wehub/labmlai--annotated_deep_learning_paper_implementations
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 12:19:01 +08:00
commit 3b90d1192f
2172 changed files with 594509 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/ja/adaptive_computation/index.html
+129
View File
@@ -0,0 +1,129 @@
<!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="適応型計算に関連するPyTorch実装/チュートリアルのセット"/>
<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="適応型計算を備えたニューラルネットワーク"/>
<meta name="twitter:description" content="適応型計算に関連するPyTorch実装/チュートリアルのセット"/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/adaptive_computation/index.html"/>
<meta property="og:title" content="適応型計算を備えたニューラルネットワーク"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="適応型計算を備えたニューラルネットワーク"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="適応型計算を備えたニューラルネットワーク"/>
<meta property="og:description" content="適応型計算に関連するPyTorch実装/チュートリアルのセット"/>
<title>適応型計算を備えたニューラルネットワーク</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/adaptive_computation/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">adaptive_computation</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/adaptive_computation/__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>適応型計算を備えたニューラルネットワーク</h1>
<p>これらは、入力サンプルの複雑さに基づいて計算の複雑さを変更するニューラルネットワークアーキテクチャです。</p>
<ul><li>🚧 TODO: リカレントニューラルネットワークの適応型計算時間</li>
<li><a href="ponder_net/index.html">PonderNet: 熟考することを学ぶ</a></li></ul>
</div>
<div class='code'>
<div class="highlight"><pre></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>
docs/ja/adaptive_computation/parity.html
+277
View File
@@ -0,0 +1,277 @@
<!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="これにより、論文「リカレントニューラルネットワークの適応的計算時間」からパリティタスクのデータが作成されます。"/>
<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="パリティタスク"/>
<meta name="twitter:description" content="これにより、論文「リカレントニューラルネットワークの適応的計算時間」からパリティタスクのデータが作成されます。"/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/adaptive_computation/parity.html"/>
<meta property="og:title" content="パリティタスク"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="パリティタスク"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="パリティタスク"/>
<meta property="og:description" content="これにより、論文「リカレントニューラルネットワークの適応的計算時間」からパリティタスクのデータが作成されます。"/>
<title>パリティタスク</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/adaptive_computation/parity.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">adaptive_computation</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/adaptive_computation/parity.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>パリティタスク</h1>
<p>これにより、論文「<a href="https://papers.labml.ai/paper/1603.08983">リカレントニューラルネットワークの適応的計算時間</a>」からパリティタスクのデータが作成されます。</p>
<p>パリティタスクの入力は、と <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style="">−</span><span class="mord" style=""><span class="mord coloredeq eqc" style="">1</span></span></span></span></span></span></span> s <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">0</span></span></span></span></span> <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">1</span></span></span></span></span></span> の付いたベクトルで、出力は s <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">1</span></span></span></span></span></span> のパリティです。s <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">1</span></span></span></span></span></span> の数が奇数の場合は 1、それ以外の場合は 0 です。入力は、<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">1</span></span></span></span></span></span><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style="">−</span><span class="mord" style=""><span class="mord coloredeq eqc" style="">1</span></span></span></span></span></span></span>ベクトル内のランダムな数の要素をまたはのいずれかにすることによって生成されます。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">19</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span>
<span class="lineno">20</span>
<span class="lineno">21</span><span class="kn">import</span> <span class="nn">torch</span>
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">torch.utils.data</span> <span class="kn">import</span> <span class="n">Dataset</span></pre></div>
</div>
</div>
<div class='section' id='section-1'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-1'>#</a>
</div>
<h3>パリティデータセット</h3>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">25</span><span class="k">class</span> <span class="nc">ParityDataset</span><span class="p">(</span><span class="n">Dataset</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-2'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-2'>#</a>
</div>
<ul><li><code class="highlight"><span></span><span class="n">n_samples</span></code>
はサンプル数</li>
<li><code class="highlight"><span></span><span class="n">n_elems</span></code>
は入力ベクトルの要素数です</li></ul>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">30</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">n_samples</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_elems</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">64</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-3'>
<div class='docs'>
<div class='section-link'>
<a href='#section-3'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">35</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_samples</span> <span class="o">=</span> <span class="n">n_samples</span>
<span class="lineno">36</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_elems</span> <span class="o">=</span> <span class="n">n_elems</span></pre></div>
</div>
</div>
<div class='section' id='section-4'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-4'>#</a>
</div>
<p>データセットのサイズ</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">38</span> <span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</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>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">42</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_samples</span></pre></div>
</div>
</div>
<div class='section' id='section-6'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-6'>#</a>
</div>
