mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-15 10:11:39 +08:00
571 lines
46 KiB
HTML
571 lines
46 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=""/>
|
|
|
|
<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="resnet.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/resnets/models/resnet.html"/>
|
|
<meta property="og:title" content="resnet.py"/>
|
|
<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="resnet.py"/>
|
|
<meta property="og:description" content=""/>
|
|
|
|
<title>resnet.py</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/resnets/models/resnet.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">resnets</a>
|
|
<a class="parent" href="index.html">models</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/resnets/models/resnet.py">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
|
|
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'>
|
|
<div class='section-link'>
|
|
<a href='#section-0'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">2</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="lineno">3</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">4</span><span class="kn">import</span> <span class="nn">torchvision</span>
|
|
<span class="lineno">5</span><span class="kn">import</span> <span class="nn">torchvision.transforms</span> <span class="k">as</span> <span class="nn">transforms</span>
|
|
<span class="lineno">6</span><span class="kn">import</span> <span class="nn">torch.optim</span> <span class="k">as</span> <span class="nn">optim</span>
|
|
<span class="lineno">7</span><span class="kn">from</span> <span class="nn">torchsummary</span> <span class="kn">import</span> <span class="n">summary</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-1'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-1'>#</a>
|
|
</div>
|
|
<p>custom import</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">10</span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
|
<span class="lineno">11</span><span class="kn">import</span> <span class="nn">time</span>
|
|
<span class="lineno">12</span><span class="kn">import</span> <span class="nn">os</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-2'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-2'>#</a>
|
|
</div>
|
|
<p>ResBlock</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">16</span><span class="k">class</span> <span class="nc">ResBlock</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-3'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-3'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">17</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">num_features</span><span class="p">,</span> <span class="n">use_batch_norm</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
|
<span class="lineno">18</span> <span class="nb">super</span><span class="p">(</span><span class="n">ResBlock</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
|
<span class="lineno">19</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_features</span> <span class="o">=</span> <span class="n">num_features</span>
|
|
<span class="lineno">20</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv_layer1</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">num_features</span><span class="p">,</span> <span class="n">num_features</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
|
|
<span class="lineno">21</span> <span class="bp">self</span><span class="o">.</span><span class="n">relu_layer</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">()</span>
|
|
<span class="lineno">22</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv_layer2</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">num_features</span><span class="p">,</span> <span class="n">num_features</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span>
|
|
<span class="lineno">23</span>
|
|
<span class="lineno">24</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_batch_norm</span> <span class="o">=</span> <span class="n">use_batch_norm</span>
|
|
<span class="lineno">25</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_batch_norm</span><span class="p">:</span>
|
|
<span class="lineno">26</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_norm_layer1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_features</span><span class="p">)</span>
|
|
<span class="lineno">27</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_norm_layer2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_features</span><span class="p">)</span>
|
|
<span class="lineno">28</span>
|
|
<span class="lineno">29</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">modules</span><span class="p">():</span>
|
|
<span class="lineno">30</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">m</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">):</span>
|
|
<span class="lineno">31</span> <span class="n">nn</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">kaiming_normal_</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">weight</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>nn.init.xavier_uniform_(m.weight)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></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="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
|
|
<span class="lineno">35</span> <span class="n">residual</span> <span class="o">=</span> <span class="n">x</span>
|
|
<span class="lineno">36</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv_layer1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="lineno">37</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_batch_norm</span><span class="p">:</span>
|
|
<span class="lineno">38</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_norm_layer1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="lineno">39</span>
|
|
<span class="lineno">40</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">relu_layer</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="lineno">41</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv_layer2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="lineno">42</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_batch_norm</span><span class="p">:</span>
|
|
<span class="lineno">43</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_norm_layer2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="lineno">44</span>
