chore: import upstream snapshot with attribution
This commit is contained in:
wehub-resource-sync
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,502 @@
|
||||
<!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="ආදම් ප්රශස්තකාරකයේ සරල පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය"/>
|
||||
|
||||
<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="අඩක් නිරවද්යතාව පුහුණුව සඳහා ආදම් ප්රශස්තකරණය"/>
|
||||
<meta name="twitter:description" content="ආදම් ප්රශස්තකාරකයේ සරල පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය"/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/adam_fp16.html"/>
|
||||
<meta property="og:title" content="අඩක් නිරවද්යතාව පුහුණුව සඳහා ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="අඩක් නිරවද්යතාව පුහුණුව සඳහා ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="අඩක් නිරවද්යතාව පුහුණුව සඳහා ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:description" content="ආදම් ප්රශස්තකාරකයේ සරල පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය"/>
|
||||
|
||||
<title>අඩක් නිරවද්යතාව පුහුණුව සඳහා ආදම් 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/adam_fp16.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/adam_fp16.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>අඩක්නිරවද්යතාව පුහුණුව සඳහා ආදම් ප්රශස්තකරණය</h1>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">10</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">Optional</span><span class="p">,</span> <span class="n">Any</span>
|
||||
<span class="lineno">11</span>
|
||||
<span class="lineno">12</span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">13</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">torch.optim</span> <span class="kn">import</span> <span class="n">Optimizer</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">torch.cuda.amp</span> <span class="kn">import</span> <span class="n">grad_scaler</span>
|
||||
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">defaultdict</span><span class="p">,</span> <span class="n">abc</span>
|
||||
<span class="lineno">17</span>
|
||||
<span class="lineno">18</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</span>
|
||||
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam</span> <span class="kn">import</span> <span class="n">Adam</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>අඩක්නිරවද්යතාව පුහුණුව සඳහා ආදම් ප්රශස්තකරණය</h2>
|
||||
<p>අපි <a href="adam.html">ඇඩම් ඔප්ටිමයිසර්</a> දීර් extend කරන නමුත් ශ්රේණි සහ මොහොත ගබඩා කිරීම සඳහා FP32 භාවිතා කරමු. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">22</span><span class="k">class</span> <span class="nc">AdamFP16</span><span class="p">(</span><span class="n">Adam</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">29</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">lr</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-3</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="o">=</span> <span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</span><span class="p">),</span> <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-16</span><span class="p">,</span>
|
||||
<span class="lineno">30</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="n">WeightDecay</span> <span class="o">=</span> <span class="n">WeightDecay</span><span class="p">(),</span> <span class="n">optimized_update</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="lineno">31</span> <span class="n">defaults</span><span class="p">:</span> <span class="n">Optional</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="o">=</span> <span class="kc">None</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>බිට්අනුක්රමික 32 ක් ගබඩා කිරීමේ පරාමිතිය. පහත <code class="highlight"><span></span><span class="n">GradScaler</span></code>
|
||||
අර්ථ දක්වා ඇති පරිදි මෙය ජනාකීර්ණ වේ. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">33</span> <span class="bp">self</span><span class="o">.</span><span class="n">grad_fp32</span> <span class="o">=</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><a href="adam.html">ඇඩම් ප්රශස්තිකරණ</a> ආරම්භකය අමතන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">35</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">lr</span><span class="p">,</span> <span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span> <span class="n">weight_decay</span><span class="p">,</span> <span class="n">optimized_update</span><span class="p">,</span> <span class="n">defaults</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>
|
||||
<h3>පරාමිතිතත්වයක් ආරම්භ කරන්න</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">state</span></code>
|
||||
පරාමිතිය ප්රශස්තකරණය රාජ්ය වේ (tensor) </li>
|
||||
<li><code class="highlight"><span></span><span class="n">group</span></code>
|
||||
පරාමිති කණ්ඩායමේ ප්රශස්තිකරණ ගුණාංග ගබඩා කරයි </li>
|
||||
</ul><li><code class="highlight"><span></span><span class="n">param</span></code>
|
||||
පරාමිතිය tensor වේ <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.902771em;vertical-align:-0.208331em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.02778em">θ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-left:-0.02778em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span><span class="mbin mtight" style="">−</span><span class="mord mtight" style="">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span></span></span></span></span></span></li>
|
||||
<p>සියලුමරාජ්ය ආතතීන් FP32 භාවිතා කරයි. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">37</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-6'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-6'>#</a>
|
||||
</div>
|
||||
<p>පරාමිතියමත ගෙන ඇති ප්රශස්තිකරණ පියවර ගණන මෙයයි, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.61508em;vertical-align:0em;"></span><span class="mord coloredeq eqe" style=""><span class="mord mathnormal" style="">t</span></span></span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">49</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">0</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>අනුක්රමිකක ඝාතීය වෙනස්වන සාමාන්යය, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style=""><span class="mord mathnormal" style="">m</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:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></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></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">51</span> <span class="n">state</span><span class="p">[</span><span class="s1">'exp_avg'</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">zeros_like</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="n">memory_format</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">preserve_format</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
<p>වර්ගඵලය අනුක්රමික වටිනාකම් ඝාතීය වෙනස්වන සාමාන්යය, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.03588em">v</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" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></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></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">53</span> <span class="n">state</span><span class="p">[</span><span class="s1">'exp_avg_sq'</span><span class="p">]</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">zeros_like</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="n">memory_format</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">preserve_format</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">float</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>පරාමිතීන්ගේFP32 පිටපතක් පවත්වා ගන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">55</span> <span class="n">state</span><span class="p">[</span><span class="s1">'fp32_copy'</span><span class="p">]</span> <span class="o">=</span> <span class="n">param</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float</span><span class="p">)</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>දීඇති පරාමිති ටෙන්සරයක් සඳහා යාවත්කාලීන පියවරක් ගන්න</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">state</span></code>
