Files
Varuna Jayasiri 2038b11d29 ja translation
2023-05-10 17:00:29 -04:00

501 lines
99 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

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="長短期記憶 (LSTM) モジュールの簡単な 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&amp;v=4"/>
<meta name="twitter:title" content="長期短期記憶 (LSTM)"/>
<meta name="twitter:description" content="長短期記憶 (LSTM) モジュールの簡単な 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/lstm/index.html"/>
<meta property="og:title" content="長期短期記憶 (LSTM)"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="長期短期記憶 (LSTM)"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="長期短期記憶 (LSTM)"/>
<meta property="og:description" content="長短期記憶 (LSTM) モジュールの簡単な PyTorch 実装/チュートリアル。"/>
<title>長期短期記憶 (LSTM)</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/lstm/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">lstm</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/lstm/__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>長期短期記憶 (LSTM)</h1>
<p><a href="https://pytorch.org">これは長短期記憶のPyTorch実装です</a></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">12</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Tuple</span>
<span class="lineno">13</span>
<span class="lineno">14</span><span class="kn">import</span> <span class="nn">torch</span>
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
<span class="lineno">16</span>
<span class="lineno">17</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>長短期メモリーセル</h2>
<p>LSTM セルが計算し、<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 eqv" style=""><span class="mord mathnormal" style="">c</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:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</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:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqv" style=""><span class="mord mathnormal" style="">c</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:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span></span></span></span></span>長期記憶のようなもので、短期記憶のようなものです。<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 eqbb" style=""><span class="mord mathnormal" style="">x</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:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span></span></span></span></span>入力とを使用して長期記憶を更新します。今回のアップデートでは、<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 eqv" style=""><span class="mord mathnormal" style="">c</span></span></span></span></span></span>一部のフィーチャはフォーゲートゲートでクリアされ<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqw" style=""><span class="mord mathnormal" style="margin-right:0.10764em">f</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:0.65952em;vertical-align:0em;"></span><span class="mord coloredeq eqz" style=""><span class="mord mathnormal" style="">i</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:0.625em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqx" style=""><span class="mord mathnormal" style="margin-right:0.03588em">g</span></span></span></span></span></span>一部のフィーチャはゲート経由で追加されます</p>
<p>新しい短期記憶は、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eqp" style=""><span class="mop" style=""><span style="">t</span><span style="">a</span><span style="">n</span><span style="">h</span></span></span></span></span></span></span>長期記憶に出力ゲートを掛けたものです。<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqba" style=""><span class="mord mathnormal" style="">o</span></span></span></span></span></span></p>
<p><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 eqv" style=""><span class="mord mathnormal" style="">c</span></span></span></span></span></span>更新を行うとき、セルは長期記憶を見ないことに注意してください。変更するだけです。また、<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 eqv" style=""><span class="mord mathnormal" style="">c</span></span></span></span></span></span>線形変換を行うこともありません。これがグラデーションの消失と爆発を解消するものです</p>
<p>更新ルールは次のとおりです。</p>
<span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:3.0000000000000004em;vertical-align:-1.2500000000000002em;"></span><span class="mord"><span class="mtable"><span class="col-align-r"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.7500000000000002em;"><span style="top:-3.91em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq eqq" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqv" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 style="top:-2.41em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord"><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</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 class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:1.2500000000000002em;"><span></span></span></span></span></span><span class="col-align-l"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.7500000000000002em;"><span style="top:-3.91em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord"></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">σ</span><span class="mopen">(</span><span class="mord coloredeq eqr" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqw" style="margin-right:0.10764em">f</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 class="mord coloredeq eqo" style=""><span class="mord" style=""></span></span><span class="mord"><span class="mord coloredeq eqv" style=""><span class="mord mathnormal" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">t</span><span class="mbin mtight"></span><span class="mord mtight">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></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 class="mord mathnormal" style="margin-right:0.03588em;">σ</span><span class="mopen">(</span><span class="mord coloredeq eqt" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 class="mord coloredeq eqo" style=""><span class="mord" style=""></span></span><span class="mord coloredeq eqp" style=""><span class="mop" style=""><span style="">t</span><span style="">a</span><span style="">n</span><span style="">h</span></span></span><span class="mopen">(</span><span class="mord coloredeq eqs" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqx" style="margin-right:0.03588em">g</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 style="top:-2.41em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord"></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">σ</span><span class="mopen">(</span><span class="mord coloredeq equ" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqba" style="">o</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 class="mord coloredeq eqo" style=""><span class="mord" style=""></span></span><span class="mord coloredeq eqp" style=""><span class="mop" style=""><span style="">t</span><span style="">a</span><span style="">n</span><span style="">h</span></span></span><span class="mopen">(</span><span class="mord coloredeq eqq" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqv" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:1.2500000000000002em;"><span></span></span></span></span></span></span></span></span></span></span></span></span><p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.66666em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqo" style=""><span class="mord" style=""></span></span></span></span></span></span>要素ごとの乗算の略です。</p>
<p>中間値とゲートは、隠れ状態と入力の線形変換として計算されます。</p>
