chore: import upstream snapshot with attribution

2026-07-13 12:19:01 +08:00
commit 3b90d1192f
2172 changed files with 594509 additions and 0 deletions
@@ -0,0 +1,289 @@
+<!DOCTYPE html>
+<html lang="zh">
+<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="一堆实用函数和类"/>
+
+    <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="公共事业"/>
+    <meta name="twitter:description" content="一堆实用函数和类"/>
+    <meta name="twitter:site" content="@labmlai"/>
+    <meta name="twitter:creator" content="@labmlai"/>
+
+    <meta property="og:url" content="https://nn.labml.ai/utils/index.html"/>
+    <meta property="og:title" content="公共事业"/>
+    <meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
+    <meta property="og:site_name" content="公共事业"/>
+    <meta property="og:type" content="object"/>
+    <meta property="og:title" content="公共事业"/>
+    <meta property="og:description" content="一堆实用函数和类"/>
+
+    <title>公共事业</title>
+    <link rel="shortcut icon" href="/icon.png"/>
+    <link rel="stylesheet" href="../pylit.css?v=1">
+    <link rel="canonical" href="https://nn.labml.ai/utils/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">utils</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/utils/__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>公共事业</h1>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">10</span><span></span><span class="kn">import</span> <span class="nn">copy</span>
+<span class="lineno">11</span>
+<span class="lineno">12</span><span class="kn">from</span> <span class="nn">torch.utils.data</span> <span class="kn">import</span> <span class="n">Dataset</span><span class="p">,</span> <span class="n">IterableDataset</span>
+<span class="lineno">13</span>
+<span class="lineno">14</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">M</span><span class="p">,</span> <span class="n">TypedModuleList</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>克隆模块</h2>
+<p><code  class="highlight"><span></span><span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span></code>
+使用给定模块的克隆制作一个</p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">17</span><span class="k">def</span> <span class="nf">clone_module_list</span><span class="p">(</span><span class="n">module</span><span class="p">:</span> <span class="n">M</span><span class="p">,</span> <span class="n">n</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">TypedModuleList</span><span class="p">[</span><span class="n">M</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">23</span>    <span class="k">return</span> <span class="n">TypedModuleList</span><span class="p">([</span><span class="n">copy</span><span class="o">.</span><span class="n">deepcopy</span><span class="p">(</span><span class="n">module</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</span><span class="p">)])</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-3'>
+        <div class='docs doc-strings'>
+            <div class='section-link'>
+                <a href='#section-3'>#</a>
+            </div>
+            <p><a id="cycle_dataloader"></a></p>
+<h2>循环数据加载器</h2>
+<p>无限加载器，在每个纪元之后回收数据加载器</p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">26</span><span class="k">def</span> <span class="nf">cycle_dataloader</span><span class="p">(</span><span class="n">data_loader</span><span class="p">):</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-4'>
+        <div class='docs'>
+            <div class='section-link'>
+                <a href='#section-4'>#</a>
+            </div>
+            
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">34</span>    <span class="k">while</span> <span class="kc">True</span><span class="p">:</span>
+<span class="lineno">35</span>        <span class="k">for</span> <span class="n">batch</span> <span class="ow">in</span> <span class="n">data_loader</span><span class="p">:</span>
+<span class="lineno">36</span>            <span class="k">yield</span> <span class="n">batch</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-5'>
+        <div class='docs doc-strings'>
+            <div class='section-link'>
+                <a href='#section-5'>#</a>
+            </div>
+            <p><a id="map_style_dataset"></a></p>
+<h2>地图样式数据集</h2>
+<p>这会将转换<a href="https://pytorch.org/docs/stable/data.html#torch.utils.data.IterableDataset"><code  class="highlight"><span></span><span class="n">IterableDataset</span></code>
+</a>为<a href="https://pytorch.org/docs/stable/data.html#map-style-datasets">地图样式的数据集</a>，以便我们可以随机排列数据集。</p>
+<p><em>这仅在数据集大小较小且可以保存在内存中时才有效。</em></p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">39</span><span class="k">class</span> <span class="nc">MapStyleDataset</span><span class="p">(</span><span class="n">Dataset</span><span class="p">):</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-6'>
+        <div class='docs'>
+            <div class='section-link'>
+                <a href='#section-6'>#</a>
+            </div>
+            
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">52</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">dataset</span><span class="p">:</span> <span class="n">IterableDataset</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>将数据加载到内存</p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">54</span>        <span class="bp">self</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="p">[</span><span class="n">d</span> <span class="k">for</span> <span class="n">d</span> <span class="ow">in</span> <span class="n">dataset</span><span class="p">]</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-8'>
+        <div class='docs doc-strings'>
+            <div class='section-link'>
+                <a href='#section-8'>#</a>
+            </div>
+            <p>按索引获取样本</p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">56</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></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-9'>
+        <div class='docs'>
+            <div class='section-link'>
+                <a href='#section-9'>#</a>
+            </div>
+            
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">58</span>        <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">[</span><span class="n">idx</span><span class="p">]</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-10'>
