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/zh/capsule_networks/index.html
+489
View File
File diff suppressed because one or more lines are too long
docs/zh/capsule_networks/mnist.html
+599
View File
@@ -0,0 +1,599 @@
<!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="在 MNIST 数据集上训练胶囊网络的代码"/>
<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="使用胶囊网络对 MNIST 数字进行分类"/>
<meta name="twitter:description" content="在 MNIST 数据集上训练胶囊网络的代码"/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/capsule_networks/mnist.html"/>
<meta property="og:title" content="使用胶囊网络对 MNIST 数字进行分类"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="使用胶囊网络对 MNIST 数字进行分类"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="使用胶囊网络对 MNIST 数字进行分类"/>
<meta property="og:description" content="在 MNIST 数据集上训练胶囊网络的代码"/>
<title>使用胶囊网络对 MNIST 数字进行分类</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/capsule_networks/mnist.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">capsule_networks</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/capsule_networks/mnist.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>使用胶囊网络对 MNIST 数字进行分类</h1>
<p>这是一个带注释的 PyTorch 代码，用于使用 PyTorch 对 MNIST 数字进行分类。</p>
<p>本文实施了论文《<a href="https://arxiv.org/abs/1710.09829">胶囊间动态路由</a>》中描述的实验。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">14</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">15</span>
<span class="lineno">16</span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span>
<span class="lineno">17</span><span class="kn">import</span> <span class="nn">torch.nn.functional</span> <span class="k">as</span> <span class="nn">F</span>
<span class="lineno">18</span><span class="kn">import</span> <span class="nn">torch.utils.data</span>
<span class="lineno">19</span>
<span class="lineno">20</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">experiment</span><span class="p">,</span> <span class="n">tracker</span>
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">option</span>
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">labml_helpers.datasets.mnist</span> <span class="kn">import</span> <span class="n">MNISTConfigs</span>
<span class="lineno">23</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">24</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span>
<span class="lineno">25</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">26</span><span class="kn">from</span> <span class="nn">labml_nn.capsule_networks</span> <span class="kn">import</span> <span class="n">Squash</span><span class="p">,</span> <span class="n">Router</span><span class="p">,</span> <span class="n">MarginLoss</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>用于对 MNIST 数字进行分类的模型</h2>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">29</span><span class="k">class</span> <span class="nc">MNISTCapsuleNetworkModel</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-2'>
<div class='docs'>
<div class='section-link'>
<a href='#section-2'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">34</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">35</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-3'>
<div class='docs'>
<div class='section-link'>
<a href='#section-3'>#</a>
</div>
<p>第一个卷积层有<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 eql" style=""><span class="mord" style="">2</span></span><span class="mord">56</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">9</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:0.64444em;vertical-align:0em;"></span><span class="mord">9</span></span></span></span></span>卷积内核</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">37</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">out_channels</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">9</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-4'>
<div class='docs'>
<div class='section-link'>
<a href='#section-4'>#</a>
</div>
<p>第二层（Primary Capsules）是卷积胶囊层，带有卷积<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.68333em;vertical-align:0em;"></span><span class="mord coloredeq eqn" style=""><span class="mord" style="">8</span></span><span class="mord mathnormal" style="margin-right:0.02778em;">D</span></span></span></span></span>胶囊<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 eqj" style=""><span class="mord" style=""><span class="mord coloredeq eqm" style="">3</span></span><span class="mord" style=""><span class="mord coloredeq eql" style="">2</span></span></span></span></span></span></span>通道（每个胶囊<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 eqn" style=""><span class="mord" style="">8</span></span></span></span></span></span>的特征）。也就是说，每个主胶囊包含 8 个卷积单位，内核为 9×9，步幅为 2。为了实现这一点，我们创建了一个带有<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 eqj" style=""><span class="mord" style=""><span class="mord coloredeq eqm" style="">3</span></span><span class="mord" style=""><span class="mord coloredeq eql" style="">2</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:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqn" style=""><span class="mord" style="">8</span></span></span></span></span></span>通道的卷积层，并对其输出进行整形和排列，以获得每个<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 eqn" style=""><span class="mord" style="">8</span></span></span></span></span></span>特征的胶囊。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">43</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="n">in_channels</span><span class="o">=</span><span class="mi">256</span><span class="p">,</span> <span class="n">out_channels</span><span class="o">=</span><span class="mi">32</span> <span class="o">*</span> <span class="mi">8</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">9</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
<span class="lineno">44</span> <span class="bp">self</span><span class="o">.</span><span class="n">squash</span> <span class="o">=</span> <span class="n">Squash</span><span class="p">()</span></pre></div>
</div>
</div>
<div class='section' id='section-5'>
<div class='docs'>
<div class='section-link'>
<a href='#section-5'>#</a>
</div>
