mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-16 10:51:23 +08:00
583 lines
47 KiB
HTML
583 lines
47 KiB
HTML
<!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 ජනප්රිය ශ්රේණියේ සම්භවය පදනම් කරගත් ප්රශස්තිකරණවල PyTorch ක්රියාත්මක කිරීම/නිබන්ධන සමූහයක්. දැනට ආදම්, AMSGrad සහ RaDam ප්රශස්තකරණය ඇතුළත් වේ."/>
|
||
|
||
<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="ප්රශස්තකරණය"/>
|
||
<meta name="twitter:description" content="PyTorch ජනප්රිය ශ්රේණියේ සම්භවය පදනම් කරගත් ප්රශස්තිකරණවල PyTorch ක්රියාත්මක කිරීම/නිබන්ධන සමූහයක්. දැනට ආදම්, AMSGrad සහ RaDam ප්රශස්තකරණය ඇතුළත් වේ."/>
|
||
<meta name="twitter:site" content="@labmlai"/>
|
||
<meta name="twitter:creator" content="@labmlai"/>
|
||
|
||
<meta property="og:url" content="https://nn.labml.ai/optimizers/index.html"/>
|
||
<meta property="og:title" content="ප්රශස්තකරණය"/>
|
||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||
<meta property="og:site_name" content="ප්රශස්තකරණය"/>
|
||
<meta property="og:type" content="object"/>
|
||
<meta property="og:title" content="ප්රශස්තකරණය"/>
|
||
<meta property="og:description" content="PyTorch ජනප්රිය ශ්රේණියේ සම්භවය පදනම් කරගත් ප්රශස්තිකරණවල PyTorch ක්රියාත්මක කිරීම/නිබන්ධන සමූහයක්. දැනට ආදම්, AMSGrad සහ RaDam ප්රශස්තකරණය ඇතුළත් වේ."/>
|
||
|
||
<title>ප්රශස්තකරණය</title>
|
||
<link rel="shortcut icon" href="/icon.png"/>
|
||
<link rel="stylesheet" href="../pylit.css?v=1">
|
||
<link rel="canonical" href="https://nn.labml.ai/optimizers/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">optimizers</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/optimizers/__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>ප්රශස්තකරණය</h1>
|
||
<h2>ප්රශස්තිකරණක්රියාත්මක කිරීම්</h2>
|
||
<ul><li><a href="adam.html">ආදම් ප්රශස්තකරණය</a> </li>
|
||
<li><a href="amsgrad.html">AMSGrad ප්රශස්තකරණය</a> </li>
|
||
<li><a href="adam_warmup.html">උණුසුම් කිරීම සමඟ ආදම් ප්රශස්තකරණය</a> </li>
|
||
<li><a href="noam.html">නව ප්රශස්තකරණය</a> </li>
|
||
<li><a href="radam.html">නිවැරදි කරන ලද ආදම් ප්රශස්තකරණය</a> </li>
|
||
<li><a href="ada_belief.html">ADABelief ප්රශස්තකරණය</a></li></ul>
|
||
<p>මෙම <a href="mnist_experiment.html">MNIST උදාහරණය</a> මෙම ප්රශස්තකරණය භාවිතා කරයි. </p>
|
||
<h2>Genericබලපත්රය යටතේ අවසර ලබා ඇත අනුවර්තී ප්රතිස්ඨාපනය මූලික පන්තිය</h2>
|
||
<p>මෙමගොනුව <em>ආදම්</em> සහ එහි දිගු සඳහා පොදු පාදක පන්තියක් අර්ථ දක්වයි. මූලික පන්තිය භාවිතා කිරීමට උපකාරී වේ නැවත භාවිතා කිරීමේ හැකියාව නිසා අවම කේතයක් සහිත වෙනත් ප්රශස්තිකාරක ක්රියාත්මක කරන්න. </p>
|
||
<p>එල්2 බර ක්ෂය වීම සඳහා විශේෂ පන්තියක් ද අපි අර්ථ දක්වන්නෙමු, එවිට එක් එක් ප්රශස්තකරණය තුළ එය ක්රියාත්මක කිරීමට අපට අවශ්ය නොවන අතර ප්රශස්තිකාරක වෙනස් නොකර L1 වැනි වෙනත් බර දිරාපත් විය හැකිය. </p>
|
||
<p>PyTorchප්රශස්තකරණය පිළිබඳ සංකල්ප කිහිපයක් මෙන්න:</p>
|
||
<h3>පරාමිතිකණ්ඩායම්</h3>
|
||
<p>PyTorchකණ්ඩායම් පරාමිතීන් කණ්ඩායම් ලෙස හැඳින්වෙන කට්ටලවලට ප්රශස්තිකරණය කරයි. සෑම කණ්ඩායමකටම ඉගෙනුම් අනුපාත වැනි තමන්ගේම අධි පරාමිතීන් තිබිය හැකිය. </p>
|
||
<p>බොහෝපොදු අවස්ථාවන්හිදී එක් කණ්ඩායමක් පමණක් වනු ඇත. මෙය ඔබ ඔබේ ප්රශස්තකරණය ආරම්භ කරන විට,</p>
|
||
<pre class="highlight lang-python"><code><span></span><span class="n">Optimizer</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">())</span></code></pre>
|
||
<p>ප්රශස්තකරණයආරම්භ කිරීමේදී ඔබට බහු පරාමිති කණ්ඩායම් නිර්වචනය කළ හැකිය:</p>
|
||
<pre class="highlight lang-python"><code><span></span><span class="n">Optimizer</span><span class="p">([{</span><span class="s1">'params'</span><span class="p">:</span> <span class="n">model1</span><span class="o">.</span><span class="n">parameters</span><span class="p">()},</span> <span class="p">{</span><span class="s1">'params'</span><span class="p">:</span> <span class="n">model2</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="s1">'lr'</span><span class="p">:</span> <span class="mi">2</span><span class="p">}])</span></code></pre>
|
||
<p>මෙන්නඅපි කණ්ඩායම් ලැයිස්තුවක් සම්මත කරමු. සෑම කණ්ඩායමක්ම 'පරාමිති' යන යතුර යටතේ එහි පරාමිතීන් සහිත ශබ්දකෝෂයකි. ඔබ ඕනෑම අධි-පරාමිතීන් ද සඳහන් කරයි. අධි පරාමිතීන් අර්ථ දක්වා නොමැති නම් ඒවා ප්රශස්තිකරණ මට්ටමේ පෙරනිමි වෙත පෙරනිමිය වනු ඇත. </p>
|
||
<p>ඔබටමෙම කණ්ඩායම් වලට ප්රවේශ විය හැකිය (සහ පවා වෙනස් කරන්න), සහ ඒවායේ අධි-පරාමිතීන් සමඟ <code class="highlight"><span></span><span class="n">optimizer</span><span class="o">.</span><span class="n">param_groups</span></code>
|
||
. මට හමු වී ඇති බොහෝ ඉගෙනුම් අනුපාත කාලසටහන් ක්රියාත්මක කිරීම් මෙයට ප්රවේශ වී 'lr' වෙනස් කරයි. </p>
|
||
<h3>ජනපදය</h3>
|
||
<p>ප්රශස්තකරණයශබ්දකෝෂයක එක් එක් පරාමිතිය සඳහා (ටෙන්සර්) ප්රාන්ත (ශබ්දකෝෂයක්) පවත්වා ගනී <code class="highlight"><span></span><span class="n">optimizer</span><span class="o">.</span><span class="n">state</span></code>
|
||
. ප්රශස්තකරණය on ාතීය සාමාන්යය වැනි දේවල් පවත්වා ගෙන යන්නේ මෙහිදීය. </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">62</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">Any</span>