|
|
<span class="lineno">45</span> <span class="n">x</span> <span class="o">+=</span> <span class="n">residual</span>
|
|
<span class="lineno">46</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">relu_layer</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="lineno">47</span> <span class="k">return</span> <span class="n">x</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>ResNet</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">50</span><span class="k">class</span> <span class="nc">ResNet</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</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">51</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">in_features</span><span class="p">,</span> <span class="n">num_class</span><span class="p">,</span> <span class="n">feature_channel_list</span><span class="p">,</span> <span class="n">batch_norm</span><span class="o">=</span> <span class="kc">False</span><span class="p">,</span> <span class="n">num_stacks</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">zero_init_residual</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
|
|
<span class="lineno">52</span> <span class="nb">super</span><span class="p">(</span><span class="n">ResNet</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
|
|
<span class="lineno">53</span> <span class="bp">self</span><span class="o">.</span><span class="n">in_features</span> <span class="o">=</span> <span class="n">in_features</span>
|
|
<span class="lineno">54</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_in_channel</span> <span class="o">=</span> <span class="n">in_features</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
|
|
<span class="lineno">55</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_class</span> <span class="o">=</span> <span class="n">num_class</span>
|
|
<span class="lineno">56</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_channel_list</span> <span class="o">=</span> <span class="n">feature_channel_list</span>
|
|
<span class="lineno">57</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_residual_blocks</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_channel_list</span><span class="p">)</span>
|
|
<span class="lineno">58</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_stacks</span> <span class="o">=</span> <span class="n">num_stacks</span>
|
|
<span class="lineno">59</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_norm</span> <span class="o">=</span> <span class="n">batch_norm</span>
|
|
<span class="lineno">60</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape_list</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="lineno">61</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">in_features</span><span class="p">)</span>
|
|
<span class="lineno">62</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">()</span>
|
|
<span class="lineno">63</span> <span class="bp">self</span><span class="o">.</span><span class="n">zero_init_residual</span><span class="o">=</span> <span class="n">zero_init_residual</span>
|
|
<span class="lineno">64</span> <span class="bp">self</span><span class="o">.</span><span class="n">build_</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>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">66</span> <span class="k">def</span> <span class="nf">build_</span><span class="p">(</span><span class="bp">self</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>track filter shape</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">68</span> <span class="n">cur_shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">GetCurShape</span><span class="p">()</span>
|
|
<span class="lineno">69</span> <span class="n">cur_shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">CalcConvOutShape</span><span class="p">(</span><span class="n">cur_shape</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">7</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</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">out_filters</span><span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_channel_list</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
|
|
<span class="lineno">70</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">cur_shape</span><span class="p">)</span>
|
|
<span class="lineno">71</span>
|
|
<span class="lineno">72</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">in_features</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
|
|
<span class="lineno">73</span> <span class="n">in_channels</span> <span class="o">=</span> <span class="mi">1</span>
|
|
<span class="lineno">74</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">75</span> <span class="n">in_channels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">in_features</span><span class="p">[</span><span class="mi">2</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>First Conv layer 7x7 stride=2, pad =1</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">78</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</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="n">in_channels</span><span class="p">,</span>
|
|
<span class="lineno">79</span> <span class="n">out_channels</span><span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_channel_list</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
|
|
<span class="lineno">80</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">7</span><span class="p">,</span>
|
|
<span class="lineno">81</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span>
|
|
<span class="lineno">82</span> <span class="n">padding</span><span class="o">=</span><span class="mi">3</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>batch norm</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">86</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_norm</span><span class="p">:</span> <span class="c1">#batch_norm</span>
|
|
<span class="lineno">87</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">feature_channel_list</span><span class="p">[</span><span class="mi">0</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>ReLU()</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">90</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">())</span>
|
|
<span class="lineno">91</span>
|
|
