chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
@@ -0,0 +1,417 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="si">
|
||||
<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="CIFAR 10 මත දර්ශන ට්රාන්ස්ෆෝමර් (VIT) පුහුණු කරන්න"/>
|
||||
|
||||
<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="CIFAR 10 මත දර්ශන ට්රාන්ස්ෆෝමර් (VIT) පුහුණු කරන්න"/>
|
||||
<meta name="twitter:description" content="CIFAR 10 මත දර්ශන ට්රාන්ස්ෆෝමර් (VIT) පුහුණු කරන්න"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/transformers/vit/experiment.html"/>
|
||||
<meta property="og:title" content="CIFAR 10 මත දර්ශන ට්රාන්ස්ෆෝමර් (VIT) පුහුණු කරන්න"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="CIFAR 10 මත දර්ශන ට්රාන්ස්ෆෝමර් (VIT) පුහුණු කරන්න"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="CIFAR 10 මත දර්ශන ට්රාන්ස්ෆෝමර් (VIT) පුහුණු කරන්න"/>
|
||||
<meta property="og:description" content="CIFAR 10 මත දර්ශන ට්රාන්ස්ෆෝමර් (VIT) පුහුණු කරන්න"/>
|
||||
|
||||
<title>CIFAR 10 මත දර්ශන ට්රාන්ස්ෆෝමර් (VIT) පුහුණු කරන්න</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/transformers/vit/experiment.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>
|
||||
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">transformers</a>
|
||||
<a class="parent" href="index.html">vit</a>
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
|
||||
<img alt="Github"
|
||||
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
|
||||
style="max-width:100%;"/></a>
|
||||
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
|
||||
<img alt="Twitter"
|
||||
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
||||
style="max-width:100%;"/></a>
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/transformers/vit/experiment.py" target="_blank">
|
||||
View code on Github</a>
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-0'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-0'>#</a>
|
||||
</div>
|
||||
<h1>CIFAR10 මත <a href="index.html">දර්ශන ට්රාන්ස්ෆෝමර් (VIT)</a> පුහුණු කරන්න</h1>
|
||||
<p><a href="https://app.labml.ai/run/afdd5332188b11edbdf543360515b595"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen"></a></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">13</span><span></span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">experiment</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">option</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">labml_nn.experiments.cifar10</span> <span class="kn">import</span> <span class="n">CIFAR10Configs</span>
|
||||
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">labml_nn.transformers</span> <span class="kn">import</span> <span class="n">TransformerConfigs</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-1'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-1'>#</a>
|
||||
</div>
|
||||
<h2>වින්යාසකිරීම්</h2>
|
||||
<p>සියලුමදත්ත කට්ටල ආශ්රිත වින්යාසයන්, ප්රශස්තකරණය සහ පුහුණු ලූපයක් නිර්වචනය කරන අපි භාවිතා <a href="../../experiments/cifar10.html"><code class="highlight"><span></span><span class="n">CIFAR10Configs</span></code>
|
||||
</a> කරමු. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">19</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">CIFAR10Configs</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><a href="../configs.html#TransformerConfigs">ට්රාන්ස්ෆෝමර් <a href="../models.html#TransformerLayer">ස්ථරය ලබා ගැනීම සඳහා ට්රාන්ස්ෆෝමර්</a> වින්යාසයන්</a> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">29</span> <span class="n">transformer</span><span class="p">:</span> <span class="n">TransformerConfigs</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>පැච්එකක ප්රමාණය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">32</span> <span class="n">patch_size</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">4</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>වර්ගීකරණහිසෙහි සැඟවුණු ස්ථරයේ ප්රමාණය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">34</span> <span class="n">n_hidden_classification</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2048</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>කර්තව්යයේපන්ති ගණන </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">36</span> <span class="n">n_classes</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-6'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-6'>#</a>
|
||||
</div>
|
||||
<p> ට්රාන්ස්ෆෝමර්වින්යාස සාදන්න</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">39</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">transformer</span><span class="p">)</span>
|
||||
<span class="lineno">40</span><span class="k">def</span> <span class="nf">_transformer</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">44</span> <span class="k">return</span> <span class="n">TransformerConfigs</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
<h3>ආකෘතියසාදන්න</h3>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">47</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">model</span><span class="p">)</span>