|
||||
පරාමිතිය ප්රශස්තකරණය රාජ්ය වේ (tensor) </li>
|
||||
<li><code class="highlight"><span></span><span class="n">group</span></code>
|
||||
පරාමිති කණ්ඩායමේ ප්රශස්තිකරණ ගුණාංග ගබඩා කරයි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">grad</span></code>
|
||||
පරාමිතිය <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 mtight coloredeq eqe" style=""><span class="mord mathnormal mtight" style="">t</span></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> සඳහා වත්මන් ඵලය අනුක්රමික tensor වේ <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.902771em;vertical-align:-0.208331em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.02778em">θ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-left:-0.02778em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span><span class="mbin mtight" style="">−</span><span class="mord mtight" style="">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span></span></span></span></span></span> </li>
|
||||
</ul><li><code class="highlight"><span></span><span class="n">param</span></code>
|
||||
පරාමිතිය tensor වේ <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.902771em;vertical-align:-0.208331em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.02778em">θ</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.301108em;"><span style="top:-2.5500000000000003em;margin-left:-0.02778em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></span><span class="mbin mtight" style="">−</span><span class="mord mtight" style="">1</span></span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.208331em;"><span></span></span></span></span></span></span></span></span></span></span></span></li>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">57</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">nn</span><span class="o">.</span><span class="n">Parameter</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>FP32පරාමිතීන් ලබා ගන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">68</span> <span class="n">param_fp32</span> <span class="o">=</span> <span class="n">state</span><span class="p">[</span><span class="s1">'fp32_copy'</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>ලබාගත හැකි නම් FP32 අනුක්රමික ලබා ගන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">70</span> <span class="n">grad_fp32</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">grad_fp32</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">param</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
||||
<span class="lineno">71</span> <span class="k">if</span> <span class="n">grad_fp32</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="lineno">72</span> <span class="k">del</span> <span class="bp">self</span><span class="o">.</span><span class="n">grad_fp32</span><span class="p">[</span><span class="n">param</span><span class="p">]</span>
|
||||
<span class="lineno">73</span> <span class="n">grad</span> <span class="o">=</span> <span class="n">grad_fp32</span>
|
||||
<span class="lineno">74</span> <span class="k">else</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>එසේනොමැතිනම්, ශ්රේණිය FP32 බවට පරිවර්තනය කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">76</span> <span class="n">grad</span> <span class="o">=</span> <span class="n">grad</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float</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>බරක්ෂය වීම ගණනය කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">79</span> <span class="n">grad</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">(</span><span class="n">param_fp32</span><span class="p">,</span> <span class="n">grad</span><span class="p">,</span> <span class="n">group</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>ලබා <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqc" style=""><span class="mord" style=""><span class="mord mathnormal" style="">m</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:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></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></span> ගන්න <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.58056em;vertical-align:-0.15em;"></span><span class="mord coloredeq eqd" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.03588em">v</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" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight coloredeq eqe" style="">t</span></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></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">82</span> <span class="n">m</span><span class="p">,</span> <span class="n">v</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_mv</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-16'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-16'>#</a>
|
||||
</div>
|
||||
<p>ප්රශස්තිකරණපියවර ගණන වැඩි <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.61508em;vertical-align:0em;"></span><span class="mord coloredeq eqe" style=""><span class="mord mathnormal" style="">t</span></span></span></span></span></span> කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">85</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">+=</span> <span class="mi">1</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><em>ආදම්</em> යාවත්කාලීන කිරීම සිදු </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">88</span> <span class="bp">self</span><span class="o">.</span><span class="n">adam_update</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_fp32</span><span class="p">,</span> <span class="n">m</span><span class="p">,</span> <span class="n">v</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>පරාමිතීන්සකසන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">91</span> <span class="n">param</span><span class="o">.</span><span class="n">data</span> <span class="o">=</span> <span class="n">param_fp32</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">param</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-19'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-19'>#</a>
|
||||
</div>
|
||||
<h2>අර්ධනිරවද්යතා අනුක්රමික සහිත ග්රේඩියන්ට් පරිමාණය</h2>
|
||||
<p>FP32ශ්රේණියේ භාවිතා කිරීම සඳහා අපි පයිටෝච් ශ්රේණියේ පරිමාණය දිගු කරමු. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">94</span><span class="k">class</span> <span class="nc">GradScalerFP16</span><span class="p">(</span><span class="n">grad_scaler</span><span class="o">.</span><span class="n">GradScaler</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">101</span> <span class="k">def</span> <span class="nf">_unscale_grads_</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">optimizer</span><span class="p">:</span> <span class="n">Optimizer</span><span class="p">,</span> <span class="n">inv_scale</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">found_inf</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="lineno">102</span> <span class="n">allow_fp16</span><span class="p">:</span> <span class="nb">bool</span><span class="p">)</span> <span class="o">-></span> <span class="n">Dict</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">device</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="lineno">103</span> <span class="n">per_device_inv_scale</span> <span class="o">=</span> <span class="n">grad_scaler</span><span class="o">.</span><span class="n">_MultiDeviceReplicator</span><span class="p">(</span><span class="n">inv_scale</span><span class="p">)</span>