<span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:6.16168em;vertical-align:-2.8308399999999994em;"></span><span class="mord"><span class="mtable"><span class="col-align-r"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:3.3308400000000002em;"><span style="top:-5.456176em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq eqt" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 style="top:-3.829160000000001em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq eqr" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqw" style="margin-right:0.10764em">f</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 style="top:-2.3291600000000003em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq eqs" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqx" style="margin-right:0.03588em">g</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 style="top:-0.8291600000000008em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq equ" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqba" style="">o</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:2.8308399999999994em;"><span></span></span></span></span></span><span class="col-align-l"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:3.3308400000000002em;"><span style="top:-5.456176em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord"></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mord coloredeq eqm" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8746639999999999em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqbb" style="">x</span></span></span></span><span style="top:-3.113em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqz" style="">i</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"><span class="mord coloredeq eqbb" style=""><span class="mord mathnormal" style="">x</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</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">)</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord coloredeq eqi" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8746639999999999em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqy" style="">h</span></span></span></span><span style="top:-3.113em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqz" style="">i</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">t</span><span class="mbin mtight"></span><span class="mord mtight">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span><span style="top:-3.829160000000001em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord"></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mord coloredeq eqk" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8991079999999998em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqbb" style="">x</span></span></span></span><span style="top:-3.1130000000000004em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqw" style="margin-right:0.10764em">f</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"><span class="mord coloredeq eqbb" style=""><span class="mord mathnormal" style="">x</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</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">)</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.9670159999999998em;"><span style="top:-2.3986920000000005em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqy" style="">h</span></span></span></span><span style="top:-3.180908em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqw" style="margin-right:0.10764em">f</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.3013079999999999em;"><span></span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">t</span><span class="mbin mtight"></span><span class="mord mtight">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span><span style="top:-2.3291600000000003em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord"></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.7143919999999999em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqbb" style="">x</span></span></span></span><span style="top:-3.1130000000000004em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqx" style="margin-right:0.03588em">g</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"><span class="mord coloredeq eqbb" style=""><span class="mord mathnormal" style="">x</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</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">)</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord coloredeq eqh" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.7822999999999999em;"><span style="top:-2.3986920000000005em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqy" style="">h</span></span></span></span><span style="top:-3.180908em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqx" style="margin-right:0.03588em">g</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.3013079999999999em;"><span></span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">t</span><span class="mbin mtight"></span><span class="mord mtight">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span><span style="top:-0.8291600000000008em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord"></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">=</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.7143919999999999em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqbb" style="">x</span></span></span></span><span style="top:-3.113em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqba" style="">o</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"><span class="mord coloredeq eqbb" style=""><span class="mord mathnormal" style="">x</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</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">)</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.7143919999999999em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqy" style="">h</span></span></span></span><span style="top:-3.113em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqba" style="">o</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></span></span></span><span class="mopen">(</span><span class="mord"><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">t</span><span class="mbin mtight"></span><span class="mord mtight">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:2.8308399999999994em;"><span></span></span></span></span></span></span></span></span></span></span></span></span>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">20</span><span class="k">class</span> <span class="nc">LSTMCell</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'>
<div class='section-link'>
<a href='#section-2'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">57</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">input_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">layer_norm</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span>
<span class="lineno">58</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-3'>
<div class='docs'>
<div class='section-link'>
<a href='#section-3'>#</a>
</div>
<p>これらは、<code class="highlight"><span></span><span class="nb">input</span></code>
<code class="highlight"><span></span><span class="n">hidden</span></code>
およびベクトルを変換する線形レイヤーです。そのうちの 1 つは、変換を追加するのでバイアスを必要としません</p>
</div>
<div class='code'>
<div class="highlight"><pre></pre></div>
</div>
</div>
<div class='section' id='section-4'>
<div class='docs'>
<div class='section-link'>
<a href='#section-4'>#</a>
</div>