|
||||
<span class="lineno">48</span><span class="k">def</span> <span class="nf">_vit</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">Configs</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">52</span> <span class="kn">from</span> <span class="nn">labml_nn.transformers.vit</span> <span class="kn">import</span> <span class="n">VisionTransformer</span><span class="p">,</span> <span class="n">LearnedPositionalEmbeddings</span><span class="p">,</span> <span class="n">ClassificationHead</span><span class="p">,</span> \
|
||||
<span class="lineno">53</span> <span class="n">PatchEmbeddings</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>ට්රාන්ස්ෆෝමර් <a href="../configs.html#TransformerConfigs">මානකරණ සිට ට්රාන්ස්ෆෝමර්</a> ප්රමාණය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">56</span> <span class="n">d_model</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">d_model</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>දර්ශනට්රාන්ස්ෆෝමරයක් සාදන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">58</span> <span class="k">return</span> <span class="n">VisionTransformer</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">encoder_layer</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">transformer</span><span class="o">.</span><span class="n">n_layers</span><span class="p">,</span>
|
||||
<span class="lineno">59</span> <span class="n">PatchEmbeddings</span><span class="p">(</span><span class="n">d_model</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">patch_size</span><span class="p">,</span> <span class="mi">3</span><span class="p">),</span>
|
||||
<span class="lineno">60</span> <span class="n">LearnedPositionalEmbeddings</span><span class="p">(</span><span class="n">d_model</span><span class="p">),</span>
|
||||
<span class="lineno">61</span> <span class="n">ClassificationHead</span><span class="p">(</span><span class="n">d_model</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">n_hidden_classification</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">n_classes</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-12'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-12'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">64</span><span class="k">def</span> <span class="nf">main</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>අත්හදාබැලීම සාදන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">66</span> <span class="n">experiment</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="s1">'ViT'</span><span class="p">,</span> <span class="n">comment</span><span class="o">=</span><span class="s1">'cifar10'</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>
|
||||
<p>වින්යාසයන්සාදන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">68</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</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>වින්යාසයන්පූරණය කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">70</span> <span class="n">experiment</span><span class="o">.</span><span class="n">configs</span><span class="p">(</span><span class="n">conf</span><span class="p">,</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>ප්රශස්තකරණය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">72</span> <span class="s1">'optimizer.optimizer'</span><span class="p">:</span> <span class="s1">'Adam'</span><span class="p">,</span>
|
||||
<span class="lineno">73</span> <span class="s1">'optimizer.learning_rate'</span><span class="p">:</span> <span class="mf">2.5e-4</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>ට්රාන්ස්ෆෝමර්කාවැද්දීමේ ප්රමාණය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">76</span> <span class="s1">'transformer.d_model'</span><span class="p">:</span> <span class="mi">512</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>
|
||||
<p>ඊපොච්සහ කණ්ඩායම් ප්රමාණය පුහුණු කිරීම </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">79</span> <span class="s1">'epochs'</span><span class="p">:</span> <span class="mi">32</span><span class="p">,</span>
|
||||
<span class="lineno">80</span> <span class="s1">'train_batch_size'</span><span class="p">:</span> <span class="mi">64</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>පුහුණුකිරීම සඳහා CIFAR 10 රූප </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">83</span> <span class="s1">'train_dataset'</span><span class="p">:</span> <span class="s1">'cifar10_train_augmented'</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>CIFARවර්ධනය කරන්න එපා 10 වලංගු කිරීම සඳහා රූප </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">85</span> <span class="s1">'valid_dataset'</span><span class="p">:</span> <span class="s1">'cifar10_valid_no_augment'</span><span class="p">,</span>
|
||||
