mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-11-01 03:43:09 +08:00
322 lines
22 KiB
HTML
322 lines
22 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="mlp.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/mlp.html"/>
|
|
<meta property="og:title" content="mlp.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="mlp.py"/>
|
|
<meta property="og:description" content=""/>
|
|
|
|
<title>mlp.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/mlp.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/mlp.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'>
|
|
<div class='section-link'>
|
|
<a href='#section-0'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">3</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="lineno">4</span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-1'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-1'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">6</span><span class="k">class</span> <span class="nc">MLP</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-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">7</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span>
|
|
<span class="lineno">8</span> <span class="p">,</span> <span class="n">in_features</span>
|
|
<span class="lineno">9</span> <span class="p">,</span> <span class="n">out_features</span>
|
|
<span class="lineno">10</span> <span class="p">,</span> <span class="n">hidden_layers</span>
|
|
<span class="lineno">11</span> <span class="p">,</span> <span class="n">actv_func</span>
|
|
<span class="lineno">12</span> <span class="p">,</span> <span class="n">pre_module_list</span><span class="o">=</span><span class="kc">None</span>
|
|
<span class="lineno">13</span> <span class="p">,</span> <span class="n">use_dropout</span><span class="o">=</span><span class="kc">False</span>
|
|
<span class="lineno">14</span> <span class="p">,</span> <span class="n">use_batch_norm</span><span class="o">=</span><span class="kc">False</span>
|
|
<span class="lineno">15</span> <span class="p">,</span> <span class="n">use_softmax</span><span class="o">=</span><span class="kc">True</span>
|
|
<span class="lineno">16</span> <span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="s2">"cpu"</span>
|
|
<span class="lineno">17</span> <span class="p">):</span>
|
|
<span class="lineno">18</span> <span class="nb">super</span><span class="p">(</span><span class="n">MLP</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="lineno">20</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">21</span> <span class="bp">self</span><span class="o">.</span><span class="n">out_features</span> <span class="o">=</span> <span class="n">out_features</span>
|
|
<span class="lineno">22</span> <span class="bp">self</span><span class="o">.</span><span class="n">num_hidden_layers</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">hidden_layers</span><span class="p">)</span>
|
|
<span class="lineno">23</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_layers</span> <span class="o">=</span> <span class="n">hidden_layers</span>
|
|
<span class="lineno">24</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_dropout</span> <span class="o">=</span> <span class="n">use_dropout</span>
|
|
<span class="lineno">25</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">26</span> <span class="bp">self</span><span class="o">.</span><span class="n">actv_func</span> <span class="o">=</span> <span class="n">actv_func</span>
|
|
<span class="lineno">27</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_softmax</span> <span class="o">=</span> <span class="n">use_softmax</span>
|
|
<span class="lineno">28</span>
|
|
<span class="lineno">29</span> <span class="bp">self</span><span class="o">.</span><span class="n">device</span> <span class="o">=</span> <span class="n">device</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>Add on to another model</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">32</span> <span class="k">if</span> <span class="n">pre_module_list</span><span class="p">:</span>
|
|
<span class="lineno">33</span> <span class="bp">self</span><span class="o">.</span><span class="n">module_list</span> <span class="o">=</span> <span class="n">pre_module_list</span>
|
|
<span class="lineno">34</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">35</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">36</span>
|
|
<span class="lineno">37</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-4'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-4'>#</a>
|
|
</div>
|
|
<p>Send to gpu</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">40</span> <span class="bp">self</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-5'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-5'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">42</span> <span class="k">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-6'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-6'>#</a>
|
|
</div>
|
|
<p>Activation Functions for Fully connected layers #
|
|
Start with input dimensions</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">45</span> <span class="n">dim</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">in_features</span>
|
|
<span class="lineno">46</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_hidden_layers</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-7'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-7'>#</a>
|
|
</div>
|
|
<p>Create a fully connected layer between the last layer
|
|
