mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-11-02 13:00:17 +08:00
unescape *
This commit is contained in:
Varuna Jayasiri
@ -24,6 +24,8 @@
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../../pylit.css">
|
||||
<link rel="canonical" href="https://nn.labml.ai/gan/dcgan/index.html"/>
|
||||
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.18/dist/katex.min.css" integrity="sha384-zTROYFVGOfTw7JV7KUu8udsvW2fx4lWOsCEDqhBreBwlHI4ioVRtmIvEThzJHGET" crossorigin="anonymous">
|
||||
|
||||
<!-- Global site tag (gtag.js) - Google Analytics -->
|
||||
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
|
||||
<script>
|
||||
@ -68,9 +70,9 @@
|
||||
<a href='#section-0'>#</a>
|
||||
</div>
|
||||
<h1>Deep Convolutional Generative Adversarial Networks (DCGAN)</h1>
|
||||
<p>This is a <a href="https://pytorch.org">PyTorch</a> implementation of paper
|
||||
<a href="https://papers.labml.ai/paper/1511.06434">Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks</a>.</p>
|
||||
<p>This is a <a href="https://pytorch.org">PyTorch</a> implementation of paper <a href="https://papers.labml.ai/paper/1511.06434">Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks</a>.</p>
|
||||
<p>This implementation is based on the <a href="https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html">PyTorch DCGAN Tutorial</a>.</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">15</span><span></span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span>
|
||||
@ -87,9 +89,9 @@
|
||||
<a href='#section-1'>#</a>
|
||||
</div>
|
||||
<h3>Convolutional Generator Network</h3>
|
||||
<p>This is similar to the de-convolutional network used for CelebA faces,
|
||||
but modified for MNIST images.</p>
|
||||
<p><img src="https://pytorch.org/tutorials/_images/dcgan_generator.png" style="max-width:90%" /></p>
|
||||
<p>This is similar to the de-convolutional network used for CelebA faces, but modified for MNIST images.</p>
|
||||
<p><img src="https://pytorch.org/tutorials/_images/dcgan_generator.png" style="max-width:90%" /></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">23</span><span class="k">class</span> <span class="nc">Generator</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||||
@ -112,7 +114,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-3'>#</a>
|
||||
</div>
|
||||
<p>The input is $1 \times 1$ with 100 channels</p>
|
||||
<p>The input is <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">1</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">1</span></span></span></span> with 100 channels </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">36</span> <span class="bp">self</span><span class="o">.</span><span class="n">layers</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span></pre></div>
|
||||
@ -123,7 +126,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<p>This gives $3 \times 3$ output</p>
|
||||
<p>This gives <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">3</span></span></span></span> output </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">38</span> <span class="n">nn</span><span class="o">.</span><span class="n">ConvTranspose2d</span><span class="p">(</span><span class="mi">100</span><span class="p">,</span> <span class="mi">1024</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||||
@ -136,7 +140,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-5'>#</a>
|
||||
</div>
|
||||
<p>This gives $7 \times 7$</p>
|
||||
<p>This gives <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">7</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">7</span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">42</span> <span class="n">nn</span><span class="o">.</span><span class="n">ConvTranspose2d</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="mi">512</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||||
@ -149,7 +154,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-6'>#</a>
|
||||
</div>
|
||||
<p>This gives $14 \times 14$</p>
|
||||
<p>This gives <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">14</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">14</span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">46</span> <span class="n">nn</span><span class="o">.</span><span class="n">ConvTranspose2d</span><span class="p">(</span><span class="mi">512</span><span class="p">,</span> <span class="mi">256</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||||
@ -162,7 +168,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-7'>#</a>
|
||||
</div>
|
||||
<p>This gives $28 \times 28$</p>
|
||||
<p>This gives <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">28</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">28</span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">50</span> <span class="n">nn</span><span class="o">.</span><span class="n">ConvTranspose2d</span><span class="p">(</span><span class="mi">256</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||||
@ -188,7 +195,10 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-9'>#</a>
|
||||
</div>
|
||||
<p>Change from shape <code>[batch_size, 100]</code> to <code>[batch_size, 100, 1, 1]</code></p>
|
||||
<p>Change from shape <code>[batch_size, 100]</code>
|
||||
to <code>[batch_size, 100, 1, 1]</code>
|
||||
</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">58</span> <span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">unsqueeze</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">unsqueeze</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
|
||||
@ -202,6 +212,7 @@ but modified for MNIST images.</p>
|
||||
<a href='#section-10'>#</a>
|
||||
</div>
|
||||
<h3>Convolutional Discriminator Network</h3>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">63</span><span class="k">class</span> <span class="nc">Discriminator</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||||
@ -224,7 +235,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-12'>#</a>
|
||||
</div>
|
||||
<p>The input is $28 \times 28$ with one channel</p>
|
||||
<p>The input is <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">28</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">28</span></span></span></span> with one channel </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">71</span> <span class="bp">self</span><span class="o">.</span><span class="n">layers</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Sequential</span><span class="p">(</span></pre></div>
|
||||
@ -235,7 +247,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-13'>#</a>
|
||||
</div>
|
||||
<p>This gives $14 \times 14$</p>
|
||||
<p>This gives <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">14</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">14</span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">73</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">256</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||||
@ -247,7 +260,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-14'>#</a>
|
||||
</div>
|
||||
<p>This gives $7 \times 7$</p>
|
||||
<p>This gives <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">7</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">7</span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">76</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">256</span><span class="p">,</span> <span class="mi">512</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||||
@ -260,7 +274,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-15'>#</a>
|
||||
</div>
|
||||
<p>This gives $3 \times 3$</p>
|
||||
<p>This gives <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">3</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">3</span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">80</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</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="mi">3</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||||
@ -273,7 +288,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-16'>#</a>
|
||||
</div>
|
||||
<p>This gives $1 \times 1$</p>
|
||||
<p>This gives <span class="katex"><span class="katex-html" aria-hidden="true"><span class="base"><span class="strut" style="height:0.72777em;vertical-align:-0.08333em;"></span><span class="mord">1</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">×</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">1</span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">84</span> <span class="n">nn</span><span class="o">.</span><span class="n">Conv2d</span><span class="p">(</span><span class="mi">1024</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||||
@ -316,8 +332,8 @@ but modified for MNIST images.</p>
|
||||
<div class='section-link'>
|
||||
<a href='#section-19'>#</a>
|
||||
</div>
|
||||
<p>We import the <a href="../original/experiment.html">simple gan experiment</a> and change the
|
||||
generator and discriminator networks</p>
|
||||
<p>We import the <a href="../original/experiment.html">simple gan experiment</a> and change the generator and discriminator networks </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">104</span><span class="n">calculate</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">generator</span><span class="p">,</span> <span class="s1">'cnn'</span><span class="p">,</span> <span class="k">lambda</span> <span class="n">c</span><span class="p">:</span> <span class="n">Generator</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>
|
||||
@ -352,24 +368,6 @@ generator and discriminator networks</p>
|
||||
<a href="https://labml.ai">labml.ai</a>
|
||||
</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')
|
||||
|
||||
Reference in New Issue
Block a user