<p>路由层获取<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 eqj" style=""><span class="mord" style=""><span class="mord coloredeq eqm" style="">3</span></span><span class="mord" style=""><span class="mord coloredeq eql" style="">2</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:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">6</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:0.64444em;vertical-align:0em;"></span><span class="mord">6</span></span></span></span></span>主胶囊并生成<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 eqh" style=""><span class="mord" style="">10</span></span></span></span></span></span>胶囊。每个主胶囊都有<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 eqn" style=""><span class="mord" style="">8</span></span></span></span></span></span>特征，而输出胶囊（Digit Capsules）都有<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 eqi" style=""><span class="mord" style="">16</span></span></span></span></span></span>特征。路由算法会迭代<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 eqm" style=""><span class="mord" style="">3</span></span></span></span></span></span>次数。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">50</span> <span class="bp">self</span><span class="o">.</span><span class="n">digit_capsules</span> <span class="o">=</span> <span class="n">Router</span><span class="p">(</span><span class="mi">32</span> <span class="o">*</span> <span class="mi">6</span> <span class="o">*</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">16</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-6'>
<div class='docs'>
<div class='section-link'>
<a href='#section-6'>#</a>
</div>
<p>这是本文中提到的解码器。它采用<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 eqh" style=""><span class="mord" style="">10</span></span></span></span></span></span>数字胶囊的输出，每个胶囊都有重现图像的<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 eqi" style=""><span class="mord" style="">16</span></span></span></span></span></span>功能。它穿过大小<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">51</span><span class="mord coloredeq eql" style=""><span class="mord" style="">2</span></span></span></span></span></span>和<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:0.00773em;">R</span><span class="mord mathnormal">e</span><span class="mord mathnormal" style="margin-right:0.10903em;">LU</span></span></span></span></span>激活<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 eqh" style=""><span class="mord" style="">10</span></span><span class="mord coloredeq eql" style=""><span class="mord" style="">2</span></span><span class="mord">4</span></span></span></span></span>的线性层。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">55</span> <span class="bp">self</span><span class="o">.</span><span class="n">decoder</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span>
<span class="lineno">56</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="mi">16</span> <span class="o">*</span> <span class="mi">10</span><span class="p">,</span> <span class="mi">512</span><span class="p">),</span>
<span class="lineno">57</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
<span class="lineno">58</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="mi">512</span><span class="p">,</span> <span class="mi">1024</span><span class="p">),</span>
<span class="lineno">59</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">(),</span>
<span class="lineno">60</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="mi">784</span><span class="p">),</span>
<span class="lineno">61</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sigmoid</span><span class="p">()</span>
<span class="lineno">62</span> <span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-7'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-7'>#</a>
</div>
<p><code class="highlight"><span></span><span class="n">data</span></code>
是 MNIST 图像，有形状<code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">28</span><span class="p">,</span> <span class="mi">28</span><span class="p">]</span></code>
</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">64</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-8'>
<div class='docs'>
<div class='section-link'>
<a href='#section-8'>#</a>
</div>
<p>穿过第一个卷积层。此图层的输出具有形状<code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="mi">256</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">20</span><span class="p">]</span></code>
</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">70</span> <span class="n">x</span> <span class="o">=</span> <span class="n">F</span><span class="o">.</span><span class="n">relu</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv1</span><span class="p">(</span><span class="n">data</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>穿过第二个卷积层。这个的输出有形状<code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="mi">32</span> <span class="o">*</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">6</span><span class="p">,</span> <span class="mi">6</span><span class="p">]</span></code>
。<em>请注意，此图层的步长为<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 eql" style=""><span class="mord" style="">2</span></span></span></span></span></span></em>。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">74</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-10'>
<div class='docs'>
<div class='section-link'>
<a href='#section-10'>#</a>
</div>
<p>调整大小并排列以获得胶囊</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">77</span> <span class="n">caps</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="mi">8</span><span class="p">,</span> <span class="mi">32</span> <span class="o">*</span> <span class="mi">6</span> <span class="o">*</span> <span class="mi">6</span><span class="p">)</span><span class="o">.</span><span class="n">permute</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="mi">1</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>挤压胶囊</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">79</span> <span class="n">caps</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">squash</span><span class="p">(</span><span class="n">caps</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-12'>
<div class='docs'>
<div class='section-link'>
<a href='#section-12'>#</a>