<p>これにより<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.071664em;vertical-align:-0.247em;"></span><span class="mord coloredeq eqm" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.824664em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqbb" style="">x</span></span></span></span><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqz" style="">i</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></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:1.0961079999999999em;vertical-align:-0.247em;"></span><span class="mord coloredeq eqk" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.8491079999999999em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqbb" style="">x</span></span></span></span><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqw" style="margin-right:0.10764em">f</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></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:0.9414399999999999em;vertical-align:-0.247em;"></span><span class="mord coloredeq eql" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.664392em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqbb" style="">x</span></span></span></span><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqx" style="margin-right:0.03588em">g</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></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:0.9414399999999999em;vertical-align:-0.247em;"></span><span class="mord coloredeq eqn" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.664392em;"><span style="top:-2.4530000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqbb" style="">x</span></span></span></span><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqba" style="">o</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.247em;"><span></span></span></span></span></span></span></span></span></span></span></span>変換が組み合わされます。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">64</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_lin</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span> <span class="mi">4</span> <span class="o">*</span> <span class="n">hidden_size</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>これにより<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.1077719999999998em;vertical-align:-0.2831079999999999em;"></span><span class="mord coloredeq eqi" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.824664em;"><span style="top:-2.4168920000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqy" style="">h</span></span></span></span><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqz" style="">i</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.2831079999999999em;"><span></span></span></span></span></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:1.2683239999999998em;vertical-align:-0.3013079999999999em;"></span><span class="mord coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.9670159999999999em;"><span style="top:-2.3986920000000005em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqy" style="">h</span></span></span></span><span style="top:-3.1809080000000005em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqw" style="margin-right:0.10764em">f</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.3013079999999999em;"><span></span></span></span></span></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:1.083608em;vertical-align:-0.3013079999999999em;"></span><span class="mord coloredeq eqh" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.7823em;"><span style="top:-2.3986920000000005em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqy" style="">h</span></span></span></span><span style="top:-3.1809080000000005em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqx" style="margin-right:0.03588em">g</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.3013079999999999em;"><span></span></span></span></span></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:0.9775479999999999em;vertical-align:-0.2831079999999999em;"></span><span class="mord coloredeq eqj" style=""><span class="mord mathnormal" style="margin-right:0.01968em">l</span><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="mord" style=""><span class="mord mathnormal" style="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.664392em;"><span style="top:-2.4168920000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqy" style="">h</span></span></span></span><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqba" style="">o</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.2831079999999999em;"><span></span></span></span></span></span></span></span></span></span></span></span>変換が組み合わされます。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">66</span> <span class="bp">self</span><span class="o">.</span><span class="n">input_lin</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">input_size</span><span class="p">,</span> <span class="mi">4</span> <span class="o">*</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</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>
<p>レイヤー正規化を適用するかどうか。</p>
<p>レイヤーの正規化を適用すると、より良い結果が得られます。<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.65952em;vertical-align:0em;"></span><span class="mord coloredeq eqz" style=""><span class="mord mathnormal" style="">i</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:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqw" style=""><span class="mord mathnormal" style="margin-right:0.10764em">f</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:0.625em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqx" style=""><span class="mord mathnormal" style="margin-right:0.03588em">g</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:0.43056em;vertical-align:0em;"></span><span class="mord coloredeq eqba" style=""><span class="mord mathnormal" style="">o</span></span></span></span></span></span>および埋め込みは正規化され、次の形式で正規化されます <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqq" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqv" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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> <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"><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</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="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 equ" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqba" style="">o</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 eqo" style=""><span class="mord" style=""></span></span><span class="mord coloredeq eqp" style=""><span class="mop" style=""><span style="">t</span><span style="">a</span><span style="">n</span><span style="">h</span></span></span><span class="mopen">(</span><span class="mop"><span class="mord mathnormal">L</span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span></span><span class="mopen">(</span><span class="mord coloredeq eqq" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqv" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">73</span> <span class="k">if</span> <span class="n">layer_norm</span><span class="p">:</span>
<span class="lineno">74</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_norm</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">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">(</span><span class="n">hidden_size</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>
<span class="lineno">75</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_norm_c</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">)</span>
<span class="lineno">76</span> <span class="k">else</span><span class="p">:</span>
<span class="lineno">77</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_norm</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">nn</span><span class="o">.</span><span class="n">Identity</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>
<span class="lineno">78</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_norm_c</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-7'>