<span class="lineno">86</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>ඉතිරිකිරීම/පැටවීම සඳහා ආකෘතිය සකසන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">88</span> <span class="n">experiment</span><span class="o">.</span><span class="n">add_pytorch_models</span><span class="p">({</span><span class="s1">'model'</span><span class="p">:</span> <span class="n">conf</span><span class="o">.</span><span class="n">model</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>අත්හදාබැලීම ආරම්භ කර පුහුණු ලූපය ක්රියාත්මක කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">90</span> <span class="k">with</span> <span class="n">experiment</span><span class="o">.</span><span class="n">start</span><span class="p">():</span>
|
||||
<span class="lineno">91</span> <span class="n">conf</span><span class="o">.</span><span class="n">run</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-23'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-23'>#</a>
|
||||
</div>
|
||||
<p> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">95</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
||||
<span class="lineno">96</span> <span class="n">main</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<a href="https://papers.labml.ai">Trending Research Papers</a>
|
||||
<a href="https://labml.ai">labml.ai</a>
|
||||
</div>
|
||||
</div>
|
||||
<script src=../../interactive.js?v=1"></script>
|
||||
<script>
|
||||
function handleImages() {
|
||||
var images = document.querySelectorAll('p>img')
|
||||
|
||||
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>
|
||||
@@ -0,0 +1,703 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="si">
|
||||
<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="PyTorch ක්රියාත්මක කිරීම/නිබන්ධනය “රූපයක් වටිනවා 16x16 වචන: පරිමාණයෙන් රූප හඳුනාගැනීම සඳහා ට්රාන්ස්ෆෝමර්”"/>
|
||||
|
||||
<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="දර්ශන ට්රාන්ස්ෆෝමර් (VIT)"/>
|
||||
<meta name="twitter:description" content="PyTorch ක්රියාත්මක කිරීම/නිබන්ධනය “රූපයක් වටිනවා 16x16 වචන: පරිමාණයෙන් රූප හඳුනාගැනීම සඳහා ට්රාන්ස්ෆෝමර්”"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/transformers/vit/index.html"/>
|
||||
<meta property="og:title" content="දර්ශන ට්රාන්ස්ෆෝමර් (VIT)"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="දර්ශන ට්රාන්ස්ෆෝමර් (VIT)"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="දර්ශන ට්රාන්ස්ෆෝමර් (VIT)"/>
|
||||
<meta property="og:description" content="PyTorch ක්රියාත්මක කිරීම/නිබන්ධනය “රූපයක් වටිනවා 16x16 වචන: පරිමාණයෙන් රූප හඳුනාගැනීම සඳහා ට්රාන්ස්ෆෝමර්”"/>
|
||||
|
||||
<title>දර්ශන ට්රාන්ස්ෆෝමර් (VIT)</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/transformers/vit/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>
|
||||
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">transformers</a>
|
||||
<a class="parent" href="index.html">vit</a>
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
|
||||
<img alt="Github"
|
||||
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
|
||||
style="max-width:100%;"/></a>
|
||||
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
|
||||
<img alt="Twitter"
|
||||
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
||||
style="max-width:100%;"/></a>
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/transformers/vit/__init__.py" target="_blank">
|
||||
View code on Github</a>
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-0'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-0'>#</a>
|
||||
</div>
|
||||
<h1>දර්ශනට්රාන්ස්ෆෝමර් (VIT)</h1>
|
||||
<p>මෙයඅ <a href="https://pytorch.org">පයිටෝච්</a> කඩදාසි ක්රියාත්මක කිරීම <a href="https://papers.labml.ai/paper/2010.11929">රූපයක් වටිනවා 16x16 වචන: පරිමාණයෙන් රූප හඳුනාගැනීම සඳහා ට්රාන්ස්ෆෝමර්</a> . </p>
|
||||
<p>දර්ශනට්රාන්ස්ෆෝමරය කිසිදු කැටි ගැසුණු ස්ථර නොමැතිව රූප සඳහා පිරිසිදු ට්රාන්ස්ෆෝමරයක් යොදයි. ඔවුන් රූපය පැච් බවට බෙදී ඇති අතර පැච් කාවැද්දීම් මත ට්රාන්ස්ෆෝමරයක් යොදයි. <a href="#PathEmbeddings">පැච් කාවැද්දීම්</a> ජනනය කරනු ලබන්නේ පැච් වල පැතලි පික්සල් අගයන් සඳහා සරල රේඛීය පරිවර්තනයක් යෙදීමෙනි. එවිට සම්මත ට්රාන්ස්ෆෝමර් එන්කෝඩරයක් පැච් කාවැද්දීම් සමඟ වර්ගීකරණ ටෝකනයක් සමඟ පෝෂණය <code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
වේ. රූපය එම්එල්පී සමඟ වර්ගීකරණය කිරීම සඳහා <code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
ටෝකනයේ කේතනය භාවිතා කරයි. </p>
|
||||
<p>පැච්සමඟ ට්රාන්ස්ෆෝමරය පෝෂණය කරන විට, පැච් කාවැද්දීම් වලට උගත් ස්ථානීය කාවැද්දීම් එකතු කරනු ලැබේ, මන්ද එම පැච් කාවැද්දීම් වලින් එම පැච් එක කොතැනද යන්න පිළිබඳ කිසිදු තොරතුරක් නොමැති බැවිනි. ස්ථානීය කාවැද්දීම් යනු එක් එක් පැච් ස්ථානය සඳහා දෛශික සමූහයක් වන අතර අනෙක් පරාමිතීන් සමඟ ශ්රේණියේ සම්භවය සමඟ පුහුණු වේ. </p>
|
||||
<p>විශාලදත්ත කට්ටල පිළිබඳ පූර්ව පුහුණුව ලැබූ විට VITs හොඳින් ක්රියා කරයි. කඩදාසි යෝජනා කරන්නේ එම්එල්පී වර්ගීකරණ හිසක් සමඟ ඒවා පෙර පුහුණු කිරීම සහ හොඳින් සුසර කිරීමේදී තනි රේඛීය තට්ටුවක් භාවිතා කිරීමයි. කඩදාසි මිලියන 300 ක රූප දත්ත කට්ටලයක් මත පෙර පුහුණු කරන ලද VIT සමඟ SOTA පරාජය කරයි. පැච් ප්රමාණය එලෙසම තබා ගනිමින් අනුමානය අතරතුර ඔවුන් ඉහළ විභේදන රූප භාවිතා කරයි. නව පැච් ස්ථාන සඳහා ස්ථානීය කාවැද්දීම් ගණනය කරනු ලබන්නේ ස්ථානීය කාවැද්දීම් ඉගෙනීම අන්තර්ග්රහණය කිරීමෙනි. </p>
|
||||
<p><a href="experiment.html">CIFA-10 හි VIT පුහුණු කරන අත්හදා බැලීමක්</a> මෙන්න. එය කුඩා දත්ත සමුදාය මත පුහුණු වෙනවා නිසා මෙය ඉතා හොඳින් කරන්නේ නැහැ. එය ඕනෑම කෙනෙකුට VITs සමඟ ධාවනය කර සෙල්ලම් කළ හැකි සරල අත්හදා බැලීමකි. </p>