<p>サンプルを生成</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">44</span> <span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">idx</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-&gt;</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></pre></div>
</div>
</div>
<div class='section' id='section-7'>
<div class='docs'>
<div class='section-link'>
<a href='#section-7'>#</a>
</div>
<p>空のベクトル</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">50</span> <span class="n">x</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">zeros</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">n_elems</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>ゼロ以外の要素の数-<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">1</span></span></span></span></span></span> 要素の数と要素数の間のランダムな数</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">52</span> <span class="n">n_non_zero</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_elems</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="p">(</span><span class="mi">1</span><span class="p">,))</span><span class="o">.</span><span class="n">item</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>0 以外の要素を「」と <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style="">1</span></span></span></span></span></span> <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style="">−</span><span class="mord" style=""><span class="mord coloredeq eqc" style="">1</span></span></span></span></span></span></span>「」で埋める</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">54</span> <span class="n">x</span><span class="p">[:</span><span class="n">n_non_zero</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randint</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="p">(</span><span class="n">n_non_zero</span><span class="p">,))</span> <span class="o">*</span> <span class="mi">2</span> <span class="o">-</span> <span class="mi">1</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>要素をランダムに並べ替える</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">56</span> <span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">randperm</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_elems</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>パリティ</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">59</span> <span class="n">y</span> <span class="o">=</span> <span class="p">(</span><span class="n">x</span> <span class="o">==</span> <span class="mf">1.</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="o">%</span> <span class="mi">2</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></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">62</span> <span class="k">return</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</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>
docs/ja/adaptive_computation/ponder_net/experiment.html
+640
View File
@@ -0,0 +1,640 @@
<!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="このトレインは PonderNet on パリティタスクです"/>
<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="PonderNet パリティタスク実験"/>
<meta name="twitter:description" content="このトレインは PonderNet on パリティタスクです"/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/adaptive_computation/ponder_net/experiment.html"/>
<meta property="og:title" content="PonderNet パリティタスク実験"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="PonderNet パリティタスク実験"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="PonderNet パリティタスク実験"/>
<meta property="og:description" content="このトレインは PonderNet on パリティタスクです"/>
<title>PonderNet パリティタスク実験</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/adaptive_computation/ponder_net/experiment.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">adaptive_computation</a>
<a class="parent" href="index.html">ponder_net</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/adaptive_computation/ponder_net/experiment.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><a href="index.html">PonderNet <a href="../parity.html">パリティタスク実験</a></a></h1>
<p><a href="../parity.html">これはパリティタスクで</a> <a href="index.html">PonderNet</a> をトレーニングします。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">13</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span>
<span class="lineno">14</span>
<span class="lineno">15</span><span class="kn">import</span> <span class="nn">torch</span>
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">torch.utils.data</span> <span class="kn">import</span> <span class="n">DataLoader</span>
<span class="lineno">18</span>
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">tracker</span><span class="p">,</span> <span class="n">experiment</span>
<span class="lineno">20</span><span class="kn">from</span> <span class="nn">labml_helpers.metrics.accuracy</span> <span class="kn">import</span> <span class="n">AccuracyDirect</span>
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml_helpers.train_valid</span> <span class="kn">import</span> <span class="n">SimpleTrainValidConfigs</span><span class="p">,</span> <span class="n">BatchIndex</span>
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">labml_nn.adaptive_computation.parity</span> <span class="kn">import</span> <span class="n">ParityDataset</span>
<span class="lineno">23</span><span class="kn">from</span> <span class="nn">labml_nn.adaptive_computation.ponder_net</span> <span class="kn">import</span> <span class="n">ParityPonderGRU</span><span class="p">,</span> <span class="n">ReconstructionLoss</span><span class="p">,</span> <span class="n">RegularizationLoss</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>
<p><a href="https://docs.labml.ai/api/helpers.html#labml_helpers.train_valid.SimpleTrainValidConfigs">シンプルなトレーニングループによる構成</a></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">26</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">SimpleTrainValidConfigs</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>
<p>エポック数</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">33</span> <span class="n">epochs</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">100</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>エポックあたりのバッチ数</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">35</span> <span class="n">n_batches</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">500</span></pre></div>