|
||||
<span class="lineno">104</span> <span class="n">per_device_found_inf</span> <span class="o">=</span> <span class="n">grad_scaler</span><span class="o">.</span><span class="n">_MultiDeviceReplicator</span><span class="p">(</span><span class="n">found_inf</span><span class="p">)</span>
|
||||
<span class="lineno">105</span>
|
||||
<span class="lineno">106</span> <span class="n">per_device_and_dtype_grads</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="k">lambda</span><span class="p">:</span> <span class="n">defaultdict</span><span class="p">(</span><span class="nb">list</span><span class="p">))</span> <span class="c1"># type: ignore[var-annotated]</span>
|
||||
<span class="lineno">107</span>
|
||||
<span class="lineno">108</span> <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-21'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-21'>#</a>
|
||||
</div>
|
||||
<p>පරාමිතීන්හරහා ලූප් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">110</span> <span class="k">for</span> <span class="n">group</span> <span class="ow">in</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">param_groups</span><span class="p">:</span>
|
||||
<span class="lineno">111</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="s2">"params"</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>පුහුණුකළ නොහැකි පරාමිතීන් මඟ හරින්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">113</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">114</span> <span class="k">continue</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>විරලආතතීන් සඳහා ක්රියාත්මක නොවේ </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">116</span> <span class="k">if</span> <span class="n">param</span><span class="o">.</span><span class="n">grad</span><span class="o">.</span><span class="n">is_sparse</span><span class="p">:</span>
|
||||
<span class="lineno">117</span> <span class="k">raise</span> <span class="ne">NotImplementedError</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>අපිFP32 ශ්රේණියේ <code class="highlight"><span></span><span class="n">AdamFP16</span></code>
|
||||
ප්රශස්තිකරණ කට්ටලය <code class="highlight"><span></span><span class="n">optimizer</span><span class="o">.</span><span class="n">grad_fp32</span><span class="p">[</span><span class="n">param</span><span class="p">]</span></code>
|
||||
භාවිතා කරන්නේ නම් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">120</span> <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">optimizer</span><span class="p">,</span> <span class="n">AdamFP16</span><span class="p">):</span>
|
||||
<span class="lineno">121</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">to</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">float</span><span class="p">)</span>
|
||||
<span class="lineno">122</span> <span class="n">optimizer</span><span class="o">.</span><span class="n">grad_fp32</span><span class="p">[</span><span class="n">param</span><span class="p">]</span> <span class="o">=</span> <span class="n">grad</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>එසේනොමැතිනම්, අනුක්රමික FP32 බවට පරිවර්තනය නොකරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">124</span> <span class="k">else</span><span class="p">:</span>
|
||||
<span class="lineno">125</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="lineno">126</span>
|
||||
<span class="lineno">127</span> <span class="n">per_device_and_dtype_grads</span><span class="p">[</span><span class="n">grad</span><span class="o">.</span><span class="n">device</span><span class="p">][</span><span class="n">grad</span><span class="o">.</span><span class="n">dtype</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">grad</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>සියලුමඅනුක්රමික පරිමාණය කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">130</span> <span class="k">for</span> <span class="n">device</span><span class="p">,</span> <span class="n">per_dtype_grads</span> <span class="ow">in</span> <span class="n">per_device_and_dtype_grads</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||||
<span class="lineno">131</span> <span class="k">for</span> <span class="n">grads</span> <span class="ow">in</span> <span class="n">per_dtype_grads</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
|
||||
<span class="lineno">132</span> <span class="n">torch</span><span class="o">.</span><span class="n">_amp_foreach_non_finite_check_and_unscale_</span><span class="p">(</span><span class="n">grads</span><span class="p">,</span>
|
||||
<span class="lineno">133</span> <span class="n">per_device_found_inf</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">device</span><span class="p">),</span>
|
||||
<span class="lineno">134</span> <span class="n">per_device_inv_scale</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">device</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> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">136</span> <span class="k">return</span> <span class="n">per_device_found_inf</span><span class="o">.</span><span class="n">_per_device_tensors</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 +1,243 @@
|
||||
<!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="උණුසුම් කිරීම සමඟ ආදම් ප්රශස්තිකරණයේ සරල පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය."/>
|
||||
|
||||
<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="උණුසුම සහිත ආදම් ප්රශස්තකරණය"/>
|
||||
<meta name="twitter:description" content="උණුසුම් කිරීම සමඟ ආදම් ප්රශස්තිකරණයේ සරල පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය."/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/adam_warmup.html"/>
|
||||
<meta property="og:title" content="උණුසුම සහිත ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="උණුසුම සහිත ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="උණුසුම සහිත ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:description" content="උණුසුම් කිරීම සමඟ ආදම් ප්රශස්තිකරණයේ සරල පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය."/>
|
||||
|
||||
<title>උණුසුම සහිත ආදම් 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/adam_warmup.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/adam_warmup.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>උණුසුම්කිරීම සමඟ ඇඩම් ප්රශස්තකරණය</h1>
|
||||
<p>මෙය <a href="amsgrad.html">AMSGrad ප්රශස්තකරණය</a> පුළුල් කරන අතර උනුසුම් අවධියක් එක් කරයි. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">12</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="lineno">13</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.amsgrad</span> <span class="kn">import</span> <span class="n">AMSGrad</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>උණුසුම්කිරීම සමඟ ඇඩම් ප්රශස්තකරණය</h2>
|
||||
<p>මෙමපන්තිය AMSGrad ප්රශස්තකරණයෙන් අර්ථ දක්වා ඇත <a href="amsgrad.html"><code class="highlight"><span></span><span class="n">amsgrad</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a>. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">18</span><span class="k">class</span> <span class="nc">AdamWarmup</span><span class="p">(</span><span class="n">AMSGrad</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>ප්රශස්තකරණයආරම්භ කරන්න</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">params</span></code>
|
||||