|
||
<span class="lineno">63</span>
|
||
<span class="lineno">64</span><span class="kn">import</span> <span class="nn">torch</span>
|
||
<span class="lineno">65</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||
<span class="lineno">66</span><span class="kn">from</span> <span class="nn">torch.optim.optimizer</span> <span class="kn">import</span> <span class="n">Optimizer</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><em>ආදම්</em> සහ දිගු සඳහා මූලික පන්තිය</h2>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">69</span><span class="k">class</span> <span class="nc">GenericAdaptiveOptimizer</span><span class="p">(</span><span class="n">Optimizer</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>
|
||
<h3>ආරම්භකරන්න</h3>
|
||
<ul><li><code class="highlight"><span></span><span class="n">params</span></code>
|
||
යනු පරාමිති එකතු කිරීම හෝ පරාමිති කණ්ඩායම් සමූහයකි. </li>
|
||
<li><code class="highlight"><span></span><span class="n">defaults</span></code>
|
||
පෙරනිමි අධි-පරාමිතීන්ගේ ශබ්ද කෝෂයක් </li>
|
||
<li><code class="highlight"><span></span><span class="n">lr</span></code>
|
||
ඉගෙනුම් අනුපාතය, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord mathnormal" style="margin-right:0.0037em;">α</span></span></span></span></span> </li>
|
||
<li><code class="highlight"><span></span><span class="n">betas</span></code>
|
||
මෙම tuple වේ <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mopen">(</span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.05278em;">β</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.30110799999999993em;"><span style="top:-2.5500000000000003em;margin-left:-0.05278em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight">2</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span><span class="mclose">)</span></span></span></span></span> </li>
|
||
</ul><li><code class="highlight"><span></span><span class="n">eps</span></code>
|
||
වේ <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.43056em;vertical-align:0em;"></span><span class="mord mathnormal">ϵ</span></span></span></span></span></li>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">74</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">params</span><span class="p">,</span> <span class="n">defaults</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">],</span> <span class="n">lr</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span> <span class="n">betas</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">float</span><span class="p">],</span> <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span><span class="p">):</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-3'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-3'>#</a>
|
||
</div>
|
||
<p>අධි-පරාමිතීන්පරීක්ෂා කරන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">86</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">lr</span><span class="p">:</span>
|
||
<span class="lineno">87</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid learning rate: </span><span class="si">{</span><span class="n">lr</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||
<span class="lineno">88</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">eps</span><span class="p">:</span>
|
||
<span class="lineno">89</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid epsilon value: </span><span class="si">{</span><span class="n">eps</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||
<span class="lineno">90</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">betas</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o"><</span> <span class="mf">1.0</span><span class="p">:</span>
|
||
<span class="lineno">91</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid beta parameter at index 0: </span><span class="si">{</span><span class="n">betas</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||
<span class="lineno">92</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">betas</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o"><</span> <span class="mf">1.0</span><span class="p">:</span>
|
||
<span class="lineno">93</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid beta parameter at index 1: </span><span class="si">{</span><span class="n">betas</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="si">}</span><span class="s2">"</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>පෙරනිමිසඳහා අධි-පරාමිතීන් එකතු කරන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">96</span> <span class="n">defaults</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">lr</span><span class="o">=</span><span class="n">lr</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="o">=</span><span class="n">eps</span><span class="p">))</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-5'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-5'>#</a>
