mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-14 09:31:42 +08:00
416 lines
32 KiB
HTML
416 lines
32 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="train.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/utils/train.html"/>
|
|
<meta property="og:title" content="train.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="train.py"/>
|
|
<meta property="og:description" content=""/>
|
|
|
|
<title>train.py</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/resnets/utils/train.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">utils</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/resnets/utils/train.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">import</span> <span class="nn">torch</span>
|
|
<span class="lineno">4</span><span class="kn">from</span> <span class="nn">torch.utils.data</span> <span class="kn">import</span> <span class="n">DataLoader</span><span class="p">,</span> <span class="n">ConcatDataset</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>from sklearn.model_selection import KFold
|
|
from torch.utils.data.sampler import SubsetRandomSampler</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">8</span><span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
|
|
<span class="lineno">9</span><span class="kn">from</span> <span class="nn">pylab</span> <span class="kn">import</span> <span class="o">*</span>
|
|
<span class="lineno">10</span><span class="kn">import</span> <span class="nn">os</span>
|
|
<span class="lineno">11</span>
|
|
<span class="lineno">12</span><span class="kn">from</span> <span class="nn">torch.optim.lr_scheduler</span> <span class="kn">import</span> <span class="n">ReduceLROnPlateau</span><span class="p">,</span> <span class="n">StepLR</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">16</span><span class="k">class</span> <span class="nc">Trainer</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">net</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">"default"</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mf">0.0005</span><span class="p">,</span> <span class="n">use_lr_schedule</span> <span class="o">=</span><span class="kc">False</span> <span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
|
<span class="lineno">18</span> <span class="bp">self</span><span class="o">.</span><span class="n">net</span> <span class="o">=</span> <span class="n">net</span>
|
|
<span class="lineno">19</span> <span class="bp">self</span><span class="o">.</span><span class="n">opt</span> <span class="o">=</span> <span class="n">opt</span>
|
|
<span class="lineno">20</span> <span class="bp">self</span><span class="o">.</span><span class="n">cost</span> <span class="o">=</span> <span class="n">cost</span>
|
|
<span class="lineno">21</span> <span class="bp">self</span><span class="o">.</span><span class="n">device</span> <span class="o">=</span> <span class="n">device</span>
|
|
<span class="lineno">22</span> <span class="bp">self</span><span class="o">.</span><span class="n">epoch</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="lineno">23</span> <span class="bp">self</span><span class="o">.</span><span class="n">start_epoch</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="lineno">24</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="n">name</span>
|
|
<span class="lineno">25</span>
|
|
<span class="lineno">26</span> <span class="bp">self</span><span class="o">.</span><span class="n">lr</span> <span class="o">=</span> <span class="n">lr</span>
|
|
<span class="lineno">27</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_lr_schedule</span> <span class="o">=</span> <span class="n">use_lr_schedule</span>
|
|
<span class="lineno">28</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_lr_schedule</span><span class="p">:</span>
|
|
<span class="lineno">29</span> <span class="bp">self</span><span class="o">.</span><span class="n">scheduler</span> <span class="o">=</span> <span class="n">ReduceLROnPlateau</span><span class="p">(</span> <span class="bp">self</span><span class="o">.</span><span class="n">opt</span><span class="p">,</span> <span class="s1">'max'</span><span class="p">,</span> <span class="n">factor</span><span class="o">=</span><span class="mf">0.1</span><span class="p">,</span> <span class="n">patience</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">threshold</span><span class="o">=</span><span class="mf">0.00001</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">True</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>self.scheduler = StepLR(self.opt, step_size=15, gamma=0.1)</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>
|
|
<p>Train loop over epochs. Optinal use testloader to return test accuracy after each epoch</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">33</span> <span class="k">def</span> <span class="nf">Train</span><span class="p">(</span><span class="bp">self</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="kc">None</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>Enable Dropout</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-7'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-7'>#</a>
|
|
</div>
|
|
<p>Record loss/accuracies</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">37</span> <span class="n">loss</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">epochs</span><span class="p">)</span>
|
|
<span class="lineno">38</span> <span class="bp">self</span><span class="o">.</span><span class="n">epoch</span> <span class="o">=</span> <span class="mi">0</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>If testloader is used, loss will be the accuracy</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">41</span> <span class="k">for</span> <span class="n">epoch</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">start_epoch</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">start_epoch</span><span class="o">+</span><span class="n">epochs</span><span class="p">):</span>
|
|