|
||||
<p><a href="https://app.labml.ai/run/afdd5332188b11edbdf543360515b595"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen"></a></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">45</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">46</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">47</span>
|
||||
<span class="lineno">48</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span>
|
||||
<span class="lineno">49</span><span class="kn">from</span> <span class="nn">labml_nn.transformers</span> <span class="kn">import</span> <span class="n">TransformerLayer</span>
|
||||
<span class="lineno">50</span><span class="kn">from</span> <span class="nn">labml_nn.utils</span> <span class="kn">import</span> <span class="n">clone_module_list</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-1'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-1'>#</a>
|
||||
</div>
|
||||
<p> <a id="PatchEmbeddings"></a></p>
|
||||
<h2>පැච්කාවැද්දීම් ලබා ගන්න</h2>
|
||||
<p>කඩදාසිරූපය සමාන ප්රමාණයේ පැච් වලට බෙදී ඇති අතර එක් එක් පැච් එක සඳහා පැතලි පික්සල් මත රේඛීය පරිවර්තනයක් සිදු කරයි. </p>
|
||||
<p>අපිඑකම දේ ක්රියාත්මක කිරීම සරල නිසා, කැටි ගැසුණු ස්ථරයක් හරහා ක්රියාත්මක කරමු. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">53</span><span class="k">class</span> <span class="nc">PatchEmbeddings</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-2'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-2'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">d_model</span></code>
|
||||
ට්රාන්ස්ෆෝමර් කාවැද්දීම් ප්රමාණය වේ </li>
|
||||
<li><code class="highlight"><span></span><span class="n">patch_size</span></code>
|
||||
පැච් වල ප්රමාණයයි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">in_channels</span></code>
|
||||
ආදාන රූපයේ නාලිකා ගණන (rgb සඳහා 3)</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">65</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">d_model</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">patch_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">in_channels</span><span class="p">:</span> <span class="nb">int</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">71</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</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>අපිකර්නල් ප්රමාණයෙන් හා ලප ප්රමාණය සමාන stride දිග සමග convolution ස්ථරය නිර්මාණය කරන්න. මෙය රූපය පැච් වලට බෙදීමට හා එක් එක් පැච් එකේ රේඛීය පරිවර්තනයක් කිරීමට සමාන වේ. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">76</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv</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">in_channels</span><span class="p">,</span> <span class="n">d_model</span><span class="p">,</span> <span class="n">patch_size</span><span class="p">,</span> <span class="n">stride</span><span class="o">=</span><span class="n">patch_size</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-5'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-5'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
|
||||
යනු හැඩයේ ආදාන රූපයයි <code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">]</span></code>
|
||||
</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">78</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="n">torch</span><span class="o">.</span><span class="n">Tensor</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>කැටිගැසුණු ස්ථරය යොදන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">83</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv</span><span class="p">(</span><span class="n">x</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>හැඩයලබා ගන්න. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">85</span> <span class="n">bs</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h</span><span class="p">,</span> <span class="n">w</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">shape</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>හැඩයටනැවත සකස් කරන්න <code class="highlight"><span></span><span class="p">[</span><span class="n">patches</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">d_model</span><span class="p">]</span></code>
|
||||
</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">87</span> <span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">permute</span><span class="p">(</span><span class="mi">2</span><span class="p">,</span> <span class="mi">3</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="lineno">88</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">h</span> <span class="o">*</span> <span class="n">w</span><span class="p">,</span> <span class="n">bs</span><span class="p">,</span> <span class="n">c</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>පැච්කාවැද්දීම් ආපසු ලබා දෙන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">91</span> <span class="k">return</span> <span class="n">x</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-10'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-10'>#</a>