|
||
</div>
|
||
<p>PyTorchප්රශස්තකරණය ආරම්භ කරන්න. මෙය පෙරනිමි අධි-පරාමිතීන් සහිත පරාමිති කණ්ඩායම් නිර්මාණය කරනු ඇත </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">99</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</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>
|
||
<h3>දීඇති පරාමිතිය tensor සඳහා රාජ්ය ආරම්භ</h3>
|
||
<p>පරාමිතීන් <code class="highlight"><span></span><span class="n">state</span></code>
|
||
සඳහා ආරම්භ කිරීම සඳහා මෙය කේතය සමඟ ඉක්මවා යා යුතුය <code class="highlight"><span></span><span class="n">param</span></code>
|
||
. <code class="highlight"><span></span><span class="n">group</span></code>
|
||
යනු පරාමිති කණ්ඩායම් ශබ්ද කෝෂය <code class="highlight"><span></span><span class="n">param</span></code>
|
||
අයත් වේ. </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">101</span> <span class="k">def</span> <span class="nf">init_state</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="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">param</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Parameter</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">108</span> <span class="k">pass</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>පරාමිතිආතතියක් මත ප්රශස්තිකරණ පියවර ගන්න</h3>
|
||
<p>මෙමoverridden හා <code class="highlight"><span></span><span class="n">param</span></code>
|
||
tensor මත ප්රශස්තිකරණය පියවර ගත යුතු <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.69444em;vertical-align:0em;"></span><span class="mord mathnormal" style="margin-right:0.02778em;">θ</span></span></span></span></span>, එම පරාමිතිය සඳහා ඵලය අනුක්රමික කොහෙද <code class="highlight"><span></span><span class="n">grad</span></code>
|
||
, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.625em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord mathnormal" style="margin-right:0.03588em;">g</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.2805559999999999em;"><span style="top:-2.5500000000000003em;margin-left:-0.03588em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mathnormal mtight">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.15em;"><span></span></span></span></span></span></span></span></span></span></span>, <code class="highlight"><span></span><span class="n">state</span></code>
|
||
යනු එම පරාමිතිය සඳහා ප්රශස්තිකරණ රාජ්ය ශබ්ද කෝෂය <code class="highlight"><span></span><span class="n">group</span></code>
|
||
වන අතර පරාමිති කණ්ඩායම් <code class="highlight"><span></span><span class="n">param</span></code>
|
||
ශබ්දකෝෂයට අයත් වේ. </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">110</span> <span class="k">def</span> <span class="nf">step_param</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="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">],</span> <span class="n">grad</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">param</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-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">119</span> <span class="k">pass</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>
|
||
<h3>පියවරප්රශස්තකරණය</h3>
|
||
<p><em>ආදම්</em> මත පදනම් වූ ප්රශස්තිකරණ අවශ්යතා සෑම පොදු දේවල් කරන අච්චු ක්රමයක් අපි නිර්මාණය කර ඇත්තෙමු. </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">121</span> <span class="nd">@torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">()</span>
|
||
<span class="lineno">122</span> <span class="k">def</span> <span class="nf">step</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">closure</span><span class="o">=</span><span class="kc">None</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>අලාභයගණනය කරන්න. </p>
|
||
<p>🤔ඔබට මෙය අවශ්ය විට මට විශ්වාස නැත. මම හිතන්නේ එය ඔබ අලාභය ගණනය කරන, කරන <code class="highlight"><span></span><span class="n">loss</span><span class="o">.</span><span class="n">backward</span></code>
|
||
සහ අලාභය ආපසු ලබා දෙන ශ්රිතයක් අර්ථ දැක්වුවහොත්, එය තනිවම අමතනවා වෙනුවට ඔබට එය සම්මත කළ හැකිය <code class="highlight"><span></span><span class="n">optimizer</span><span class="o">.</span><span class="n">step</span></code>
|
||
. 🤷♂️ </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">133</span> <span class="n">loss</span> <span class="o">=</span> <span class="kc">None</span>
|
||
<span class="lineno">134</span> <span class="k">if</span> <span class="n">closure</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="lineno">135</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">enable_grad</span><span class="p">():</span>
|
||
