mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-14 01:13:00 +08:00
294 lines
20 KiB
HTML
294 lines
20 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="pretrained_nets.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/pretrained_nets.html"/>
|
|
<meta property="og:title" content="pretrained_nets.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="pretrained_nets.py"/>
|
|
<meta property="og:description" content=""/>
|
|
|
|
<title>pretrained_nets.py</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/resnets/pretrained_nets.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>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/resnets/pretrained_nets.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">3</span><span></span><span class="kn">from</span> <span class="nn">utils.train</span> <span class="kn">import</span> <span class="n">Trainer</span> <span class="c1"># Default custom training class</span>
|
|
<span class="lineno">4</span><span class="kn">from</span> <span class="nn">models.resnet</span> <span class="kn">import</span> <span class="o">*</span>
|
|
<span class="lineno">5</span><span class="kn">from</span> <span class="nn">torchvision</span> <span class="kn">import</span> <span class="n">models</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>GPU Check</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">8</span><span class="n">device</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s2">"cuda:0"</span> <span class="k">if</span> <span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span><span class="p">()</span> <span class="k">else</span> <span class="s2">"cpu"</span><span class="p">)</span>
|
|
<span class="lineno">9</span><span class="nb">print</span><span class="p">(</span><span class="s2">"Device: "</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">device</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>
|
|
<p>Use different train/test data augmentations</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">12</span><span class="n">transform_test</span> <span class="o">=</span> <span class="n">transforms</span><span class="o">.</span><span class="n">Compose</span><span class="p">(</span>
|
|
<span class="lineno">13</span> <span class="p">[</span><span class="n">transforms</span><span class="o">.</span><span class="n">ToTensor</span><span class="p">(),</span>
|
|
<span class="lineno">14</span> <span class="n">transforms</span><span class="o">.</span><span class="n">Normalize</span><span class="p">((</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">),</span> <span class="p">(</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</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>Get Cifar 10 Datasets</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">17</span><span class="n">save</span><span class="o">=</span><span class="s1">'./data/Cifar10'</span>
|
|
<span class="lineno">18</span><span class="n">transform_train</span> <span class="o">=</span> <span class="n">transforms</span><span class="o">.</span><span class="n">Compose</span><span class="p">([</span>
|
|
<span class="lineno">19</span> <span class="n">transforms</span><span class="o">.</span><span class="n">RandomHorizontalFlip</span><span class="p">(</span><span class="n">p</span><span class="o">=</span><span class="mf">1.0</span><span class="p">),</span>
|
|
<span class="lineno">20</span> <span class="n">transforms</span><span class="o">.</span><span class="n">RandomRotation</span><span class="p">(</span><span class="mi">20</span><span class="p">),</span>
|
|
<span class="lineno">21</span> <span class="n">transforms</span><span class="o">.</span><span class="n">RandomCrop</span><span class="p">(</span><span class="mi">32</span><span class="p">,</span> <span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">2</span><span class="p">),</span> <span class="n">pad_if_needed</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">padding_mode</span><span class="o">=</span><span class="s1">'constant'</span><span class="p">),</span>
|
|
<span class="lineno">22</span> <span class="n">transforms</span><span class="o">.</span><span class="n">ToTensor</span><span class="p">(),</span>
|
|
<span class="lineno">23</span> <span class="n">transforms</span><span class="o">.</span><span class="n">Normalize</span><span class="p">((</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">),</span> <span class="p">(</span><span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</span><span class="p">,</span> <span class="mf">0.5</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>Get Cifar 10 Datasets</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">26</span><span class="n">trainset</span> <span class="o">=</span> <span class="n">torchvision</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">CIFAR10</span><span class="p">(</span><span class="n">root</span><span class="o">=</span><span class="n">save</span><span class="p">,</span> <span class="n">train</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">download</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">transform</span><span class="o">=</span><span class="n">transform_train</span><span class="p">)</span>
|
|