|
||||
</div>
|
||||
<p> <a id="LearnedPositionalEmbeddings"></a></p>
|
||||
<h2>පරාමිතිකරණයකළ ස්ථානීය කේතීකරණ එකතු කරන්න</h2>
|
||||
<p>මෙයපැච් කාවැද්දීම් සඳහා උගත් ස්ථානීය කාවැද්දීම් එකතු කරයි. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">94</span><span class="k">class</span> <span class="nc">LearnedPositionalEmbeddings</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-11'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-11'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">d_model</span></code>
|
||||
ට්රාන්ස්ෆෝමර් කාවැද්දීම් ප්රමාණය වේ </li>
|
||||
<li><code class="highlight"><span></span><span class="n">max_len</span></code>
|
||||
පැච් වල උපරිම ගණන</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">103</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">d_model</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">max_len</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">5_000</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">108</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</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>එක්එක් ස්ථානය සඳහා ස්ථානීය කාවැද්දීම් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">110</span> <span class="bp">self</span><span class="o">.</span><span class="n">positional_encodings</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Parameter</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">max_len</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">d_model</span><span class="p">),</span> <span class="n">requires_grad</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-14'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-14'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
|
||||
හැඩයේ පැච් කාවැද්දීම් වේ <code class="highlight"><span></span><span class="p">[</span><span class="n">patches</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">d_model</span><span class="p">]</span></code>
|
||||
</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">112</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="n">torch</span><span class="o">.</span><span class="n">Tensor</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>දීඇති පැච් සඳහා ස්ථානීය කාවැද්දීම් ලබා ගන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">117</span> <span class="n">pe</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">positional_encodings</span><span class="p">[:</span><span class="n">x</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</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>පැච්කාවැද්දීම් වලට එකතු කර ආපසු යන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">119</span> <span class="k">return</span> <span class="n">x</span> <span class="o">+</span> <span class="n">pe</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-17'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-17'>#</a>
|
||||
</div>
|
||||
<p> <a id="ClassificationHead"></a></p>
|
||||
<h2>එම්එල්පීවර්ගීකරණ හිස</h2>
|
||||
<p><code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
ටෝකන් කාවැද්දීම මත පදනම්ව රූපය වර්ගීකරණය කිරීම සඳහා ස්ථර දෙකේ එම්එල්පී හිස මෙයයි. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">122</span><span class="k">class</span> <span class="nc">ClassificationHead</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-18'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-18'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">d_model</span></code>
|
||||
ට්රාන්ස්ෆෝමර් කාවැද්දීම ප්රමාණය වේ </li>
|
||||
<li><code class="highlight"><span></span><span class="n">n_hidden</span></code>
|
||||
සැඟවුණු ස්ථරයේ ප්රමාණයයි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">n_classes</span></code>
|
||||
වර්ගීකරණ කාර්යයේ පන්ති ගණන වේ</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">130</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">d_model</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_hidden</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_classes</span><span class="p">:</span> <span class="nb">int</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">136</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</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>පළමුස්ථරය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">138</span> <span class="bp">self</span><span class="o">.</span><span class="n">linear1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">d_model</span><span class="p">,</span> <span class="n">n_hidden</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>සක්රීයකිරීම </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">140</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span> <span class="o">=</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-22'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-22'>#</a>
|
||||
</div>
|
||||