</div>
</div>
<div class='section' id='section-4'>
<div class='docs'>
<div class='section-link'>
<a href='#section-4'>#</a>
</div>
<p>バッチサイズ</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">37</span> <span class="n">batch_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">128</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>モデル</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">40</span> <span class="n">model</span><span class="p">:</span> <span class="n">ParityPonderGRU</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.83333em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord mathnormal" style="">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.32833099999999993em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="margin-right:0.00773em">R</span><span class="mord mathnormal mtight" style="">ec</span></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">43</span> <span class="n">loss_rec</span><span class="p">:</span> <span class="n">ReconstructionLoss</span></pre></div>
</div>
</div>
<div class='section' id='section-7'>
<div class='docs'>
<div class='section-link'>
<a href='#section-7'>#</a>
</div>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.969438em;vertical-align:-0.286108em;"></span><span class="mord coloredeq eqe" style=""><span class="mord" style=""><span class="mord mathnormal" style="">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.328331em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="margin-right:0.00773em">R</span><span class="mord mathnormal mtight" style="">e</span><span class="mord mathnormal mtight" 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:0.286108em;"><span></span></span></span></span></span></span></span></span></span></span></span></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">45</span> <span class="n">loss_reg</span><span class="p">:</span> <span class="n">RegularizationLoss</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>入力ベクトルの要素数。<em>デモ用に低く設定しています。そうしないと、トレーニングに時間がかかります。パリティのタスクは簡単そうに見えますが、サンプルを見てパターンを理解するのはかなり難しいです</em></p>。
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">51</span> <span class="n">n_elems</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">8</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>隠れ層 (状態) 内のユニット数</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">53</span> <span class="n">n_hidden</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">64</span></pre></div>
</div>
</div>
<div class='section' id='section-10'>
<div class='docs'>
<div class='section-link'>
<a href='#section-10'>#</a>
</div>
<p>最大ステップ数 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.68333em;vertical-align:0em;"></span><span class="mord mathnormal" style="margin-right:0.10903em;">N</span></span></span></span></span></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">55</span> <span class="n">max_steps</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">20</span></pre></div>
</div>
</div>
<div class='section' id='section-11'>
<div class='docs'>
<div class='section-link'>
<a href='#section-11'>#</a>
</div>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.980548em;vertical-align:-0.286108em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style=""><span class="mord mathnormal" style="">λ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.15139200000000003em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">p</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><span></span></span></span></span></span></span></span></span></span></span></span>幾何分布用 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.036108em;vertical-align:-0.286108em;"></span><span class="mord"><span class="mord mathnormal">p</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.32833099999999993em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">G</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="mopen">(</span><span class="mord coloredeq eqc" style=""><span class="mord" style=""><span class="mord mathnormal" style="">λ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.15139200000000003em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mathnormal mtight" style="">p</span></span></span></span><span class="vlist-s">​</span></span><span class="vlist-r"><span class="vlist" style="height:0.286108em;"><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">58</span> <span class="n">lambda_p</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.2</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>正則化損失係数 <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.969438em;vertical-align:-0.286108em;"></span><span class="mord coloredeq eqe" style=""><span class="mord" style=""><span class="mord mathnormal" style="">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.328331em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="margin-right:0.00773em">R</span><span class="mord mathnormal mtight" style="">e</span><span class="mord mathnormal mtight" 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:0.286108em;"><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 eqf" style=""><span class="mord mathnormal" style="margin-right:0.05278em">β</span></span></span></span></span></span></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">60</span> <span class="n">beta</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</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>標準によるグラデーションクリッピング</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">63</span> <span class="n">grad_norm_clip</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span></pre></div>
</div>
</div>
<div class='section' id='section-14'>
<div class='docs'>
<div class='section-link'>
<a href='#section-14'>#</a>
</div>
<p>トレーニングおよび検証ローダー</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">66</span> <span class="n">train_loader</span><span class="p">:</span> <span class="n">DataLoader</span>
<span class="lineno">67</span> <span class="n">valid_loader</span><span class="p">:</span> <span class="n">DataLoader</span></pre></div>