<span class="lineno">136</span> <span class="n">loss</span> <span class="o">=</span> <span class="n">closure</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>පරාමිතිකණ්ඩායම් හරහා නැවත ක්රියාත්මක කරන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">139</span> <span class="k">for</span> <span class="n">group</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">param_groups</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>පරාමිතිකණ්ඩායමේ පරාමිතීන් හරහා නැවත ක්රියාත්මක කරන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">141</span> <span class="k">for</span> <span class="n">param</span> <span class="ow">in</span> <span class="n">group</span><span class="p">[</span><span class="s1">'params'</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>පරාමිතියටකිසිදු අනුක්රමික නොමැති නම් මඟ හරින්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">143</span> <span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
<span class="lineno">144</span> <span class="k">continue</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>ශ්රේණියේආතතිය ලබා ගන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">146</span> <span class="n">grad</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span><span class="o">.</span><span class="n">data</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>අපිවිරල අනුක්රමික හැසිරවිය නැහැ </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">148</span> <span class="k">if</span> <span class="n">grad</span><span class="o">.</span><span class="n">is_sparse</span><span class="p">:</span>
|
||
<span class="lineno">149</span> <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">'GenericAdaptiveOptimizer does not support sparse gradients,'</span>
|
||
<span class="lineno">150</span> <span class="s1">' please consider SparseAdam instead'</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>පරාමිතියසඳහා රාජ්ය ලබා ගන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">153</span> <span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">state</span><span class="p">[</span><span class="n">param</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>රාජ්යuninitialized නම් රාජ්ය ආරම්භ </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">156</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">state</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||
<span class="lineno">157</span> <span class="bp">self</span><span class="o">.</span><span class="n">init_state</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="n">group</span><span class="p">,</span> <span class="n">param</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>පරාමිතියමත ප්රශස්තිකරණ පියවර ගන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">160</span> <span class="bp">self</span><span class="o">.</span><span class="n">step_param</span><span class="p">(</span><span class="n">state</span><span class="p">,</span> <span class="n">group</span><span class="p">,</span> <span class="n">grad</span><span class="p">,</span> <span class="n">param</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>වසාදැමීමෙන් ගණනය කරන ලද අලාභය ආපසු ලබා දෙන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">163</span> <span class="k">return</span> <span class="n">loss</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-21'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-21'>#</a>
|
||
</div>
|
||
<h2>L2සිරුරේ බර ක්ෂය</h2>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">166</span><span class="k">class</span> <span class="nc">WeightDecay</span><span class="p">:</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-22'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-22'>#</a>
|
||
</div>
|
||
<h3>බරක්ෂය වීම ආරම්භ කරන්න</h3>
|
||
<ul><li><code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||
ක්ෂය සංගුණකය වේ </li>
|
||
<li><code class="highlight"><span></span><span class="n">weight_decouple</span></code>
|
||
යනු බර ක්ෂය වීම ශ්රේණියට එකතු කළ යුතුද යන්න හෝ පරාමිතියෙන් කෙලින්ම ක්ෂය වීම පෙන්නුම් කරන ධජයකි. ශ්රේණියට එකතු කළහොත් එය සාමාන්ය ප්රශස්තිකරණ යාවත්කාලීනය හරහා ගමන් කරයි. </li>
|
||
<li><code class="highlight"><span></span><span class="n">absolute</span></code>
|
||
මෙම ධජය මඟින් බර ක්ෂය වීමේ සංගුණකය නිරපේක්ෂ ද යන්න පෙන්නුම් කරයි. ක්ෂය වීම පරාමිතිය මත සෘජුවම සිදු කරන විට මෙය අදාළ වේ. මෙය අසත්යයක් නම් සැබෑ ක්ෂය වීමයි <code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||
</li>
|
||
<li><code class="highlight"><span></span><span class="n">learning_rate</span></code>
|
||
. </li></ul>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">171</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">weight_decay</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.</span><span class="p">,</span> <span class="n">weight_decouple</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span> <span class="n">absolute</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</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>අධිපරාමිතීන් පරීක්ෂා කරන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">184</span> <span class="k">if</span> <span class="ow">not</span> <span class="mf">0.0</span> <span class="o"><=</span> <span class="n">weight_decay</span><span class="p">:</span>