<p>දෙවනස්ථරය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">142</span> <span class="bp">self</span><span class="o">.</span><span class="n">linear2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">n_hidden</span><span class="p">,</span> <span class="n">n_classes</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-23'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-23'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
|
||||
<code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
ටෝකනය සඳහා ට්රාන්ස්ෆෝමර් කේතනය වේ</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">144</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="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-24'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-24'>#</a>
|
||||
</div>
|
||||
<p>පළමුස්ථරය සහ සක්රිය කිරීම </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">149</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">act</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">linear1</span><span class="p">(</span><span class="n">x</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>
|
||||
<p>දෙවනස්ථරය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">151</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">linear2</span><span class="p">(</span><span class="n">x</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> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">154</span> <span class="k">return</span> <span class="n">x</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-27'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-27'>#</a>
|
||||
</div>
|
||||
<h2>දැක්මට්රාන්ස්ෆෝමර්</h2>
|
||||
<p>මෙය <a href="#PatchEmbeddings">පැච් කාවැද්දීම්</a>, <a href="#LearnedPositionalEmbeddings">ස්ථානීය කාවැද්දීම්, ට්රාන්ස්ෆෝමර්</a>සහ <a href="#ClassificationHead">වර්ගීකරණ හිස</a>ඒකාබද්ධ කරයි. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">157</span><span class="k">class</span> <span class="nc">VisionTransformer</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-28'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-28'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">transformer_layer</span></code>
|
||||
යනු තනි <a href="../models.html#TransformerLayer">ට්රාන්ස්ෆෝමර් ස්ථරයක</a>පිටපතක්. ට්රාන්ස්ෆෝමරය සෑදීම සඳහා අපි එහි පිටපත් සාදන්නෙමු <code class="highlight"><span></span><span class="n">n_layers</span></code>
|
||||
. </li>
|
||||
<li><code class="highlight"><span></span><span class="n">n_layers</span></code>
|
||||
<a href="../models.html#TransformerLayer">ට්රාන්ස්ෆෝමර් ස්ථර</a>ගණන වේ. </li>
|
||||
<li><code class="highlight"><span></span><span class="n">patch_emb</span></code>
|
||||
<a href="#PatchEmbeddings">පැච් කාවැද්දීම් ස්ථරය</a>වේ. </li>
|
||||
<li><code class="highlight"><span></span><span class="n">pos_emb</span></code>
|
||||
යනු <a href="#LearnedPositionalEmbeddings">ස්ථානීය කාවැද්දීම් ස්ථරයයි</a>. </li>
|
||||
<li><code class="highlight"><span></span><span class="n">classification</span></code>
|
||||
<a href="#ClassificationHead">වර්ගීකරණ හිස</a>වේ. </li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">165</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">transformer_layer</span><span class="p">:</span> <span class="n">TransformerLayer</span><span class="p">,</span> <span class="n">n_layers</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
|
||||
<span class="lineno">166</span> <span class="n">patch_emb</span><span class="p">:</span> <span class="n">PatchEmbeddings</span><span class="p">,</span> <span class="n">pos_emb</span><span class="p">:</span> <span class="n">LearnedPositionalEmbeddings</span><span class="p">,</span>
|
||||
<span class="lineno">167</span> <span class="n">classification</span><span class="p">:</span> <span class="n">ClassificationHead</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">176</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-30'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-30'>#</a>
|
||||
</div>
|
||||
<p>පැච්කාවැද්දීම් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">178</span> <span class="bp">self</span><span class="o">.</span><span class="n">patch_emb</span> <span class="o">=</span> <span class="n">patch_emb</span>
|
||||
<span class="lineno">179</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_emb</span> <span class="o">=</span> <span class="n">pos_emb</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-31'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-31'>#</a>
|
||||
</div>
|
||||
<p>වර්ගීකරණහිස </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">181</span> <span class="bp">self</span><span class="o">.</span><span class="n">classification</span> <span class="o">=</span> <span class="n">classification</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-32'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-32'>#</a>
|
||||
</div>
|
||||
<p>ට්රාන්ස්ෆෝමර්ස්ථරයේ පිටපත් සාදන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">183</span> <span class="bp">self</span><span class="o">.</span><span class="n">transformer_layers</span> <span class="o">=</span> <span class="n">clone_module_list</span><span class="p">(</span><span class="n">transformer_layer</span><span class="p">,</span> <span class="n">n_layers</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-33'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-33'>#</a>