<span class="lineno">92</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_residual_blocks</span><span class="o">-</span><span class="mi">1</span><span class="p">):</span>
|
|
<span class="lineno">93</span> <span class="n">in_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_channel_list</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
|
|
<span class="lineno">94</span> <span class="n">out_size</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">feature_channel_list</span><span class="p">[</span><span class="n">i</span><span class="o">+</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="lineno">95</span>
|
|
<span class="lineno">96</span> <span class="n">res_block</span> <span class="o">=</span> <span class="n">ResBlock</span><span class="p">(</span><span class="n">in_size</span><span class="p">,</span> <span class="n">use_batch_norm</span><span class="o">=</span><span class="kc">True</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>
|
|
<h1>Stacking Residual blocks</h1>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">99</span> <span class="k">for</span> <span class="n">num</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_stacks</span><span class="p">):</span>
|
|
<span class="lineno">100</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">res_block</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>
|
|
<h1>Intermediate Conv and ReLU()</h1>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">103</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</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="n">in_size</span><span class="p">,</span>
|
|
<span class="lineno">104</span> <span class="n">out_channels</span><span class="o">=</span> <span class="n">out_size</span><span class="p">,</span>
|
|
<span class="lineno">105</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span>
|
|
<span class="lineno">106</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
|
|
<span class="lineno">107</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</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>track filter shape</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">110</span> <span class="n">cur_shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">CalcConvOutShape</span><span class="p">(</span><span class="n">cur_shape</span><span class="p">,</span> <span class="n">kernel_size</span><span class="o">=</span><span class="mi">3</span><span class="p">,</span> <span class="n">padding</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span>
|
|
<span class="lineno">111</span> <span class="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">out_filters</span><span class="o">=</span><span class="n">out_size</span><span class="p">)</span>
|
|
<span class="lineno">112</span>
|
|
<span class="lineno">113</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">cur_shape</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>
|
|
<h1>batch norm</h1>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">116</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">batch_norm</span><span class="p">:</span> <span class="c1"># batch_norm</span>
|
|
<span class="lineno">117</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">BatchNorm2d</span><span class="p">(</span><span class="n">out_size</span><span class="p">))</span>
|
|
<span class="lineno">118</span>
|
|
<span class="lineno">119</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">ReLU</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>print(“shape list”, self.shape_list)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-18'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-18'>#</a>
|
|
</div>
|
|
<p>TODO include in the main loop
|
|
Last Residual block</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">125</span> <span class="n">res_block</span> <span class="o">=</span> <span class="n">ResBlock</span><span class="p">(</span><span class="n">out_size</span><span class="p">,</span> <span class="n">use_batch_norm</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
<span class="lineno">126</span> <span class="k">for</span> <span class="n">num</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">num_stacks</span><span class="p">):</span>
|
|
<span class="lineno">127</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">res_block</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-19'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-19'>#</a>
|
|
</div>
|
|
<p>Last AvgPool layer
|
|
self.module_list.append(nn.AvgPool2d(kernel_size=2, stride=2, padding=0))</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">131</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2d</span><span class="p">(</span><span class="n">kernel_size</span><span class="o">=</span><span class="mi">2</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></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-20'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-20'>#</a>
|
|
</div>
|
|
<p>track filter shape</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">134</span> <span class="n">cur_shape</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">CalcConvOutShape</span><span class="p">(</span><span class="n">cur_shape</span><span class="p">,</span> <span class="n">kernel_size</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="n">stride</span><span class="o">=</span><span class="mi">2</span><span class="p">,</span> <span class="n">out_filters</span><span class="o">=</span><span class="n">out_size</span><span class="p">)</span>
|
|
<span class="lineno">135</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">cur_shape</span><span class="p">)</span>
|
|
<span class="lineno">136</span>
|
|
<span class="lineno">137</span> <span class="n">s</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">GetCurShape</span><span class="p">()</span>
|
|
<span class="lineno">138</span> <span class="n">in_features</span> <span class="o">=</span> <span class="n">s</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">s</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">*</span> <span class="n">s</span><span class="p">[</span><span class="mi">2</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>Initialization</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">141</span> <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">modules</span><span class="p">():</span>
|
|