</div>
</div>
<div class='section' id='section-15'>
<div class='docs'>
<div class='section-link'>
<a href='#section-15'>#</a>
</div>
<p>精度計算ツール</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">70</span> <span class="n">accuracy</span> <span class="o">=</span> <span class="n">AccuracyDirect</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">72</span> <span class="k">def</span> <span class="nf">init</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-17'>
<div class='docs'>
<div class='section-link'>
<a href='#section-17'>#</a>
</div>
<p>インジケータを画面に印刷</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">74</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_scalar</span><span class="p">(</span><span class="s1">&#39;loss.*&#39;</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
<span class="lineno">75</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_scalar</span><span class="p">(</span><span class="s1">&#39;loss_reg.*&#39;</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
<span class="lineno">76</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_scalar</span><span class="p">(</span><span class="s1">&#39;accuracy.*&#39;</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
<span class="lineno">77</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_scalar</span><span class="p">(</span><span class="s1">&#39;steps.*&#39;</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-18'>
<div class='docs'>
<div class='section-link'>
<a href='#section-18'>#</a>
</div>
<p>トレーニングと検証のために、エポックに合わせてそれらを計算するメトリックを設定する必要があります</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">80</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_modules</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">accuracy</span><span class="p">]</span></pre></div>
</div>
</div>
<div class='section' id='section-19'>
<div class='docs'>
<div class='section-link'>
<a href='#section-19'>#</a>
</div>
<p>モデルを初期化</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">83</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span> <span class="o">=</span> <span class="n">ParityPonderGRU</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_elems</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_hidden</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_steps</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</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><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.83333em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord mathnormal" style="">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.32833099999999993em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="margin-right:0.00773em">R</span><span class="mord mathnormal mtight" style="">ec</span></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">85</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_rec</span> <span class="o">=</span> <span class="n">ReconstructionLoss</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">BCEWithLogitsLoss</span><span class="p">(</span><span class="n">reduction</span><span class="o">=</span><span class="s1">&#39;none&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-21'>
<div class='docs'>
<div class='section-link'>
<a href='#section-21'>#</a>
</div>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.969438em;vertical-align:-0.286108em;"></span><span class="mord coloredeq eqe" style=""><span class="mord" style=""><span class="mord mathnormal" style="">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.328331em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="margin-right:0.00773em">R</span><span class="mord mathnormal mtight" style="">e</span><span class="mord mathnormal mtight" 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:0.286108em;"><span></span></span></span></span></span></span></span></span></span></span></span></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">87</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_reg</span> <span class="o">=</span> <span class="n">RegularizationLoss</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">lambda_p</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_steps</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</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>トレーニングおよび検証ローダー</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">90</span> <span class="bp">self</span><span class="o">.</span><span class="n">train_loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">ParityDataset</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_batches</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_elems</span><span class="p">),</span>
<span class="lineno">91</span> <span class="n">batch_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span><span class="p">)</span>
<span class="lineno">92</span> <span class="bp">self</span><span class="o">.</span><span class="n">valid_loader</span> <span class="o">=</span> <span class="n">DataLoader</span><span class="p">(</span><span class="n">ParityDataset</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span> <span class="o">*</span> <span class="mi">32</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_elems</span><span class="p">),</span>
<span class="lineno">93</span> <span class="n">batch_size</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">batch_size</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-23'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-23'>#</a>
</div>
<p>このメソッドは、バッチごとにトレーナーによって呼び出されます。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">95</span> <span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</span><span class="p">:</span> <span class="n">Any</span><span class="p">,</span> <span class="n">batch_idx</span><span class="p">:</span> <span class="n">BatchIndex</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>モデルモードを設定</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">100</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">train</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</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>入力とラベルを取得してモデルのデバイスに移動します</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">103</span> <span class="n">data</span><span class="p">,</span> <span class="n">target</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">),</span> <span class="n">batch</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</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>トレーニングモードでのインクリメントステップ</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">106</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</span><span class="p">:</span>