<div class='docs'>
<div class='section-link'>
<a href='#section-7'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">80</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">h</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">c</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-8'>
<div class='docs'>
<div class='section-link'>
<a href='#section-8'>#</a>
</div>
<p>、、の線形変換は<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.80952em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqt" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqr" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqw" style="margin-right:0.10764em">f</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqs" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqx" style="margin-right:0.03588em">g</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq equ" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqba" style="">o</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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>同じ線形層を使用して計算します。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">83</span> <span class="n">ifgo</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_lin</span><span class="p">(</span><span class="n">h</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">input_lin</span><span class="p">(</span><span class="n">x</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>
<p>各レイヤーは 4 <code class="highlight"><span></span><span class="n">hidden_size</span></code>
倍の出力を生成し、それらを分割します</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">85</span> <span class="n">ifgo</span> <span class="o">=</span> <span class="n">ifgo</span><span class="o">.</span><span class="n">chunk</span><span class="p">(</span><span class="mi">4</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-10'>
<div class='docs'>
<div class='section-link'>
<a href='#section-10'>#</a>
</div>
<p>レイヤーの正規化を適用(元の用紙には使用しないが、より良い結果になる)</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">88</span> <span class="n">ifgo</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">layer_norm</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">ifgo</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</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-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></span><span class="mord coloredeq eqt" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqr" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqw" style="margin-right:0.10764em">f</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq eqs" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqx" style="margin-right:0.03588em">g</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord coloredeq equ" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqba" style="">o</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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></span></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">91</span> <span class="n">i</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">g</span><span class="p">,</span> <span class="n">o</span> <span class="o">=</span> <span class="n">ifgo</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><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqq" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqv" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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="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 mathnormal" style="margin-right:0.03588em;">σ</span><span class="mopen">(</span><span class="mord coloredeq eqr" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqw" style="margin-right:0.10764em">f</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 class="mord coloredeq eqo" style=""><span class="mord" style=""></span></span><span class="mord"><span class="mord coloredeq eqv" style=""><span class="mord mathnormal" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">t</span><span class="mbin mtight"></span><span class="mord mtight">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></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:1em;vertical-align:-0.25em;"></span><span class="mord mathnormal" style="margin-right:0.03588em;">σ</span><span class="mopen">(</span><span class="mord coloredeq eqt" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqz" style="">i</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 class="mord coloredeq eqo" style=""><span class="mord" style=""></span></span><span class="mord coloredeq eqp" style=""><span class="mop" style=""><span style="">t</span><span style="">a</span><span style="">n</span><span style="">h</span></span></span><span class="mopen">(</span><span class="mord coloredeq eqs" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqx" style="margin-right:0.03588em">g</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">94</span> <span class="n">c_next</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="n">f</span><span class="p">)</span> <span class="o">*</span> <span class="n">c</span> <span class="o">+</span> <span class="n">torch</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">tanh</span><span class="p">(</span><span class="n">g</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><span ><span class="katex-display"><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"><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</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="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 mathnormal" style="margin-right:0.03588em;">σ</span><span class="mopen">(</span><span class="mord coloredeq equ" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqba" style="">o</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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 class="mord coloredeq eqo" style=""><span class="mord" style=""></span></span><span class="mord coloredeq eqp" style=""><span class="mop" style=""><span style="">t</span><span style="">a</span><span style="">n</span><span style="">h</span></span></span><span class="mopen">(</span><span class="mord coloredeq eqq" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqv" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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>オプションでレイヤーノルムを適用 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqq" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqv" style="">c</span></span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;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="">t</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></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">98</span> <span class="n">h_next</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="n">o</span><span class="p">)</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">tanh</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">layer_norm_c</span><span class="p">(</span><span class="n">c_next</span><span class="p">))</span>
<span class="lineno">99</span>
<span class="lineno">100</span> <span class="k">return</span> <span class="n">h_next</span><span class="p">,</span> <span class="n">c_next</span></pre></div>
</div>
</div>
<div class='section' id='section-14'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-14'>#</a>
</div>
<h2>マルチレイヤーLSTM</h2>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">103</span><span class="k">class</span> <span class="nc">LSTM</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-15'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-15'>#</a>
</div>
