップのサイズは、ストライドの長さのブロックで数ブロック進むと半分になります。<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 eqq" style=""><span class="mord" style="">2</span></span></span></span></span></span>フィーチャマップのサイズを小さくすると、チャネル数が増えます。最後に、特徴マップを平均してベクトル表現を求めます</p>。
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">240</span><span class="k">class</span> <span class="nc">ResNetBase</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-47'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-47'>#</a>
|
||
</div>
|
||
<ul><li><code class="highlight"><span></span><span class="n">n_blocks</span></code>
|
||
は、各フィーチャマップサイズのブロック数のリストです。</li>
|
||
<li><code class="highlight"><span></span><span class="n">n_channels</span></code>
|
||
は、各フィーチャマップサイズのチャネル数です。</li>
|
||
<li><code class="highlight"><span></span><span class="n">bottlenecks</span></code>
|
||
ボトルネックとなるチャネル数です。その場合<code class="highlight"><span></span><span class="kc">None</span></code>
|
||
、<a href="#residual_block">残留ブロックが使用されます</a></li>。
|
||
<li><code class="highlight"><span></span><span class="n">img_channels</span></code>
|
||
は入力のチャンネル数です。</li>
|
||
<li><code class="highlight"><span></span><span class="n">first_kernel_size</span></code>
|
||
は初期畳み込み層のカーネルサイズ</li></ul>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">254</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">n_blocks</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="n">n_channels</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="lineno">255</span> <span class="n">bottlenecks</span><span class="p">:</span> <span class="n">Optional</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="kc">None</span><span class="p">,</span>
|
||
<span class="lineno">256</span> <span class="n">img_channels</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">3</span><span class="p">,</span> <span class="n">first_kernel_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">7</span><span class="p">):</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-48'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-48'>#</a>
|
||
</div>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">265</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-49'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-49'>#</a>
|
||
</div>
|
||
<p>各フィーチャマップサイズのブロック数とチャネル数</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">268</span> <span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">n_blocks</span><span class="p">)</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="n">n_channels</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-50'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-50'>#</a>
|
||
</div>
|
||
<p><a href="#bottleneck_residual_block">ボトルネックの残留ブロックを使用する場合は</a>、機能マップのサイズごとにボトルネックのチャネル数を指定する必要があります。</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">271</span> <span class="k">assert</span> <span class="n">bottlenecks</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="n">bottlenecks</span><span class="p">)</span> <span class="o">==</span> <span class="nb">len</span><span class="p">(</span><span class="n">n_channels</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-51'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-51'>#</a>
|
||
</div>
|
||
<p>初期畳み込み層は、<code class="highlight"><span></span><span class="n">img_channels</span></code>
|
||
最初の残差ブロックのチャネル数からにマッピングされます () <code class="highlight"><span></span><span class="n">n_channels</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span></code>
|
||
</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">275</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">img_channels</span><span class="p">,</span> <span class="n">n_channels</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
|
||
<span class="lineno">276</span> <span class="n">kernel_size</span><span class="o">=</span><span class="n">first_kernel_size</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="n">first_kernel_size</span> <span class="o">//</span> <span class="mi">2</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-52'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-52'>#</a>
|
||
</div>
|
||
<p>初期畳み込み後のバッチノルム</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">278</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">n_channels</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-53'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-53'>#</a>
|
||
</div>
|
||
<p>ブロック一覧</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">281</span> <span class="n">blocks</span> <span class="o">=</span> <span class="p">[]</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-54'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-54'>#</a>
|
||
</div>
|
||
<p>前のレイヤー (またはブロック) のチャンネル数</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">283</span> <span class="n">prev_channels</span> <span class="o">=</span> <span class="n">n_channels</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-55'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-55'>#</a>
|
||
</div>
|
||
<p>各フィーチャマップサイズをループスループ</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">285</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">channels</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">n_channels</span><span class="p">):</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-56'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-56'>#</a>
|
||
</div>
|
||
<p>新しいフィーチャマップサイズの最初のブロックのストライドの長さは、<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 eqq" style=""><span class="mord" style="">2</span></span></span></span></span></span>一番最初のブロックを除いてです。</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">288</span> <span class="n">stride</span> <span class="o">=</span> <span class="mi">2</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">blocks</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span> <span class="k">else</span> <span class="mi">1</span>
|
||
<span class="lineno">289</span>
|
||
<span class="lineno">290</span> <span class="k">if</span> <span class="n">bottlenecks</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-57'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-57'>#</a>