<span class="lineno">42</span> <span class="bp">self</span><span class="o">.</span><span class="n">epoch</span> <span class="o">=</span> <span class="n">epoch</span><span class="o">+</span><span class="mi">1</span>
|
|
<span class="lineno">43</span>
|
|
<span class="lineno">44</span> <span class="bp">self</span><span class="o">.</span><span class="n">net</span><span class="o">.</span><span class="n">train</span><span class="p">()</span> <span class="c1"># Enable Dropout</span>
|
|
<span class="lineno">45</span> <span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">trainloader</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>Get the inputs; data is a list of [inputs, labels]</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">47</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">:</span>
|
|
<span class="lineno">48</span> <span class="n">images</span><span class="p">,</span> <span class="n">labels</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">),</span> <span class="n">data</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
|
<span class="lineno">49</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">50</span> <span class="n">images</span><span class="p">,</span> <span class="n">labels</span> <span class="o">=</span> <span class="n">data</span>
|
|
<span class="lineno">51</span>
|
|
<span class="lineno">52</span> <span class="bp">self</span><span class="o">.</span><span class="n">opt</span><span class="o">.</span><span class="n">zero_grad</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>Forward + backward + optimize</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">54</span> <span class="n">outputs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">net</span><span class="p">(</span><span class="n">images</span><span class="p">)</span>
|
|
<span class="lineno">55</span> <span class="n">epoch_loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cost</span><span class="p">(</span><span class="n">outputs</span><span class="p">,</span> <span class="n">labels</span><span class="p">)</span>
|
|
<span class="lineno">56</span> <span class="n">epoch_loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span>
|
|
<span class="lineno">57</span> <span class="bp">self</span><span class="o">.</span><span class="n">opt</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
|
<span class="lineno">58</span>
|
|
<span class="lineno">59</span> <span class="n">loss</span><span class="p">[</span><span class="n">epoch</span><span class="p">]</span> <span class="o">+=</span> <span class="n">epoch_loss</span><span class="o">.</span><span class="n">item</span><span class="p">()</span>
|
|
<span class="lineno">60</span>
|
|
<span class="lineno">61</span> <span class="k">if</span> <span class="n">testloader</span><span class="p">:</span>
|
|
<span class="lineno">62</span> <span class="n">loss</span><span class="p">[</span><span class="n">epoch</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">Test</span><span class="p">(</span><span class="n">testloader</span><span class="p">)</span>
|
|
<span class="lineno">63</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">64</span> <span class="n">loss</span><span class="p">[</span><span class="n">epoch</span><span class="p">]</span> <span class="o">/=</span> <span class="nb">len</span><span class="p">(</span><span class="n">trainloader</span><span class="p">)</span>
|
|
<span class="lineno">65</span>
|
|
<span class="lineno">66</span> <span class="nb">print</span><span class="p">(</span><span class="s2">"Epoch </span><span class="si">%d</span><span class="s2"> Learning rate </span><span class="si">%.6f</span><span class="s2"> </span><span class="si">%s</span><span class="s2">: </span><span class="si">%.3f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span>
|
|
<span class="lineno">67</span> <span class="bp">self</span><span class="o">.</span><span class="n">epoch</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">opt</span><span class="o">.</span><span class="n">param_groups</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="s1">'lr'</span><span class="p">],</span> <span class="s2">"Accuracy"</span> <span class="k">if</span> <span class="n">testloader</span> <span class="k">else</span> <span class="s2">"Loss"</span><span class="p">,</span> <span class="n">loss</span><span class="p">[</span><span class="n">epoch</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>learning rate scheduler</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">70</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">use_lr_schedule</span><span class="p">:</span>
|
|
<span class="lineno">71</span> <span class="bp">self</span><span class="o">.</span><span class="n">scheduler</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="n">loss</span><span class="p">[</span><span class="n">epoch</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>self.scheduler.step()</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-13'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-13'>#</a>
|
|
</div>
|
|
<p>Saving best model</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">75</span> <span class="k">if</span> <span class="n">loss</span><span class="p">[</span><span class="n">epoch</span><span class="p">]</span> <span class="o">>=</span> <span class="n">torch</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">loss</span><span class="p">):</span>
|
|
<span class="lineno">76</span> <span class="bp">self</span><span class="o">.</span><span class="n">save_best_model</span><span class="p">({</span>
|
|
<span class="lineno">77</span> <span class="s1">'epoch'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">epoch</span><span class="p">,</span>
|
|
<span class="lineno">78</span> <span class="s1">'state_dict'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">net</span><span class="o">.</span><span class="n">state_dict</span><span class="p">(),</span>
|
|
<span class="lineno">79</span> <span class="s1">'optimizer'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">opt</span><span class="o">.</span><span class="n">state_dict</span><span class="p">(),</span>