|
||||
</div>
|
||||
<p><code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
කාවැද්දීම ටෝකනය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">186</span> <span class="bp">self</span><span class="o">.</span><span class="n">cls_token_emb</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Parameter</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">transformer_layer</span><span class="o">.</span><span class="n">size</span><span class="p">),</span> <span class="n">requires_grad</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-34'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-34'>#</a>
|
||||
</div>
|
||||
<p>අවසානසාමාන්යකරණ ස්තරය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">188</span> <span class="bp">self</span><span class="o">.</span><span class="n">ln</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">([</span><span class="n">transformer_layer</span><span class="o">.</span><span class="n">size</span><span class="p">])</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-35'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-35'>#</a>
|
||||
</div>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">x</span></code>
|
||||
යනු හැඩයේ ආදාන රූපයයි <code class="highlight"><span></span><span class="p">[</span><span class="n">batch_size</span><span class="p">,</span> <span class="n">channels</span><span class="p">,</span> <span class="n">height</span><span class="p">,</span> <span class="n">width</span><span class="p">]</span></code>
|
||||
</li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">190</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="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-36'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-36'>#</a>
|
||||
</div>
|
||||
<p>පැච්කාවැද්දීම් ලබා ගන්න. මෙය හැඩයේ ආතතිකයක් ලබා දෙයි <code class="highlight"><span></span><span class="p">[</span><span class="n">patches</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">,</span> <span class="n">d_model</span><span class="p">]</span></code>
|
||||
</p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">195</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">patch_emb</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-37'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-37'>#</a>
|
||||
</div>
|
||||
<p>ස්ථානීයකාවැද්දීම් එකතු කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">197</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pos_emb</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-38'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-38'>#</a>
|
||||
</div>
|
||||
<p>ට්රාන්ස්ෆෝමරයපෝෂණය කිරීමට පෙර <code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
ටෝකන් කාවැද්දීම් සංයුක්ත කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">199</span> <span class="n">cls_token_emb</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">cls_token_emb</span><span class="o">.</span><span class="n">expand</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">x</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">],</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span>
|
||||
<span class="lineno">200</span> <span class="n">x</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">([</span><span class="n">cls_token_emb</span><span class="p">,</span> <span class="n">x</span><span class="p">])</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-39'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-39'>#</a>
|
||||
</div>
|
||||
<p>කිසිදුඅවධානයක් ආවරණ සහිත ට්රාන්ස්ෆෝමර් ස්ථර හරහා ගමන් කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">203</span> <span class="k">for</span> <span class="n">layer</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">transformer_layers</span><span class="p">:</span>
|
||||
<span class="lineno">204</span> <span class="n">x</span> <span class="o">=</span> <span class="n">layer</span><span class="p">(</span><span class="n">x</span><span class="o">=</span><span class="n">x</span><span class="p">,</span> <span class="n">mask</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-40'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-40'>#</a>
|
||||
</div>
|
||||
<p><code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
ටෝකනයේ ට්රාන්ස්ෆෝමර් ප්රතිදානය ලබා ගන්න (එය අනුපිළිවෙලෙහි පළමු වේ). </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">207</span> <span class="n">x</span> <span class="o">=</span> <span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-41'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-41'>#</a>
|
||||
</div>
|
||||
<p>ස්ථරයසාමාන්යකරණය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">210</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ln</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-42'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-42'>#</a>
|
||||
</div>
|
||||