and the current hidden layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">49</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">Linear</span><span class="p">(</span><span class="n">dim</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_layers</span><span class="p">[</span><span class="n">i</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>Update the current dimension</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">51</span> <span class="n">dim</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_layers</span><span class="p">[</span><span class="n">i</span><span class="p">]</span>
|
|
<span class="lineno">52</span>
|
|
<span class="lineno">53</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">54</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">BatchNorm1d</span><span class="p">(</span><span class="n">dim</span><span class="p">,</span> <span class="n">affine</span><span class="o">=</span><span class="kc">True</span><span class="p">)</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>Add the Activation function</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">57</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="bp">self</span><span class="o">.</span><span class="n">GetActivation</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">actv_func</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> <span class="p">)</span>
|
|
<span class="lineno">58</span>
|
|
<span class="lineno">59</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_dropout</span><span class="p">:</span>
|
|
<span class="lineno">60</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">Dropout</span><span class="p">(</span><span class="n">p</span><span class="o">=</span><span class="mf">0.10</span><span class="p">)</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>Fully connect to output dimensions</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">63</span> <span class="k">if</span> <span class="n">dim</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">out_features</span><span class="p">:</span>
|
|
<span class="lineno">64</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">Linear</span><span class="p">(</span><span class="n">dim</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">out_features</span><span class="p">)</span> <span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-11'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-11'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">67</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></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-12'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-12'>#</a>
|
|
</div>
|
|
<p>Flatten the 2d image into 1d
|
|
Also convert into float for FC layer</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">torch</span><span class="o">.</span><span class="n">flatten</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">float</span><span class="p">(),</span> <span class="n">start_dim</span><span class="o">=</span><span class="mi">1</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>Apply each layer in the module list</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">73</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="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">module_list</span><span class="p">)</span> <span class="p">):</span>
|
|
<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">module_list</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">x</span><span class="p">)</span>
|
|
<span class="lineno">75</span>
|
|
<span class="lineno">76</span> <span class="k">return</span> <span class="n">x</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-14'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-14'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">78</span> <span class="k">def</span> <span class="nf">GetActivation</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s2">"relu"</span><span class="p">):</span>
|
|
<span class="lineno">79</span> <span class="k">if</span> <span class="n">name</span> <span class="o">==</span> <span class="s2">"relu"</span><span class="p">:</span>
|
|
<span class="lineno">80</span> <span class="k">return</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</span><span class="p">()</span>
|
|
<span class="lineno">81</span> <span class="k">elif</span> <span class="n">name</span> <span class="o">==</span> <span class="s2">"leakyrelu"</span><span class="p">:</span>
|
|
<span class="lineno">82</span> <span class="k">return</span> <span class="n">nn</span><span class="o">.</span><span class="n">LeakyReLU</span><span class="p">()</span>
|
|
<span class="lineno">83</span> <span class="k">elif</span> <span class="n">name</span> <span class="o">==</span> <span class="s2">"Sigmoid"</span><span class="p">:</span>
|
|
<span class="lineno">84</span> <span class="k">return</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sigmoid</span><span class="p">()</span>
|
|
<span class="lineno">85</span> <span class="k">elif</span> <span class="n">name</span> <span class="o">==</span> <span class="s2">"Tanh"</span><span class="p">:</span>
|
|
<span class="lineno">86</span> <span class="k">return</span> <span class="n">nn</span><span class="o">.</span><span class="n">Tanh</span><span class="p">()</span>
|
|
<span class="lineno">87</span> <span class="k">elif</span> <span class="n">name</span> <span class="o">==</span> <span class="s2">"Identity"</span><span class="p">:</span>
|
|
<span class="lineno">88</span> <span class="k">return</span> <span class="n">nn</span><span class="o">.</span><span class="n">Identity</span><span class="p">()</span>
|
|
<span class="lineno">89</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">90</span> <span class="k">return</span> <span class="n">nn</span><span class="o">.</span><span class="n">ReLU</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> |