යනු පරාමිතීන් ලැයිස්තුවයි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
යනු ඉගෙනුම් අනුපාතයයි <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 coloredeq eqf" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span> </li>
|
||||
<li><code class="highlight"><span></span><span class="n">betas</span></code>
|
||||
(<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></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></span></span></span>, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></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></span></span></span>) ක tuple වේ </li>
|
||||
<li><code class="highlight"><span></span><span class="n">eps</span></code>
|
||||
<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 accent"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.69444em;"><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord coloredeq eqc" style=""><span class="mord mathnormal" style="">ϵ</span></span></span><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="accent-body" style="left:-0.19444em;"><span class="mord">^</span></span></span></span></span></span></span></span></span></span></span> හෝ මත <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 coloredeq eqc" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span> පදනම් වේ <code class="highlight"><span></span><span class="n">optimized_update</span></code>
|
||||
</li>
|
||||
<li><code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||||
<code class="highlight"><span></span><span class="n">WeightDecay</span></code>
|
||||
අර්ථ දක්වා ඇති පන්තියේ අවස්ථාවකි <a href="index.html"><code class="highlight"><span></span><span class="fm">__init__</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a> </li>
|
||||
<li>'optimized_update'යනු එකතු කිරීමෙන් පසු එය කිරීමෙන් දෙවන මොහොතේ පක්ෂග්රාහීව නිවැරදි කිරීම ප්රශස්ත කිරීම සඳහා ද යන්න ධජයකි <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 coloredeq eqc" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span> </li>
|
||||
<li><code class="highlight"><span></span><span class="n">amsgrad</span></code>
|
||||
ආදම් සරල කිරීම සඳහා AMSGrad හෝ වැටීම භාවිතා කළ යුතුද යන්න දැක්වෙන ධජයකි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">warmup</span></code>
|
||||
උනුසුම් පියවර ගණන </li>
|
||||
<li><code class="highlight"><span></span><span class="n">defaults</span></code>
|
||||
කණ්ඩායම් අගයන් සඳහා පෙරනිමි ශබ්ද කෝෂයකි. ඔබට පන්තිය දීර් extend කිරීමට අවශ්ය විට මෙය ප්රයෝජනවත් <code class="highlight"><span></span><span class="n">AdamWarmup</span></code>
|
||||
වේ. </li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">24</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">lr</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</span><span class="p">),</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-16</span><span class="p">,</span>
|
||||
<span class="lineno">25</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="n">WeightDecay</span> <span class="o">=</span> <span class="n">WeightDecay</span><span class="p">(),</span>
|
||||
<span class="lineno">26</span> <span class="n">optimized_update</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="lineno">27</span> <span class="n">amsgrad</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">defaults</span><span class="o">=</span><span class="kc">None</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">44</span> <span class="n">defaults</span> <span class="o">=</span> <span class="p">{}</span> <span class="k">if</span> <span class="n">defaults</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">defaults</span>
|
||||
<span class="lineno">45</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">warmup</span><span class="o">=</span><span class="n">warmup</span><span class="p">))</span>
|
||||
<span class="lineno">46</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">lr</span><span class="p">,</span> <span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span> <span class="n">weight_decay</span><span class="p">,</span> <span class="n">optimized_update</span><span class="p">,</span> <span class="n">amsgrad</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<h3>ඉගෙනීම-අනුපාතයලබා ගන්න</h3>
|
||||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqf" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mop">min</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="delimsizing size3">(</span></span><span class="mord">1</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.29208em;"><span style="top:-2.314em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq eqh" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord mathnormal">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.686em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord"><span class="delimsizing size3">)</span></span></span></span></span></span></span> උණුසුම් කිරීමේ පියවර ගණන <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 coloredeq eqh" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</span></span></span></span></span></span> කොහේද? </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">48</span> <span class="k">def</span> <span class="nf">get_lr</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-5'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-5'>#</a>
|
||||
</div>
|
||||
<p>අපිඋනුසුම් අවධියක සිටී නම් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">56</span> <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">]</span> <span class="o">></span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</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>සිට <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord">0</span></span></span></span></span> රේඛීයව වැඩිවන 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 coloredeq eqf" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">58</span> <span class="k">return</span> <span class="mf">1e-8</span> <span class="o">+</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</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">'warmup'</span><span class="p">]</span>
|
||||
<span class="lineno">59</span> <span class="k">else</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>නිරන්තරඉගෙනුම් 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 coloredeq eqf" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">61</span> <span class="k">return</span> <span class="n">group</span><span class="p">[</span><span class="s1">'lr'</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 +1,294 @@
|
||||
<!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="GPT සඳහා උණුසුම් හා කොසයින් ක්ෂය වීම සහිත ඇඩම් ප්රශස්තිකරණයේ පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය."/>
|
||||
|
||||
<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="උණුසුම් හා කොසයින් ක්ෂය වීම සහිත ආදම් ප්රශස්තකරණය"/>
|
||||
<meta name="twitter:description" content="GPT සඳහා උණුසුම් හා කොසයින් ක්ෂය වීම සහිත ඇඩම් ප්රශස්තිකරණයේ පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය."/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/adam_warmup_cosine_decay.html"/>
|
||||
<meta property="og:title" content="උණුසුම් හා කොසයින් ක්ෂය වීම සහිත ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="උණුසුම් හා කොසයින් ක්ෂය වීම සහිත ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="උණුසුම් හා කොසයින් ක්ෂය වීම සහිත ආදම් ප්රශස්තකරණය"/>
|
||||
<meta property="og:description" content="GPT සඳහා උණුසුම් හා කොසයින් ක්ෂය වීම සහිත ඇඩම් ප්රශස්තිකරණයේ පයිටෝච් ක්රියාත්මක කිරීම/නිබන්ධනය."/>
|
||||
|
||||