<p>LSTM <code class="highlight"><span></span><span class="n">n_layers</span></code>
のネットワークを作成します。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">108</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">input_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_layers</span><span class="p">:</span> <span class="nb">int</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>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">113</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
<span class="lineno">114</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_layers</span> <span class="o">=</span> <span class="n">n_layers</span>
<span class="lineno">115</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</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>レイヤーごとにセルを作成します。最初のレイヤーだけが直接入力を取得することに注意してください。残りのレイヤーは、下のレイヤーから入力を取得します</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">118</span> <span class="bp">self</span><span class="o">.</span><span class="n">cells</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">LSTMCell</span><span class="p">(</span><span class="n">input_size</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">)]</span> <span class="o">+</span>
<span class="lineno">119</span> <span class="p">[</span><span class="n">LSTMCell</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span> <span class="n">hidden_size</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="n">n_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)])</span></pre></div>
</div>
</div>
<div class='section' id='section-18'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-18'>#</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">n_steps</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">input_size</span><span class="p">]</span></code>
<code class="highlight"><span></span><span class="n">state</span></code>
<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span></span></span></span></span>の形状はとが組み合わさったもので<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 eqv" style=""><span class="mord mathnormal" style="">c</span></span></span></span></span></span><code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">]</span></code>
それぞれの形状はです。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">121</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">state</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Tuple</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">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</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>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">126</span> <span class="n">n_steps</span><span class="p">,</span> <span class="n">batch_size</span> <span class="o">=</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></pre></div>
</div>
</div>
<div class='section' id='section-20'>
<div class='docs'>
<div class='section-link'>
<a href='#section-20'>#</a>
</div>
<p>次の場合にステートを初期化します <code class="highlight"><span></span><span class="kc">None</span></code>
</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">129</span> <span class="k">if</span> <span class="n">state</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="lineno">130</span> <span class="n">h</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">new_zeros</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</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="bp">self</span><span class="o">.</span><span class="n">n_layers</span><span class="p">)]</span>
<span class="lineno">131</span> <span class="n">c</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">new_zeros</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</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="bp">self</span><span class="o">.</span><span class="n">n_layers</span><span class="p">)]</span>
<span class="lineno">132</span> <span class="k">else</span><span class="p">:</span>
<span class="lineno">133</span> <span class="p">(</span><span class="n">h</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span> <span class="o">=</span> <span class="n">state</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>テンソルを逆に積み重ねて各レイヤーの状態を取得します</p>
<p>📝 テンソル自体で作業することもできますが、デバッグは簡単です</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">137</span> <span class="n">h</span><span class="p">,</span> <span class="n">c</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">unbind</span><span class="p">(</span><span class="n">h</span><span class="p">)),</span> <span class="nb">list</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">unbind</span><span class="p">(</span><span class="n">c</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>各タイムステップで最終レイヤーの出力を収集する配列。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">140</span> <span class="n">out</span> <span class="o">=</span> <span class="p">[]</span>
<span class="lineno">141</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_steps</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>最初のレイヤーへの入力は入力そのものです</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">143</span> <span class="n">inp</span> <span class="o">=</span> <span class="n">x</span><span class="p">[</span><span class="n">t</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>レイヤーをループする</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">145</span> <span class="k">for</span> <span class="n">layer</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_layers</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>レイヤーの状態を取得</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">147</span> <span class="n">h</span><span class="p">[</span><span class="n">layer</span><span class="p">],</span> <span class="n">c</span><span class="p">[</span><span class="n">layer</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cells</span><span class="p">[</span><span class="n">layer</span><span class="p">](</span><span class="n">inp</span><span class="p">,</span> <span class="n">h</span><span class="p">[</span><span class="n">layer</span><span class="p">],</span> <span class="n">c</span><span class="p">[</span><span class="n">layer</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>次のレイヤーへの入力は、このレイヤーの状態です</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">149</span> <span class="n">inp</span> <span class="o">=</span> <span class="n">h</span><span class="p">[</span><span class="n">layer</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord coloredeq eqy" style=""><span class="mord mathnormal" style="">h</span></span></span></span></span></span>最終レイヤーの出力を集める</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">151</span> <span class="n">out</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">h</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-28'>
<div class='docs'>
<div class='section-link'>
<a href='#section-28'>#</a>
</div>
<p>出力とステートを積み重ねる</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">154</span> <span class="n">out</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">out</span><span class="p">)</span>
<span class="lineno">155</span> <span class="n">h</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">h</span><span class="p">)</span>
<span class="lineno">156</span> <span class="n">c</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">c</span><span class="p">)</span>
<span class="lineno">157</span>
<span class="lineno">158</span> <span class="k">return</span> <span class="n">out</span><span class="p">,</span> <span class="p">(</span><span class="n">h</span><span class="p">,</span> <span class="n">c</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>