mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-11-01 03:43:09 +08:00
567 lines
40 KiB
HTML
567 lines
40 KiB
HTML
<!DOCTYPE html>
|
||
<html>
|
||
<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="Code for training Capsule Networks on MNIST dataset"/>
|
||
|
||
<meta name="twitter:card" content="summary"/>
|
||
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||
<meta name="twitter:title" content="Classify MNIST digits with Capsule Networks"/>
|
||
<meta name="twitter:description" content="Code for training Capsule Networks on MNIST dataset"/>
|
||
<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="Classify MNIST digits with Capsule Networks"/>
|
||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||
<meta property="og:site_name" content="LabML Neural Networks"/>
|
||
<meta property="og:type" content="object"/>
|
||
<meta property="og:title" content="Classify MNIST digits with Capsule Networks"/>
|
||
<meta property="og:description" content="Code for training Capsule Networks on MNIST dataset"/>
|
||
|
||
<title>Classify MNIST digits with Capsule Networks</title>
|
||
<link rel="shortcut icon" href="/icon.png"/>
|
||
<link rel="stylesheet" href="../pylit.css">
|
||
<link rel="canonical" href="https://nn.labml.ai/capsule_networks/mnist.html"/>
|
||
<!-- 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/lab-ml/labml_nn/tree/master/labml_nn/capsule_networks/mnist.py">
|
||
<img alt="Github"
|
||
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
|
||
style="max-width:100%;"/></a>
|
||
<a href="https://join.slack.com/t/labforml/shared_invite/zt-egj9zvq9-Dl3hhZqobexgT7aVKnD14g/"
|
||
rel="nofollow">
|
||
<img alt="Join Slact"
|
||
src="https://img.shields.io/badge/slack-chat-green.svg?logo=slack"
|
||
style="max-width:100%;"/></a>
|
||
<a href="https://twitter.com/labmlai"
|
||
rel="nofollow">
|
||
<img alt="Twitter"
|
||
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
||
style="max-width:100%;"/></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>Classify MNIST digits with Capsule Networks</h1>
|
||
<p>This is an annotated PyTorch code to classify MNIST digits with PyTorch.</p>
|
||
<p>This paper implements the experiment described in paper
|
||
<a href="https://arxiv.org/abs/1710.09829">Dynamic Routing Between Capsules</a>.</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>Model for classifying MNIST digits</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>First convolution layer has $256$, $9 \times 9$ convolution kernels</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>The second layer (Primary Capsules) s a convolutional capsule layer with $32$ channels
|
||
of convolutional $8D$ capsules ($8$ features per capsule).
|
||
That is, each primary capsule contains 8 convolutional units with a 9 × 9 kernel and a stride of 2.
|
||
In order to implement this we create a convolutional layer with $32 \times 8$ channels and
|
||
reshape and permutate its output to get the capsules of $8$ features each.</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>Routing layer gets the $32 \times 6 \times 6$ primary capsules and produces $10$ capsules.
|
||
Each of the primary capsules have $8$ features, while output capsules (Digit Capsules)
|
||
have $16$ features.
|
||
The routing algorithm iterates $3$ times.</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>This is the decoder mentioned in the paper.
|
||
It takes the outputs of the $10$ digit capsules, each with $16$ features to reproduce the
|
||
image. It goes through linear layers of sizes $512% and $1024$ with $ReLU$ activations.</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>data</code> are the MNIST images, with shape <code>[batch_size, 1, 28, 28]</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>Pass through the first convolution layer.
|
||
Output of this layer has shape <code>[batch_size, 256, 20, 20]</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>Pass through the second convolution layer.
|
||
Output of this has shape <code>[batch_size, 32 * 8, 6, 6]</code>.
|
||
*Note that this layer has a stride length of $2$.</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>Resize and permutate to get the capsules</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>Squash the capsules</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>Take them through the router to get digit capsules.
|
||
This has shape <code>[batch_size, 10, 16]</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>Get masks for reconstructioon</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>The prediction by the capsule network is the capsule with longest length</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>Create a mask to maskout all the other capsules</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>Mask the digit capsules to get only the capsule that made the prediction and
|
||
take it through decoder to get reconstruction</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>Reshape the reconstruction to match the image dimensions</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>Configurations with MNIST data and Train & Validation setup</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">'capsule_network_model'</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>Print losses and accuracy to screen</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">'loss.*'</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">'accuracy.*'</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>We need to set the metrics to calculate them for the epoch for training and validation</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>This method gets called by the trainer</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>Set the model mode</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>Get the images and labels and move them to the model’s device</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>Increment step in training mode</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>Whether to log activations</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>Run the model</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>Calculate the total loss</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">"loss."</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>Call accuracy metric</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>Log parameters and gradients</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">'model'</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>Set the model</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>Run the experiment</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">'capsule_network_mnist'</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">'optimizer.optimizer'</span><span class="p">:</span> <span class="s1">'Adam'</span><span class="p">,</span>
|
||
<span class="lineno">169</span> <span class="s1">'optimizer.learning_rate'</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">'model'</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">'__main__'</span><span class="p">:</span>
|
||
<span class="lineno">178</span> <span class="n">main</span><span class="p">()</span></pre></div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/MathJax.js?config=TeX-AMS_HTML">
|
||
</script>
|
||
<!-- MathJax configuration -->
|
||
<script type="text/x-mathjax-config">
|
||
MathJax.Hub.Config({
|
||
tex2jax: {
|
||
inlineMath: [ ['$','$'] ],
|
||
displayMath: [ ['$$','$$'] ],
|
||
processEscapes: true,
|
||
processEnvironments: true
|
||
},
|
||
// Center justify equations in code and markdown cells. Elsewhere
|
||
// we use CSS to left justify single line equations in code cells.
|
||
displayAlign: 'center',
|
||
"HTML-CSS": { fonts: ["TeX"] }
|
||
});
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
</script>
|
||
</body>
|
||
</html> |