<title>උණුසුම් හා කොසයින් ක්ෂය වීම සහිත ආදම් 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/adam_warmup_cosine_decay.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/adam_warmup_cosine_decay.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>උණුසුම්හා කොසීන් ක්ෂය වීම සමඟ ඇඩම් ප්රශස්තකරණය</h1>
|
||||
<p>මෙය <a href="adam.html">AMSGrad ප්රශස්තකරණය</a> පුළුල් කරන අතර උනුසුම් අවධියක් එක් කරයි. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">11</span><span></span><span class="kn">import</span> <span class="nn">math</span>
|
||||
<span class="lineno">12</span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span>
|
||||
<span class="lineno">13</span>
|
||||
<span class="lineno">14</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.amsgrad</span> <span class="kn">import</span> <span class="n">AMSGrad</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="EmbeddingsWithPositionalEncoding"></a></p>
|
||||
<h2>උණුසුම්හා කොසීන් ක්ෂය වීම සමඟ ඇඩම් ප්රශස්තකරණය</h2>
|
||||
<p>මෙමපන්තිය AMSGrad ප්රශස්තකරණයෙන් අර්ථ දක්වා ඇත <a href="amsgrad.html"><code class="highlight"><span></span><span class="n">amsgrad</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a>. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">18</span><span class="k">class</span> <span class="nc">AdamWarmupCosineDecay</span><span class="p">(</span><span class="n">AMSGrad</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>ප්රශස්තකරණයආරම්භ කරන්න</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">params</span></code>
|
||||
යනු පරාමිතීන් ලැයිස්තුවයි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
යනු ඉගෙනුම් අනුපාතයයි <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 coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span> </li>
|
||||
<li><code class="highlight"><span></span><span class="n">betas</span></code>
|
||||
(<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></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></span></span></span>, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></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></span></span></span>) ක tuple වේ </li>
|
||||
<li><code class="highlight"><span></span><span class="n">eps</span></code>
|
||||
<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 accent"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.69444em;"><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord coloredeq eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="accent-body" style="left:-0.19444em;"><span class="mord">^</span></span></span></span></span></span></span></span></span></span></span> හෝ මත <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 coloredeq eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span> පදනම් වේ <code class="highlight"><span></span><span class="n">optimized_update</span></code>
|
||||
</li>
|
||||
<li><code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||||
<code class="highlight"><span></span><span class="n">WeightDecay</span></code>
|
||||
අර්ථ දක්වා ඇති පන්තියේ අවස්ථාවකි <a href="index.html"><code class="highlight"><span></span><span class="fm">__init__</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a> </li>
|
||||
<li>'optimized_update'යනු එකතු කිරීමෙන් පසු එය කිරීමෙන් දෙවන මොහොතේ පක්ෂග්රාහීව නිවැරදි කිරීම ප්රශස්ත කිරීම සඳහා ද යන්න ධජයකි <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 coloredeq eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span> </li>
|
||||
<li><code class="highlight"><span></span><span class="n">amsgrad</span></code>
|
||||
ආදම් සරල කිරීම සඳහා AMSGrad හෝ වැටීම භාවිතා කළ යුතුද යන්න දැක්වෙන ධජයකි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">warmup</span></code>
|
||||
උනුසුම් පියවර ගණන </li>
|
||||
<li><code class="highlight"><span></span><span class="n">total_steps</span></code>
|
||||
මුළු පියවර ගණන. කොසයින් ක්ෂය වීම මේ වන විට 0 දක්වා ළඟා වේ, නමුත් අප ගන්නා <code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
නිසා 10% ක රැඳී සිටියි <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.46528em;vertical-align:0em;"></span><span class="mord coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span><span class="mspace" style="margin-right:0.2222222222222222em;"></span><span class="mbin">∗</span><span class="mspace" style="margin-right:0.2222222222222222em;"></span></span><span class="base"><span class="strut" style="height:1em;vertical-align:-0.25em;"></span><span class="mop">max</span><span class="mopen">(</span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span><span class="mord">.1</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord mathnormal">d</span><span class="mord mathnormal">ec</span><span class="mord mathnormal">a</span><span class="mord mathnormal" style="margin-right:0.03588em;">y</span><span class="mclose">)</span></span></span></span></span> </li>
|
||||
<li><code class="highlight"><span></span><span class="n">defaults</span></code>
|
||||
කණ්ඩායම් අගයන් සඳහා පෙරනිමි ශබ්ද කෝෂයකි. ඔබට පන්තිය දීර් extend කිරීමට අවශ්ය විට මෙය ප්රයෝජනවත් <code class="highlight"><span></span><span class="n">AdamWarmup</span></code>
|
||||
වේ. </li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">27</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">lr</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</span><span class="p">),</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-16</span><span class="p">,</span>
|
||||
<span class="lineno">28</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="n">WeightDecay</span> <span class="o">=</span> <span class="n">WeightDecay</span><span class="p">(),</span>
|
||||
<span class="lineno">29</span> <span class="n">optimized_update</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="lineno">30</span> <span class="n">amsgrad</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">total_steps</span><span class="o">=</span><span class="mf">1e10</span><span class="p">,</span> <span class="n">defaults</span><span class="o">=</span><span class="kc">None</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">49</span> <span class="n">defaults</span> <span class="o">=</span> <span class="p">{}</span> <span class="k">if</span> <span class="n">defaults</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">defaults</span>
|
||||
<span class="lineno">50</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">warmup</span><span class="o">=</span><span class="n">warmup</span><span class="p">,</span> <span class="n">total_steps</span><span class="o">=</span><span class="n">total_steps</span><span class="p">))</span>
|
||||
<span class="lineno">51</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">lr</span><span class="p">,</span> <span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span> <span class="n">weight_decay</span><span class="p">,</span> <span class="n">optimized_update</span><span class="p">,</span> <span class="n">amsgrad</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<h3>ඉගෙනීම-අනුපාතයලබා ගන්න</h3>
|
||||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mop">min</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="delimsizing size3">(</span></span><span class="mord">1</span><span class="mpunct">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord"><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.29208em;"><span style="top:-2.314em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord coloredeq eqi" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em;"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord"><span class="mord mathnormal">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.686em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord"><span class="delimsizing size3">)</span></span></span></span></span></span></span> උණුසුම් කිරීමේ පියවර ගණන <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 coloredeq eqi" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</span></span></span></span></span></span> කොහේද? </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">53</span> <span class="k">def</span> <span class="nf">get_lr</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-5'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-5'>#</a>