</div>
<p>带他们通过路由器获得数字胶囊。这有形状<code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="mi">16</span><span class="p">]</span></code>
。</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">82</span> <span class="n">caps</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">digit_capsules</span><span class="p">(</span><span class="n">caps</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-13'>
<div class='docs'>
<div class='section-link'>
<a href='#section-13'>#</a>
</div>
<p>获取用于重建的口罩</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">85</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span></pre></div>
</div>
</div>
<div class='section' id='section-14'>
<div class='docs'>
<div class='section-link'>
<a href='#section-14'>#</a>
</div>
<p>胶囊网络的预测是长度最长的胶囊</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">87</span> <span class="n">pred</span> <span class="o">=</span> <span class="p">(</span><span class="n">caps</span> <span class="o">**</span> <span class="mi">2</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">1</span><span class="p">)</span><span class="o">.</span><span class="n">argmax</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-15'>
<div class='docs'>
<div class='section-link'>
<a href='#section-15'>#</a>
</div>
<p>创建遮罩以遮盖所有其他胶囊</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">89</span> <span class="n">mask</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">eye</span><span class="p">(</span><span class="mi">10</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">data</span><span class="o">.</span><span class="n">device</span><span class="p">)[</span><span class="n">pred</span><span class="p">]</span></pre></div>
</div>
</div>
<div class='section' id='section-16'>
<div class='docs'>
<div class='section-link'>
<a href='#section-16'>#</a>
</div>
<p>掩盖数字胶囊以仅获得做出预测的胶囊，然后将其通过解码器进行重建</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">93</span> <span class="n">reconstructions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">decoder</span><span class="p">((</span><span class="n">caps</span> <span class="o">*</span> <span class="n">mask</span><span class="p">[:,</span> <span class="p">:,</span> <span class="kc">None</span><span class="p">])</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="o">-</span><span class="mi">1</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>重塑重建以匹配图像尺寸</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">95</span> <span class="n">reconstructions</span> <span class="o">=</span> <span class="n">reconstructions</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">28</span><span class="p">,</span> <span class="mi">28</span><span class="p">)</span>
<span class="lineno">96</span>
<span class="lineno">97</span> <span class="k">return</span> <span class="n">caps</span><span class="p">,</span> <span class="n">reconstructions</span><span class="p">,</span> <span class="n">pred</span></pre></div>
</div>
</div>
<div class='section' id='section-18'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-18'>#</a>
</div>
<p>使用 MNIST 数据和训练与验证设置的配置</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">100</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">MNISTConfigs</span><span class="p">,</span> <span class="n">SimpleTrainValidConfigs</span><span class="p">):</span></pre></div>
</div>
</div>
<div class='section' id='section-19'>
<div class='docs'>
<div class='section-link'>
<a href='#section-19'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">104</span> <span class="n">epochs</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span>
<span class="lineno">105</span> <span class="n">model</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span> <span class="o">=</span> <span class="s1">&#39;capsule_network_model&#39;</span>
<span class="lineno">106</span> <span class="n">reconstruction_loss</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MSELoss</span><span class="p">()</span>
<span class="lineno">107</span> <span class="n">margin_loss</span> <span class="o">=</span> <span class="n">MarginLoss</span><span class="p">(</span><span class="n">n_labels</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
<span class="lineno">108</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-20'>
<div class='docs'>
<div class='section-link'>
<a href='#section-20'>#</a>
</div>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">110</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-21'>
<div class='docs'>
<div class='section-link'>
<a href='#section-21'>#</a>
</div>
<p>印刷损耗和屏幕精度</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">112</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">113</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></pre></div>
</div>
</div>
<div class='section' id='section-22'>
<div class='docs'>
<div class='section-link'>
<a href='#section-22'>#</a>
</div>
<p>我们需要设置指标来计算训练和验证时期的指标</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">116</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-23'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-23'>#</a>
</div>
<p>这个方法被训练器调用</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">118</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>设置模型模式</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">123</span> <span class="bp">self</span><span class="o">.</span><span class="n">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>获取图像和标签并将其移动到模特的设备上</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">126</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>在训练模式中增加步数</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">129</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">130</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>是否记录激活次数</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">133</span> <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">is_log_activations</span><span class="o">=</span><span class="n">batch_idx</span><span class="o">.</span><span class="n">is_last</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>运行模型</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">135</span> <span class="n">caps</span><span class="p">,</span> <span class="n">reconstructions</span><span class="p">,</span> <span class="n">pred</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-29'>