<span class="lineno">107</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add_global_step</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">data</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>モデルを実行</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">110</span> <span class="n">p</span><span class="p">,</span> <span class="n">y_hat</span><span class="p">,</span> <span class="n">p_sampled</span><span class="p">,</span> <span class="n">y_hat_sampled</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">data</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>再構成損失の計算</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">113</span> <span class="n">loss_rec</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_rec</span><span class="p">(</span><span class="n">p</span><span class="p">,</span> <span class="n">y_hat</span><span class="p">,</span> <span class="n">target</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float</span><span class="p">))</span>
<span class="lineno">114</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">&quot;loss.&quot;</span><span class="p">,</span> <span class="n">loss_rec</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-29'>
<div class='docs'>
<div class='section-link'>
<a href='#section-29'>#</a>
</div>
<p>正則化損失の計算</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">117</span> <span class="n">loss_reg</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_reg</span><span class="p">(</span><span class="n">p</span><span class="p">)</span>
<span class="lineno">118</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">&quot;loss_reg.&quot;</span><span class="p">,</span> <span class="n">loss_reg</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-30'>
<div class='docs'>
<div class='section-link'>
<a href='#section-30'>#</a>
</div>
<p><span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.68333em;vertical-align:0em;"></span><span class="mord mathnormal">L</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:0.83333em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord mathnormal" style="">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.32833099999999993em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="margin-right:0.00773em">R</span><span class="mord mathnormal mtight" style="">ec</span></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:0.2222222222222222em;"></span><span class="mbin">+</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.980548em;vertical-align:-0.286108em;"></span><span class="mord coloredeq eqf" style=""><span class="mord mathnormal" style="margin-right:0.05278em">β</span></span><span class="mord coloredeq eqe" style=""><span class="mord" style=""><span class="mord mathnormal" style="">L</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.328331em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="margin-right:0.00773em">R</span><span class="mord mathnormal mtight" style="">e</span><span class="mord mathnormal mtight" 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:0.286108em;"><span></span></span></span></span></span></span></span></span></span></span></span></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">121</span> <span class="n">loss</span> <span class="o">=</span> <span class="n">loss_rec</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">*</span> <span class="n">loss_reg</span></pre></div>
</div>
</div>
<div class='section' id='section-31'>
<div class='docs'>
<div class='section-link'>
<a href='#section-31'>#</a>
</div>
<p>予想される歩数の計算</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">124</span> <span class="n">steps</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">p</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">p</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
<span class="lineno">125</span> <span class="n">expected_steps</span> <span class="o">=</span> <span class="p">(</span><span class="n">p</span> <span class="o">*</span> <span class="n">steps</span><span class="p">[:,</span> <span class="kc">None</span><span class="p">])</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">dim</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="lineno">126</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">&quot;steps.&quot;</span><span class="p">,</span> <span class="n">expected_steps</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-32'>
<div class='docs'>
<div class='section-link'>
<a href='#section-32'>#</a>
</div>
<p>通話精度指標</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">129</span> <span class="bp">self</span><span class="o">.</span><span class="n">accuracy</span><span class="p">(</span><span class="n">y_hat_sampled</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">,</span> <span class="n">target</span><span class="p">)</span>
<span class="lineno">130</span>
<span class="lineno">131</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</span><span class="p">:</span></pre></div>
</div>
</div>
<div class='section' id='section-33'>
<div class='docs'>
<div class='section-link'>
<a href='#section-33'>#</a>
</div>
<p>勾配の計算</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">133</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-34'>
<div class='docs'>
<div class='section-link'>
<a href='#section-34'>#</a>
</div>
<p>クリップグラデーション</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">135</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">clip_grad_norm_</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">max_norm</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">grad_norm_clip</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-35'>