|
||
</div>
|
||
<p><a href="#residual_block">にマッピングされる残差ブロック</a> <code class="highlight"><span></span><span class="n">prev_channels</span></code>
|
||
<code class="highlight"><span></span><span class="n">channels</span></code>
|
||
</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">292</span> <span class="n">blocks</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">ResidualBlock</span><span class="p">(</span><span class="n">prev_channels</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="n">stride</span><span class="p">))</span>
|
||
<span class="lineno">293</span> <span class="k">else</span><span class="p">:</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-58'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-58'>#</a>
|
||
</div>
|
||
<p><a href="#bottleneck_residual_block">からにマップされるボトルネック残留ブロック</a> <code class="highlight"><span></span><span class="n">prev_channels</span></code>
|
||
<code class="highlight"><span></span><span class="n">channels</span></code>
|
||
</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">296</span> <span class="n">blocks</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">BottleneckResidualBlock</span><span class="p">(</span><span class="n">prev_channels</span><span class="p">,</span> <span class="n">bottlenecks</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">channels</span><span class="p">,</span>
|
||
<span class="lineno">297</span> <span class="n">stride</span><span class="o">=</span><span class="n">stride</span><span class="p">))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-59'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-59'>#</a>
|
||
</div>
|
||
<p>チャンネル数を変更</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">300</span> <span class="n">prev_channels</span> <span class="o">=</span> <span class="n">channels</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-60'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-60'>#</a>
|
||
</div>
|
||
<p>残りのブロックを追加-フィーチャマップのサイズやチャンネルは変更なし</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">302</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="n">n_blocks</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span><span class="p">):</span>
|
||
<span class="lineno">303</span> <span class="k">if</span> <span class="n">bottlenecks</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-61'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-61'>#</a>
|
||
</div>
|
||
<p><a href="#residual_block">残留ブロック</a></p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">305</span> <span class="n">blocks</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">ResidualBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span>
|
||
<span class="lineno">306</span> <span class="k">else</span><span class="p">:</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-62'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-62'>#</a>
|
||
</div>
|
||
<p><a href="#bottleneck_residual_block">ボトルネックの残留ブロック</a></p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">308</span> <span class="n">blocks</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">BottleneckResidualBlock</span><span class="p">(</span><span class="n">channels</span><span class="p">,</span> <span class="n">bottlenecks</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">channels</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-63'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-63'>#</a>
|
||
</div>
|
||
<p>ブロックを積み重ねよう</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">311</span> <span class="bp">self</span><span class="o">.</span><span class="n">blocks</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span><span class="o">*</span><span class="n">blocks</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-64'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-64'>#</a>
|
||
</div>
|
||
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
|
||
形がある <code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">img_channels</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">]</span></code>
|
||
</li></ul>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">313</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-65'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-65'>#</a>
|
||
</div>
|
||
<p>初期畳み込みとバッチ正規化</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">319</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">bn</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv</span><span class="p">(</span><span class="n">x</span><span class="p">))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-66'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-66'>#</a>
|
||
</div>
|
||
<p>残り (またはボトルネック) ブロック</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">321</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">blocks</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-67'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-67'>#</a>
|
||
</div>
|
||
<p><code class="highlight"><span></span><span class="n">x</span></code>
|
||
<code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span><span class="p">]</span></code>
|
||
形状を次のように変更 <code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">h</span> <span class="o">*</span> <span class="n">w</span><span class="p">]</span></code>
|
||
</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">323</span> <span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">view</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">0</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">1</span><span class="p">],</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-68'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-68'>#</a>
|
||
</div>
|
||
<p>グローバルアベレージプーリング</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">325</span> <span class="k">return</span> <span class="n">x</span><span class="o">.</span><span class="n">mean</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='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> |