<div class='docs'>
<div class='section-link'>
<a href='#section-29'>#</a>
</div>
<p>计算总损失</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">138</span> <span class="n">loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">margin_loss</span><span class="p">(</span><span class="n">caps</span><span class="p">,</span> <span class="n">target</span><span class="p">)</span> <span class="o">+</span> <span class="mf">0.0005</span> <span class="o">*</span> <span class="bp">self</span><span class="o">.</span><span class="n">reconstruction_loss</span><span class="p">(</span><span class="n">reconstructions</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
<span class="lineno">139</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</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>呼叫准确度指标</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">142</span> <span class="bp">self</span><span class="o">.</span><span class="n">accuracy</span><span class="p">(</span><span class="n">pred</span><span class="p">,</span> <span class="n">target</span><span class="p">)</span>
<span class="lineno">143</span>
<span class="lineno">144</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">145</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span>
<span class="lineno">146</span>
<span class="lineno">147</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-31'>
<div class='docs'>
<div class='section-link'>
<a href='#section-31'>#</a>
</div>
<p>日志参数和梯度</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">149</span> <span class="k">if</span> <span class="n">batch_idx</span><span class="o">.</span><span class="n">is_last</span><span class="p">:</span>
<span class="lineno">150</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">&#39;model&#39;</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">)</span>
<span class="lineno">151</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>
<span class="lineno">152</span>
<span class="lineno">153</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-32'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-32'>#</a>
</div>
<p>设置模型</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">156</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">model</span><span class="p">)</span>
<span class="lineno">157</span><span class="k">def</span> <span class="nf">capsule_network_model</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">Configs</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>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">159</span> <span class="k">return</span> <span class="n">MNISTCapsuleNetworkModel</span><span class="p">()</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
</div>
</div>
<div class='section' id='section-34'>
<div class='docs doc-strings'>
<div class='section-link'>
<a href='#section-34'>#</a>
</div>
<p>运行实验</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">162</span><span class="k">def</span> <span class="nf">main</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>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">166</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;capsule_network_mnist&#39;</span><span class="p">)</span>
<span class="lineno">167</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</span><span class="p">()</span>
<span class="lineno">168</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="s1">&#39;optimizer.optimizer&#39;</span><span class="p">:</span> <span class="s1">&#39;Adam&#39;</span><span class="p">,</span>
<span class="lineno">169</span> <span class="s1">&#39;optimizer.learning_rate&#39;</span><span class="p">:</span> <span class="mf">1e-3</span><span class="p">})</span>
<span class="lineno">170</span>
<span class="lineno">171</span> <span class="n">experiment</span><span class="o">.</span><span class="n">add_pytorch_models</span><span class="p">({</span><span class="s1">&#39;model&#39;</span><span class="p">:</span> <span class="n">conf</span><span class="o">.</span><span class="n">model</span><span class="p">})</span>
<span class="lineno">172</span>
<span class="lineno">173</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">174</span> <span class="n">conf</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
<span class="lineno">175</span>
<span class="lineno">176</span>
<span class="lineno">177</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">178</span> <span class="n">main</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>
docs/zh/capsule_networks/readme.html
+132
View File
@@ -0,0 +1,132 @@
<!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="胶囊网络"/>
<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/capsule_networks/readme.html"/>
<meta property="og:title" content="胶囊网络"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&amp;v=4"/>
<meta property="og:site_name" content="胶囊网络"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="胶囊网络"/>
<meta property="og:description" content=""/>
<title>胶囊网络</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/capsule_networks/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">capsule_networks</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/capsule_networks/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/capsule_networks/index.html">胶囊网络</a></h1>
<p>这是<a href="https://arxiv.org/abs/1710.09829">胶囊间动态路由</a>的 <a href="https://pytorch.org">PyTorch</a> 实现/教程。</p>
<p>Capsule 网络是一种神经网络架构，它以胶囊的形式嵌入特征，并通过投票机制将它们路由到下一层胶囊。</p>
<p>与其他模型实现不同，我们提供了一个示例，因为仅使用模块很难理解某些概念。<a href="mnist.html">这是使用胶囊对 MNIST 数据集进行分类的模型的带注释的代码</a></p>
<p>该文件包含了 Capsule Networks 核心模块的实现。</p>
<p>我用 <a href="https://github.com/jindongwang/Pytorch-CapsuleNet">jindongwang/pytorch-CapsuleNet</a> 来澄清我对这篇论文的一些困惑。</p>
<p>这是一本在 MNIST 数据集上训练 Capsule 网络的笔记本。</p>
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/capsule_networks/mnist.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a></p>
</div>
<div class='code'>
</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>