|
||||
</div>
|
||||
<p>අපිඋනුසුම් අවධියක සිටී නම් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">61</span> <span class="k">if</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">]</span> <span class="o">></span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</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>සිට <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.64444em;vertical-align:0em;"></span><span class="mord coloredeq eqh" style=""><span class="mord" style="">0</span></span></span></span></span></span> රේඛීයව වැඩිවන 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 coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">63</span> <span class="k">return</span> <span class="mf">1e-8</span> <span class="o">+</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</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">'warmup'</span><span class="p">]</span>
|
||||
<span class="lineno">64</span> <span class="k">else</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>නිරන්තරඉගෙනුම් 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 coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">66</span> <span class="n">progress</span> <span class="o">=</span> <span class="p">(</span><span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">])</span> <span class="o">/</span> <span class="nb">max</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">group</span><span class="p">[</span><span class="s1">'total_steps'</span><span class="p">]</span> <span class="o">-</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">])</span>
|
||||
<span class="lineno">67</span> <span class="k">return</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="nb">max</span><span class="p">(</span><span class="mf">0.1</span><span class="p">,</span> <span class="mf">0.5</span> <span class="o">*</span> <span class="p">(</span><span class="mf">1.0</span> <span class="o">+</span> <span class="n">math</span><span class="o">.</span><span class="n">cos</span><span class="p">(</span><span class="n">math</span><span class="o">.</span><span class="n">pi</span> <span class="o">*</span> <span class="n">progress</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>විවිධඋනුසුම් සහ ආකෘති ප්රමාණ සඳහා ප්ලොට් ඉගෙනුම් අනුපාතය</h3>
|
||||
<p><img alt="Plot of learning rate" src="noam_lr.png"></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">70</span><span class="k">def</span> <span class="nf">_test_lr</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">76</span> <span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
|
||||
<span class="lineno">77</span> <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
<span class="lineno">78</span> <span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">79</span>
|
||||
<span class="lineno">80</span> <span class="n">model</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="mi">10</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
|
||||
<span class="lineno">81</span> <span class="n">opt</span> <span class="o">=</span> <span class="n">AdamWarmupCosineDecay</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">5000</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mf">1e-4</span><span class="p">,</span> <span class="n">total_steps</span><span class="o">=</span><span class="mf">4e6</span><span class="p">)</span>
|
||||
<span class="lineno">82</span> <span class="n">steps</span> <span class="o">=</span> <span class="mi">20_000</span>
|
||||
<span class="lineno">83</span> <span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">steps</span><span class="p">),</span> <span class="p">[</span><span class="n">opt</span><span class="o">.</span><span class="n">get_lr</span><span class="p">({</span><span class="s1">'step'</span><span class="p">:</span> <span class="n">i</span><span class="p">},</span> <span class="n">opt</span><span class="o">.</span><span class="n">defaults</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">steps</span><span class="p">)])</span>
|
||||
<span class="lineno">84</span> <span class="n">plt</span><span class="o">.</span><span class="n">legend</span><span class="p">([</span><span class="s2">"5000:4e6"</span><span class="p">,</span> <span class="s2">"5000:2e6"</span><span class="p">,</span> <span class="s2">"5000:1e6"</span><span class="p">])</span>
|
||||
<span class="lineno">85</span> <span class="n">plt</span><span class="o">.</span><span class="n">title</span><span class="p">(</span><span class="s2">"Learning Rate"</span><span class="p">)</span>
|
||||
<span class="lineno">86</span> <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
|
||||
<span class="lineno">87</span>
|
||||
<span class="lineno">88</span> <span class="n">steps</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="mf">6e6</span><span class="p">)</span>
|
||||
<span class="lineno">89</span> <span class="n">step_size</span> <span class="o">=</span> <span class="mi">1000</span>
|
||||
<span class="lineno">90</span> <span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">steps</span><span class="p">,</span> <span class="n">step_size</span><span class="p">),</span> <span class="p">[</span><span class="n">opt</span><span class="o">.</span><span class="n">get_lr</span><span class="p">({</span><span class="s1">'step'</span><span class="p">:</span> <span class="n">i</span><span class="p">},</span> <span class="n">opt</span><span class="o">.</span><span class="n">defaults</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="n">steps</span><span class="p">,</span> <span class="n">step_size</span><span class="p">)])</span>
|
||||
<span class="lineno">91</span> <span class="n">plt</span><span class="o">.</span><span class="n">legend</span><span class="p">([</span><span class="s2">"5000:4e6"</span><span class="p">,</span> <span class="s2">"5000:2e6"</span><span class="p">,</span> <span class="s2">"5000:1e6"</span><span class="p">])</span>
|
||||
<span class="lineno">92</span> <span class="n">plt</span><span class="o">.</span><span class="n">title</span><span class="p">(</span><span class="s2">"Learning Rate"</span><span class="p">)</span>
|
||||
<span class="lineno">93</span> <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
|
||||
<span class="lineno">94</span>
|
||||
<span class="lineno">95</span>
|
||||
<span class="lineno">96</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">97</span> <span class="n">_test_lr</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>
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,443 @@
|
||||
<!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="මෙය ප්රශස්තකරණය සඳහා වින්යාසගත කළ හැකි මොඩියුලයක් ක්රියාත්මක කරයි."/>
|
||||
|
||||
<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="වින්යාසගත ප්රශස්තිකරණ මොඩියුලය"/>
|
||||
<meta name="twitter:description" content="මෙය ප්රශස්තකරණය සඳහා වින්යාසගත කළ හැකි මොඩියුලයක් ක්රියාත්මක කරයි."/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/configs.html"/>
|
||||