+        <div class='docs doc-strings'>
+            <div class='section-link'>
+                <a href='#section-10'>#</a>
+            </div>
+            <p>创建迭代器</p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">60</span>    <span class="k">def</span> <span class="fm">__iter__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-11'>
+        <div class='docs'>
+            <div class='section-link'>
+                <a href='#section-11'>#</a>
+            </div>
+            
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">62</span>        <span class="k">return</span> <span class="nb">iter</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">)</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-12'>
+        <div class='docs doc-strings'>
+            <div class='section-link'>
+                <a href='#section-12'>#</a>
+            </div>
+            <p>数据集的大小</p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">64</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-13'>
+        <div class='docs'>
+            <div class='section-link'>
+                <a href='#section-13'>#</a>
+            </div>
+            
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">66</span>        <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">data</span><span class="p">)</span></pre></div>
+        </div>
+    </div>
+    <div class='footer'>
+        <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>
@@ -0,0 +1,237 @@
+<!DOCTYPE html>
+<html lang="zh">
+<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="tokenizer.py"/>
+    <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/utils/tokenizer.html"/>
+    <meta property="og:title" content="tokenizer.py"/>
+    <meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
+    <meta property="og:site_name" content="tokenizer.py"/>
+    <meta property="og:type" content="object"/>
+    <meta property="og:title" content="tokenizer.py"/>
+    <meta property="og:description" content=""/>
+
+    <title>tokenizer.py</title>
+    <link rel="shortcut icon" href="/icon.png"/>
+    <link rel="stylesheet" href="../pylit.css?v=1">
+    <link rel="canonical" href="https://nn.labml.ai/utils/tokenizer.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">utils</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/utils/tokenizer.py" 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>
+            
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">1</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Callable</span>
+<span class="lineno">2</span>
+<span class="lineno">3</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">BaseConfigs</span><span class="p">,</span> <span class="n">option</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 id="TokenizerConfigs"></a></p>
+<h2>分词器配置</h2>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">6</span><span class="k">class</span> <span class="nc">TokenizerConfigs</span><span class="p">(</span><span class="n">BaseConfigs</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">13</span>    <span class="n">tokenizer</span><span class="p">:</span> <span class="n">Callable</span> <span class="o">=</span> <span class="s1">&#39;character&#39;</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">15</span>    <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="lineno">16</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="n">_primary</span><span class="o">=</span><span class="s1">&#39;tokenizer&#39;</span><span class="p">)</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>
+            <h3>基础英语分词器</h3>
+<p>我们在这个实验中使用角色等级分词器。你可以通过设置进行切换，</p>
+<pre  class="highlight lang-"><code><span></span><span class="s1">&#39;tokenizer&#39;</span><span class="p">:</span> <span class="s1">&#39;basic_english&#39;</span></code></pre>
+<p>开始实验时在配置字典中。</p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">19</span><span class="nd">@option</span><span class="p">(</span><span class="n">TokenizerConfigs</span><span class="o">.</span><span class="n">tokenizer</span><span class="p">)</span>
+<span class="lineno">20</span><span class="k">def</span> <span class="nf">basic_english</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">34</span>    <span class="kn">from</span> <span class="nn">torchtext.data</span> <span class="kn">import</span> <span class="n">get_tokenizer</span>
+<span class="lineno">35</span>    <span class="k">return</span> <span class="n">get_tokenizer</span><span class="p">(</span><span class="s1">&#39;basic_english&#39;</span><span class="p">)</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>
+            <h3>角色等级分词器</h3>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">38</span><span class="k">def</span> <span class="nf">character_tokenizer</span><span class="p">(</span><span class="n">x</span><span class="p">:</span> <span class="nb">str</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">42</span>    <span class="k">return</span> <span class="nb">list</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-8'>
+        <div class='docs doc-strings'>
+            <div class='section-link'>
+                <a href='#section-8'>#</a>
+            </div>
+            <p>角色级别分词器配置</p>
+
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">45</span><span class="nd">@option</span><span class="p">(</span><span class="n">TokenizerConfigs</span><span class="o">.</span><span class="n">tokenizer</span><span class="p">)</span>
+<span class="lineno">46</span><span class="k">def</span> <span class="nf">character</span><span class="p">():</span></pre></div>
+        </div>
+    </div>
+    <div class='section' id='section-9'>
+        <div class='docs'>
+            <div class='section-link'>
+                <a href='#section-9'>#</a>
+            </div>
+            
+        </div>
+        <div class='code'>
+            <div class="highlight"><pre><span class="lineno">50</span>    <span class="k">return</span> <span class="n">character_tokenizer</span></pre></div>
+        </div>
+    </div>
+    <div class='footer'>
+        <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>