<span class="lineno">27</span><span class="n">testset</span> <span class="o">=</span> <span class="n">torchvision</span><span class="o">.</span><span class="n">datasets</span><span class="o">.</span><span class="n">CIFAR10</span><span class="p">(</span><span class="n">root</span><span class="o">=</span><span class="n">save</span><span class="p">,</span> <span class="n">train</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">download</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">transform</span><span class="o">=</span><span class="n">transform_test</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>Get Cifar 10 Dataloaders</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">30</span><span class="n">trainloader</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span><span class="p">(</span><span class="n">trainset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span>
|
|
<span class="lineno">31</span> <span class="n">shuffle</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</span><span class="p">)</span>
|
|
<span class="lineno">32</span>
|
|
<span class="lineno">33</span><span class="n">testloader</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">DataLoader</span><span class="p">(</span><span class="n">testset</span><span class="p">,</span> <span class="n">batch_size</span><span class="o">=</span><span class="mi">64</span><span class="p">,</span>
|
|
<span class="lineno">34</span> <span class="n">shuffle</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">num_workers</span><span class="o">=</span><span class="mi">4</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>
|
|
<h6></h6>
|
|
<p>Load the pre-trained model</p>
|
|
<h6></h6>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">40</span><span class="n">model_ft</span> <span class="o">=</span> <span class="n">models</span><span class="o">.</span><span class="n">resnet18</span><span class="p">(</span><span class="n">pretrained</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
<span class="lineno">41</span><span class="n">num_ftrs</span> <span class="o">=</span> <span class="n">model_ft</span><span class="o">.</span><span class="n">fc</span><span class="o">.</span><span class="n">in_features</span>
|
|
<span class="lineno">42</span><span class="n">model_ft</span><span class="o">.</span><span class="n">fc</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">43</span> <span class="n">nn</span><span class="o">.</span><span class="n">Dropout</span><span class="p">(</span><span class="mf">0.5</span><span class="p">),</span>
|
|
<span class="lineno">44</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">num_ftrs</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
|
|
<span class="lineno">45</span><span class="p">)</span>
|
|
<span class="lineno">46</span>
|
|
<span class="lineno">47</span>
|
|
<span class="lineno">48</span><span class="n">model_ft</span> <span class="o">=</span> <span class="n">model_ft</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</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>Loss function</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">51</span><span class="n">cost</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">CrossEntropyLoss</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>Optimizer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">54</span><span class="n">lr</span> <span class="o">=</span> <span class="mf">0.0005</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>opt = optim.SGD(model_ft.parameters(), lr=lr, momentum=0.9)</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">56</span><span class="n">opt</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Adam</span><span class="p">(</span><span class="n">model_ft</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">lr</span><span class="o">=</span><span class="n">lr</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.95</span><span class="p">),</span> <span class="n">weight_decay</span><span class="o">=</span><span class="mf">1e-4</span><span class="p">)</span> <span class="c1">#0.0005 l2_factor.item()</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>Create a trainer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">59</span><span class="n">trainer</span> <span class="o">=</span> <span class="n">Trainer</span><span class="p">(</span><span class="n">model_ft</span><span class="p">,</span> <span class="n">opt</span><span class="p">,</span> <span class="n">cost</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s2">"Transfer-learning"</span><span class="p">,</span><span class="n">lr</span><span class="o">=</span><span class="n">lr</span> <span class="p">,</span> <span class="n">use_lr_schedule</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">device</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>Run training</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">62</span><span class="n">epochs</span> <span class="o">=</span> <span class="mi">25</span>
|
|
<span class="lineno">63</span><span class="n">trainer</span><span class="o">.</span><span class="n">Train</span><span class="p">(</span><span class="n">trainloader</span><span class="p">,</span> <span class="n">epochs</span><span class="p">,</span> <span class="n">testloader</span><span class="o">=</span><span class="n">testloader</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>trainer.Train(trainloader, epochs) # check train error</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">66</span><span class="nb">print</span><span class="p">(</span><span class="s1">'done'</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>
|
|
<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> |