<meta property="og:title" content="වින්යාසගත ප්රශස්තිකරණ මොඩියුලය"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="වින්යාසගත ප්රශස්තිකරණ මොඩියුලය"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="වින්යාසගත ප්රශස්තිකරණ මොඩියුලය"/>
|
||||
<meta property="og:description" content="මෙය ප්රශස්තකරණය සඳහා වින්යාසගත කළ හැකි මොඩියුලයක් ක්රියාත්මක කරයි."/>
|
||||
|
||||
<title>වින්යාසගත ප්රශස්තිකරණ මොඩියුලය</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/configs.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/configs.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>මානකලහැකි ප්රශස්තකරණය</h1>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">10</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span>
|
||||
<span class="lineno">11</span>
|
||||
<span class="lineno">12</span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">13</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">BaseConfigs</span><span class="p">,</span> <span class="n">option</span><span class="p">,</span> <span class="n">meta_config</span>
|
||||
<span class="lineno">15</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</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="OptimizerConfigs"></a></p>
|
||||
<h2>ප්රශස්තකරණවින්යාසයන්</h2>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">18</span><span class="k">class</span> <span class="nc">OptimizerConfigs</span><span class="p">(</span><span class="n">BaseConfigs</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>ප්රශස්තකරණය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">26</span> <span class="n">optimizer</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Adam</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>සිරුරේබර ක්ෂය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">29</span> <span class="n">weight_decay_obj</span><span class="p">:</span> <span class="n">WeightDecay</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>බරක්ෂය වීම දිරාපත් වේද; එනම් බර ක්ෂය වීම අනුක්රමික වලට එකතු නොවේ </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">32</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-5'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-5'>#</a>
|
||||
</div>
|
||||
<p>සිරුරේබර ක්ෂය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">34</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</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>බරක්ෂය වීම නිරපේක්ෂ හෝ ඉගෙනුම් අනුපාතය ගුණ කළ යුතු ද යන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">36</span> <span class="n">weight_decay_absolute</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</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>ආදම්යාවත්කාලීන වීමත යන්න (විවිධ epsilon) </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">39</span> <span class="n">optimized_adam_update</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</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>ප්රශස්තිකරණයකළ යුතු පරාමිතීන් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">42</span> <span class="n">parameters</span><span class="p">:</span> <span class="nb">any</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>ඉගෙනුම්අනුපාතය <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> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">45</span> <span class="n">learning_rate</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.01</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>ආදම් <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> සඳහා බීටා අගයන් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">47</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="o">=</span> <span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</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>ආදම් <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> සඳහා එප්සිලන් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">49</span> <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-08</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>SGDසඳහා ගම්යතාව </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">52</span> <span class="n">momentum</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.5</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>AMSGradභාවිතා කළ යුතුද යන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">54</span> <span class="n">amsgrad</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</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>උනුසුම්ප්රශස්තිකරණ පියවර ගණන </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">57</span> <span class="n">warmup</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2_000</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>ප්රශස්තිකරණපියවර ගණන (කොසයින් ක්ෂය වීම සඳහා) </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">59</span> <span class="n">total_steps</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="mf">1e10</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>Adeabeliefහි SGD වෙත පරිහානියට පත් විය යුතුද යන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">62</span> <span class="n">degenerate_to_sgd</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</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>Adameliefහි නිවැරදි කරන ලද ආදම් භාවිතා කළ යුතුද යන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">65</span> <span class="n">rectify</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</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>Noamප්රශස්තකරණය සඳහා ආදර්ශ කාවැද්දීම ප්රමාණය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">68</span> <span class="n">d_model</span><span class="p">:</span> <span class="nb">int</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">70</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="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><span class="n">_primary</span><span class="o">=</span><span class="s1">'optimizer'</span><span class="p">)</span>
|
||||
<span class="lineno">72</span>
|
||||
<span class="lineno">73</span>
|
||||
<span class="lineno">74</span><span class="n">meta_config</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">parameters</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">77</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="s1">'L2'</span><span class="p">)</span>
|
||||
<span class="lineno">78</span><span class="k">def</span> <span class="nf">_weight_decay</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">79</span> <span class="k">return</span> <span class="n">WeightDecay</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">weight_decouple</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">weight_decay_absolute</span><span class="p">)</span>
|
||||
<span class="lineno">80</span>
|
||||
<span class="lineno">81</span>
|
||||
<span class="lineno">82</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'SGD'</span><span class="p">)</span>
|
||||
<span class="lineno">83</span><span class="k">def</span> <span class="nf">_sgd_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">84</span> <span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">SGD</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">c</span><span class="o">.</span><span class="n">momentum</span><span class="p">,</span>
|
||||
<span class="lineno">85</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay</span><span class="p">)</span>
|
||||
<span class="lineno">86</span>
|
||||
<span class="lineno">87</span>
|
||||
<span class="lineno">88</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'Adam'</span><span class="p">)</span>
|
||||
<span class="lineno">89</span><span class="k">def</span> <span class="nf">_adam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">90</span> <span class="k">if</span> <span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">:</span>