<span class="lineno">142</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">m</span><span class="p">,</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">):</span>
|
|
<span class="lineno">143</span> <span class="n">nn</span><span class="o">.</span><span class="n">init</span><span class="o">.</span><span class="n">kaiming_normal_</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">weight</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>nn.init.xavier_uniform_(m.weight)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-23'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-23'>#</a>
|
|
</div>
|
|
<p>if self.zero_init_residual:
|
|
for m in self.modules():
|
|
if isinstance(m, ResBlock):
|
|
nn.init.constant_(m.batch_norm_layer1.weight, 0)
|
|
nn.init.constant_(m.batch_norm_layer2.weight, 0)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-24'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-24'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">152</span> <span class="k">def</span> <span class="nf">GetCurShape</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
|
<span class="lineno">153</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">shape_list</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-25'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-25'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">155</span> <span class="k">def</span> <span class="nf">CalcConvFormula</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">W</span><span class="p">,</span> <span class="n">K</span><span class="p">,</span> <span class="n">P</span><span class="p">,</span> <span class="n">S</span><span class="p">):</span>
|
|
<span class="lineno">156</span> <span class="k">return</span> <span class="nb">int</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">floor</span><span class="p">(((</span><span class="n">W</span> <span class="o">-</span> <span class="n">K</span> <span class="o">+</span> <span class="mi">2</span> <span class="o">*</span> <span class="n">P</span><span class="p">)</span> <span class="o">/</span> <span class="n">S</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-26'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-26'>#</a>
|
|
</div>
|
|
<p>https://stackoverflow.com/questions/53580088/calculate-the-output-size-in-convolution-layer
|
|
Calculate the output shape after applying a convolution</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">160</span> <span class="k">def</span> <span class="nf">CalcConvOutShape</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">in_shape</span><span class="p">,</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">stride</span><span class="p">,</span> <span class="n">out_filters</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>Multiple options for different kernel shapes</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">162</span> <span class="k">if</span> <span class="nb">type</span><span class="p">(</span><span class="n">kernel_size</span><span class="p">)</span> <span class="o">==</span> <span class="nb">int</span><span class="p">:</span>
|
|
<span class="lineno">163</span> <span class="n">out_shape</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">CalcConvFormula</span><span class="p">(</span><span class="n">in_shape</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">kernel_size</span><span class="p">,</span> <span class="n">padding</span><span class="p">,</span> <span class="n">stride</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">2</span><span class="p">)]</span>
|
|
<span class="lineno">164</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">165</span> <span class="n">out_shape</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">CalcConvFormula</span><span class="p">(</span><span class="n">in_shape</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">kernel_size</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">padding</span><span class="p">,</span> <span class="n">stride</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">2</span><span class="p">)]</span>
|
|
<span class="lineno">166</span>
|
|
<span class="lineno">167</span> <span class="k">return</span> <span class="p">(</span><span class="n">out_shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">out_shape</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="n">out_filters</span><span class="p">)</span> <span class="c1"># , batch_size... but not necessary.</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-28'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-28'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">169</span> <span class="k">def</span> <span class="nf">AddMLP</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">MLP</span><span class="p">):</span>
|
|
<span class="lineno">170</span> <span class="k">if</span> <span class="n">MLP</span><span class="p">:</span>
|
|
<span class="lineno">171</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">MLP</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>def MLP(self, in_features, num_classes, use_batch_norm=False, use_dropout=False, use_softmax=False):
|
|
return nn.ReLU(nn.Linear(in_features, num_classes))</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-30'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-30'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">176</span> <span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span>
|
|
<span class="lineno">177</span> <span class="k">for</span> <span class="n">mod_name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="p">:</span>
|
|
<span class="lineno">178</span> <span class="n">x</span> <span class="o">=</span> <span class="n">mod_name</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="lineno">179</span> <span class="n">x</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">size</span><span class="p">(</span><span class="mi">0</span><span class="p">),</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span> <span class="c1"># flat #TODO check if it works</span>
|
|
<span class="lineno">180</span> <span class="k">return</span> <span class="n">x</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>
|
|
<script>
|
|
function handleImages() {
|
|
var images = document.querySelectorAll('p>img')
|
|
|
|
console.log(images);
|
|
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> |