<p>වර්ගීකරණහිස, පිවිසුම් ලබා ගැනීමට </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">213</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">classification</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-43'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-43'>#</a>
|
||||
</div>
|
||||
<p> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">216</span> <span class="k">return</span> <span class="n">x</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<a href="https://papers.labml.ai">Trending Research Papers</a>
|
||||
<a href="https://labml.ai">labml.ai</a>
|
||||
</div>
|
||||
</div>
|
||||
<script src=../../interactive.js?v=1"></script>
|
||||
<script>
|
||||
function handleImages() {
|
||||
var images = document.querySelectorAll('p>img')
|
||||
|
||||
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>
|
||||
@@ -0,0 +1,134 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="si">
|
||||
<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=" දර්ශන ට්රාන්ස්ෆෝමර් (VIT)"/>
|
||||
<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/transformers/vit/readme.html"/>
|
||||
<meta property="og:title" content=" දර්ශන ට්රාන්ස්ෆෝමර් (VIT)"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content=" දර්ශන ට්රාන්ස්ෆෝමර් (VIT)"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content=" දර්ශන ට්රාන්ස්ෆෝමර් (VIT)"/>
|
||||
<meta property="og:description" content=""/>
|
||||
|
||||
<title> දර්ශන ට්රාන්ස්ෆෝමර් (VIT)</title>
|
||||
<link rel="shortcut icon" href="/icon.png"/>
|
||||
<link rel="stylesheet" href="../../pylit.css?v=1">
|
||||
<link rel="canonical" href="https://nn.labml.ai/transformers/vit/readme.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>
|
||||
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">transformers</a>
|
||||
<a class="parent" href="index.html">vit</a>
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
|
||||
<img alt="Github"
|
||||
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
|
||||
style="max-width:100%;"/></a>
|
||||
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
|
||||
<img alt="Twitter"
|
||||
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
||||
style="max-width:100%;"/></a>
|
||||
</p>
|
||||
<p>
|
||||
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/transformers/vit/readme.md" target="_blank">
|
||||
View code on Github</a>
|
||||
</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-0'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-0'>#</a>
|
||||
</div>
|
||||
<h1><a href="https://nn.labml.ai/transformer/vit/index.html">දර්ශන ට්රාන්ස්ෆෝමර් (VIT)</a></h1>
|
||||
<p>මෙයඅ <a href="https://pytorch.org">පයිටෝච්</a> කඩදාසි ක්රියාත්මක කිරීම <a href="https://papers.labml.ai/paper/2010.11929">රූපයක් වටිනවා 16x16 වචන: පරිමාණයෙන් රූප හඳුනාගැනීම සඳහා ට්රාන්ස්ෆෝමර්</a> . </p>
|
||||
<p>දර්ශනට්රාන්ස්ෆෝමරය කිසිදු කැටි ගැසුණු ස්ථර නොමැතිව රූප සඳහා පිරිසිදු ට්රාන්ස්ෆෝමරයක් යොදයි. ඔවුන් රූපය පැච් බවට බෙදී ඇති අතර පැච් කාවැද්දීම් මත ට්රාන්ස්ෆෝමරයක් යොදයි. <a href="https://nn.labml.ai/transformer/vit/index.html#PathEmbeddings">පැච් කාවැද්දීම්</a> ජනනය කරනු ලබන්නේ පැච් වල පැතලි පික්සල් අගයන් සඳහා සරල රේඛීය පරිවර්තනයක් යෙදීමෙනි. එවිට සම්මත ට්රාන්ස්ෆෝමර් එන්කෝඩරයක් පැච් කාවැද්දීම් සමඟ වර්ගීකරණ ටෝකනයක් සමඟ පෝෂණය <code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
වේ. රූපය එම්එල්පී සමඟ වර්ගීකරණය කිරීම සඳහා <code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
|
||||
ටෝකනයේ කේතනය භාවිතා කරයි. </p>
|
||||
<p>පැච්සමඟ ට්රාන්ස්ෆෝමරය පෝෂණය කරන විට, පැච් කාවැද්දීම් වලට උගත් ස්ථානීය කාවැද්දීම් එකතු කරනු ලැබේ, මන්ද එම පැච් කාවැද්දීම් වලින් එම පැච් එක කොතැනද යන්න පිළිබඳ කිසිදු තොරතුරක් නොමැති බැවිනි. ස්ථානීය කාවැද්දීම් යනු එක් එක් පැච් ස්ථානය සඳහා දෛශික සමූහයක් වන අතර අනෙක් පරාමිතීන් සමඟ ශ්රේණියේ සම්භවය සමඟ පුහුණු වේ. </p>
|
||||
<p>විශාලදත්ත කට්ටල පිළිබඳ පූර්ව පුහුණුව ලැබූ විට VITs හොඳින් ක්රියා කරයි. කඩදාසි යෝජනා කරන්නේ එම්එල්පී වර්ගීකරණ හිසක් සමඟ ඒවා පෙර පුහුණු කිරීම සහ හොඳින් සුසර කිරීමේදී තනි රේඛීය තට්ටුවක් භාවිතා කිරීමයි. කඩදාසි මිලියන 300 ක රූප දත්ත කට්ටලයක් මත පෙර පුහුණු කරන ලද VIT සමඟ SOTA පරාජය කරයි. පැච් ප්රමාණය එලෙසම තබා ගනිමින් අනුමානය අතරතුර ඔවුන් ඉහළ විභේදන රූප භාවිතා කරයි. නව පැච් ස්ථාන සඳහා ස්ථානීය කාවැද්දීම් ගණනය කරනු ලබන්නේ ස්ථානීය කාවැද්දීම් ඉගෙනීම අන්තර්ග්රහණය කිරීමෙනි. </p>
|
||||
<p><a href="https://nn.labml.ai/transformer/vit/experiment.html">CIFA-10 හි VIT පුහුණු කරන අත්හදා බැලීමක්</a> මෙන්න. එය කුඩා දත්ත සමුදාය මත පුහුණු වෙනවා නිසා මෙය ඉතා හොඳින් කරන්නේ නැහැ. එය ඕනෑම කෙනෙකුට VITs සමඟ ධාවනය කර සෙල්ලම් කළ හැකි සරල අත්හදා බැලීමකි. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class='footer'>
|
||||
<a href="https://papers.labml.ai">Trending Research Papers</a>
|
||||
<a href="https://labml.ai">labml.ai</a>
|
||||
</div>
|
||||
</div>
|
||||
<script src=../../interactive.js?v=1"></script>
|
||||
<script>
|
||||
function handleImages() {
|
||||
var images = document.querySelectorAll('p>img')
|
||||
|
||||
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>
|
||||
Reference in New Issue
Block a user