|
|
<span class="lineno">80</span> <span class="p">})</span>
|
|
<span class="lineno">81</span>
|
|
<span class="lineno">82</span> <span class="k">return</span> <span class="n">loss</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-14'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-14'>#</a>
|
|
</div>
|
|
<p>Testing</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">85</span> <span class="k">def</span> <span class="nf">Test</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">testloader</span><span class="p">,</span> <span class="n">ret</span><span class="o">=</span><span class="s2">"accuracy"</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>Disable Dropout</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">87</span> <span class="bp">self</span><span class="o">.</span><span class="n">net</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-16'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-16'>#</a>
|
|
</div>
|
|
<p>Track correct and total</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">90</span> <span class="n">correct</span> <span class="o">=</span> <span class="mf">0.0</span>
|
|
<span class="lineno">91</span> <span class="n">total</span> <span class="o">=</span> <span class="mf">0.0</span>
|
|
<span class="lineno">92</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span>
|
|
<span class="lineno">93</span> <span class="k">for</span> <span class="n">data</span> <span class="ow">in</span> <span class="n">testloader</span><span class="p">:</span>
|
|
<span class="lineno">94</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">:</span>
|
|
<span class="lineno">95</span> <span class="n">images</span><span class="p">,</span> <span class="n">labels</span> <span class="o">=</span> <span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">),</span> <span class="n">data</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
|
<span class="lineno">96</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">97</span> <span class="n">images</span><span class="p">,</span> <span class="n">labels</span> <span class="o">=</span> <span class="n">data</span>
|
|
<span class="lineno">98</span>
|
|
<span class="lineno">99</span> <span class="n">outputs</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">net</span><span class="p">(</span><span class="n">images</span><span class="p">)</span>
|
|
<span class="lineno">100</span> <span class="n">_</span><span class="p">,</span> <span class="n">predicted</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="n">outputs</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
|
<span class="lineno">101</span> <span class="n">total</span> <span class="o">+=</span> <span class="n">labels</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="lineno">102</span> <span class="n">correct</span> <span class="o">+=</span> <span class="p">(</span><span class="n">predicted</span> <span class="o">==</span> <span class="n">labels</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span><span class="o">.</span><span class="n">item</span><span class="p">()</span>
|
|
<span class="lineno">103</span>
|
|
<span class="lineno">104</span> <span class="k">return</span> <span class="n">correct</span> <span class="o">/</span> <span class="n">total</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-17'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-17'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">106</span> <span class="k">def</span> <span class="nf">save_best_model</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">state</span><span class="p">):</span>
|
|
<span class="lineno">107</span> <span class="n">directory</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="s2">"./save/</span><span class="si">%s</span><span class="s2">-best-model/"</span><span class="o">%</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">))</span>
|
|
<span class="lineno">108</span> <span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">directory</span><span class="p">):</span>
|
|
<span class="lineno">109</span> <span class="n">os</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">directory</span><span class="p">)</span>
|
|
<span class="lineno">110</span> <span class="n">torch</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="s2">"</span><span class="si">%s</span><span class="s2">/model.pt"</span> <span class="o">%</span><span class="p">(</span><span class="n">directory</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-18'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-18'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">112</span> <span class="k">def</span> <span class="nf">save_checkpoint</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">state</span><span class="p">):</span>
|
|
<span class="lineno">113</span> <span class="n">directory</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">dirname</span><span class="p">(</span><span class="s2">"./save/</span><span class="si">%s</span><span class="s2">-checkpoints/"</span><span class="o">%</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">name</span><span class="p">))</span>
|
|
<span class="lineno">114</span> <span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">directory</span><span class="p">):</span>
|
|
<span class="lineno">115</span> <span class="n">os</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">directory</span><span class="p">)</span>
|
|
<span class="lineno">116</span> <span class="n">torch</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="s2">"</span><span class="si">%s</span><span class="s2">/model_epoch_</span><span class="si">%s</span><span class="s2">.pt"</span> <span class="o">%</span><span class="p">(</span><span class="n">directory</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">epoch</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>torch.save(state, “./save/checkpoints/model_epoch_%s.pt” % (self.epoch))</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre></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> |