|
||
<span class="lineno">185</span> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Invalid weight_decay value: </span><span class="si">{</span><span class="n">weight_decay</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||
<span class="lineno">186</span>
|
||
<span class="lineno">187</span> <span class="bp">self</span><span class="o">.</span><span class="n">absolute</span> <span class="o">=</span> <span class="n">absolute</span>
|
||
<span class="lineno">188</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_decouple</span> <span class="o">=</span> <span class="n">weight_decouple</span>
|
||
<span class="lineno">189</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_decay</span> <span class="o">=</span> <span class="n">weight_decay</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-24'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-24'>#</a>
|
||
</div>
|
||
<p> පරාමිතිකණ්ඩායම් සඳහා ආපසු පැහැර හැරීම්</p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">191</span> <span class="k">def</span> <span class="nf">defaults</span><span class="p">(</span><span class="bp">self</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>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">195</span> <span class="k">return</span> <span class="nb">dict</span><span class="p">(</span><span class="n">weight_decay</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">)</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-26'>
|
||
<div class='docs doc-strings'>
|
||
<div class='section-link'>
|
||
<a href='#section-26'>#</a>
|
||
</div>
|
||
<h3>බරක්ෂය වීම සිදු කර ශ්රේණිය නැවත ලබා දෙන්න</h3>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">197</span> <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">param</span><span class="p">:</span> <span class="n">torch</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">grad</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">group</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">any</span><span class="p">]):</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-27'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-27'>#</a>
|
||
</div>
|
||
<p>අපිපරාමිතිය මත ක්ෂය වීම කෙලින්ම කරන්නේ නම් </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">203</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_decouple</span><span class="p">:</span></pre></div>
|
||
</div>
|
||
</div>
|
||
<div class='section' id='section-28'>
|
||
<div class='docs'>
|
||
<div class='section-link'>
|
||
<a href='#section-28'>#</a>
|
||
</div>
|
||
<p>බරක්ෂය වීමේ සංගුණකය නිරපේක්ෂ නම් </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">205</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">absolute</span><span class="p">:</span>
|
||
<span class="lineno">206</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">mul_</span><span class="p">(</span><span class="mf">1.0</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">'weight_decay'</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>
|
||
<p>එසේනොමැති නම් </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">208</span> <span class="k">else</span><span class="p">:</span>
|
||
<span class="lineno">209</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span><span class="o">.</span><span class="n">mul_</span><span class="p">(</span><span class="mf">1.0</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">'lr'</span><span class="p">]</span> <span class="o">*</span> <span class="n">group</span><span class="p">[</span><span class="s1">'weight_decay'</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>නවීකරණයනොකළ ශ්රේණිය ආපසු ලබා දෙන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">211</span> <span class="k">return</span> <span class="n">grad</span>
|
||
<span class="lineno">212</span> <span class="k">else</span><span class="p">:</span>
|
||
<span class="lineno">213</span> <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">'weight_decay'</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">:</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>බරක්ෂය වීම ශ්රේණියට එකතු කර නවීකරණය කරන ලද ශ්රේණිය නැවත ලබා දෙන්න </p>
|
||
|
||
</div>
|
||
<div class='code'>
|
||
<div class="highlight"><pre><span class="lineno">215</span> <span class="k">return</span> <span class="n">grad</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="n">alpha</span><span class="o">=</span><span class="n">group</span><span class="p">[</span><span class="s1">'weight_decay'</span><span class="p">])</span>
|
||
<span class="lineno">216</span> <span class="k">else</span><span class="p">:</span>
|
||
<span class="lineno">217</span> <span class="k">return</span> <span class="n">grad</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> |