<div class='docs'>
<div class='section-link'>
<a href='#section-35'>#</a>
</div>
<p>オプティマイザー</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">137</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">step</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-36'>
<div class='docs'>
<div class='section-link'>
<a href='#section-36'>#</a>
</div>
<p>クリアグラデーション</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">139</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">zero_grad</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-37'>
<div class='docs'>
<div class='section-link'>
<a href='#section-37'>#</a>
</div>
<p></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">141</span> <span class="n">tracker</span><span class="o">.</span><span class="n">save</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-38'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-38'>#</a>
</div>
<p>実験を実行する</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">144</span><span class="k">def</span> <span class="nf">main</span><span class="p">():</span></pre></div>
</div>
</div>
<div class='section' id='section-39'>
<div class='docs'>
<div class='section-link'>
<a href='#section-39'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">148</span> <span class="n">experiment</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">&#39;ponder_net&#39;</span><span class="p">)</span>
<span class="lineno">149</span>
<span class="lineno">150</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</span><span class="p">()</span>
<span class="lineno">151</span> <span class="n">experiment</span><span class="o">.</span><span class="n">configs</span><span class="p">(</span><span class="n">conf</span><span class="p">,</span> <span class="p">{</span>
<span class="lineno">152</span> <span class="s1">&#39;optimizer.optimizer&#39;</span><span class="p">:</span> <span class="s1">&#39;Adam&#39;</span><span class="p">,</span>
<span class="lineno">153</span> <span class="s1">&#39;optimizer.learning_rate&#39;</span><span class="p">:</span> <span class="mf">0.0003</span><span class="p">,</span>
<span class="lineno">154</span> <span class="p">})</span>
<span class="lineno">155</span>
<span class="lineno">156</span> <span class="k">with</span> <span class="n">experiment</span><span class="o">.</span><span class="n">start</span><span class="p">():</span>
<span class="lineno">157</span> <span class="n">conf</span><span class="o">.</span><span class="n">run</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-40'>
<div class='docs'>
<div class='section-link'>
<a href='#section-40'>#</a>
</div>
<p></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">160</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="lineno">161</span> <span class="n">main</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>
docs/ja/adaptive_computation/ponder_net/index.html
+805
View File
File diff suppressed because one or more lines are too long
docs/ja/adaptive_computation/ponder_net/readme.html
+129
View File
@@ -0,0 +1,129 @@
<!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=""/>
<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="PonderNet: 熟考することを学ぶ"/>
<meta name="twitter:description" content=""/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/adaptive_computation/ponder_net/readme.html"/>
<meta property="og:title" content="PonderNet: 熟考することを学ぶ"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="PonderNet: 熟考することを学ぶ"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="PonderNet: 熟考することを学ぶ"/>
<meta property="og:description" content=""/>
<title>PonderNet: 熟考することを学ぶ</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/adaptive_computation/ponder_net/readme.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">adaptive_computation</a>
<a class="parent" href="index.html">ponder_net</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/adaptive_computation/ponder_net/readme.md" target="_blank">
View code on Github</a>
</p>
</div>
</div>
<div class='section' id='section-0'>
<div class='docs'>
<div class='section-link'>
<a href='#section-0'>#</a>
</div>
<h1><a href="https://nn.labml.ai/adaptive_computation/ponder_net/index.html">PonderNet: 熟考することを学ぶ</a></h1>
<p>これは、論文「<a href="https://papers.labml.ai/paper/2107.05407">PonderNet: 熟考を学ぼう</a>」<a href="https://pytorch.org">をPyTorchで実装したものです</a>。</p>
<p>PonderNet は入力に基づいて計算を調整します。入力に基づいてリカレントネットワークで実行するステップの数を変更します。PonderNetはこれを端から端までの勾配降下法で学習します</p>。
</div>
<div class='code'>
</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>
docs/ja/adaptive_computation/readme.html
+129
View File
@@ -0,0 +1,129 @@
<!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=""/>
<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="適応型計算を備えたニューラルネットワーク"/>
<meta name="twitter:description" content=""/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/adaptive_computation/readme.html"/>
<meta property="og:title" content="適応型計算を備えたニューラルネットワーク"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="適応型計算を備えたニューラルネットワーク"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="適応型計算を備えたニューラルネットワーク"/>
<meta property="og:description" content=""/>
<title>適応型計算を備えたニューラルネットワーク</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/adaptive_computation/readme.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">adaptive_computation</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/adaptive_computation/readme.md" target="_blank">
View code on Github</a>
</p>
</div>
</div>
<div class='section' id='section-0'>
<div class='docs'>
<div class='section-link'>
<a href='#section-0'>#</a>
</div>
<h1><a href="https://nn.labml.ai/adaptive_computation/index.html">適応型計算を備えたニューラルネットワーク</a></h1>
<p>これらは、入力サンプルの複雑さに基づいて計算の複雑さを変更するニューラルネットワークアーキテクチャです。</p>
<ul><li>🚧 TODO: リカレントニューラルネットワークの適応型計算時間</li>
<li><a href="https://nn.labml.ai/adaptive_computation/ponder_net/index.html">PonderNet: 熟考することを学ぶ</a></li></ul>
</div>
<div class='code'>
</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>