|
||||
<span class="lineno">91</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.amsgrad</span> <span class="kn">import</span> <span class="n">AMSGrad</span>
|
||||
<span class="lineno">92</span> <span class="k">return</span> <span class="n">AMSGrad</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">93</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</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">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">94</span> <span class="n">optimized_update</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">optimized_adam_update</span><span class="p">,</span>
|
||||
<span class="lineno">95</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">)</span>
|
||||
<span class="lineno">96</span> <span class="k">else</span><span class="p">:</span>
|
||||
<span class="lineno">97</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam</span> <span class="kn">import</span> <span class="n">Adam</span>
|
||||
<span class="lineno">98</span> <span class="k">return</span> <span class="n">Adam</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">99</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</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">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">100</span> <span class="n">optimized_update</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">optimized_adam_update</span><span class="p">,</span>
|
||||
<span class="lineno">101</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">)</span>
|
||||
<span class="lineno">102</span>
|
||||
<span class="lineno">103</span>
|
||||
<span class="lineno">104</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'AdamW'</span><span class="p">)</span>
|
||||
<span class="lineno">105</span><span class="k">def</span> <span class="nf">_adam_warmup_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">106</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam_warmup</span> <span class="kn">import</span> <span class="n">AdamWarmup</span>
|
||||
<span class="lineno">107</span> <span class="k">return</span> <span class="n">AdamWarmup</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">108</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</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">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">109</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">warmup</span><span class="p">)</span>
|
||||
<span class="lineno">110</span>
|
||||
<span class="lineno">111</span>
|
||||
<span class="lineno">112</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'RAdam'</span><span class="p">)</span>
|
||||
<span class="lineno">113</span><span class="k">def</span> <span class="nf">_radam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">114</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.radam</span> <span class="kn">import</span> <span class="n">RAdam</span>
|
||||
<span class="lineno">115</span> <span class="k">return</span> <span class="n">RAdam</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">116</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</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">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">117</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span>
|
||||
<span class="lineno">118</span> <span class="n">degenerated_to_sgd</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">degenerate_to_sgd</span><span class="p">)</span>
|
||||
<span class="lineno">119</span>
|
||||
<span class="lineno">120</span>
|
||||
<span class="lineno">121</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'AdaBelief'</span><span class="p">)</span>
|
||||
<span class="lineno">122</span><span class="k">def</span> <span class="nf">_ada_belief_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">123</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.ada_belief</span> <span class="kn">import</span> <span class="n">AdaBelief</span>
|
||||
<span class="lineno">124</span> <span class="k">return</span> <span class="n">AdaBelief</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">125</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</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">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">126</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span>
|
||||
<span class="lineno">127</span> <span class="n">degenerate_to_sgd</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">degenerate_to_sgd</span><span class="p">,</span>
|
||||
<span class="lineno">128</span> <span class="n">rectify</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">rectify</span><span class="p">)</span>
|
||||
<span class="lineno">129</span>
|
||||
<span class="lineno">130</span>
|
||||
<span class="lineno">131</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'Noam'</span><span class="p">)</span>
|
||||
<span class="lineno">132</span><span class="k">def</span> <span class="nf">_noam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">133</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.noam</span> <span class="kn">import</span> <span class="n">Noam</span>
|
||||
<span class="lineno">134</span> <span class="k">return</span> <span class="n">Noam</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">135</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</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">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">136</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">warmup</span><span class="p">,</span>
|
||||
<span class="lineno">137</span> <span class="n">d_model</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">d_model</span><span class="p">)</span>
|
||||
<span class="lineno">138</span>
|
||||
<span class="lineno">139</span>
|
||||
<span class="lineno">140</span><span class="nd">@option</span><span class="p">(</span><span class="n">OptimizerConfigs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="s1">'AdamWarmupCosineDecay'</span><span class="p">)</span>
|
||||
<span class="lineno">141</span><span class="k">def</span> <span class="nf">_noam_optimizer</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">OptimizerConfigs</span><span class="p">):</span>
|
||||
<span class="lineno">142</span> <span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam_warmup_cosine_decay</span> <span class="kn">import</span> <span class="n">AdamWarmupCosineDecay</span>
|
||||
<span class="lineno">143</span> <span class="k">return</span> <span class="n">AdamWarmupCosineDecay</span><span class="p">(</span><span class="n">c</span><span class="o">.</span><span class="n">parameters</span><span class="p">,</span>
|
||||
<span class="lineno">144</span> <span class="n">lr</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">learning_rate</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="n">c</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">c</span><span class="o">.</span><span class="n">eps</span><span class="p">,</span>
|
||||
<span class="lineno">145</span> <span class="n">weight_decay</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">weight_decay_obj</span><span class="p">,</span> <span class="n">amsgrad</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">amsgrad</span><span class="p">,</span>
|
||||
<span class="lineno">146</span> <span class="n">warmup</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">warmup</span><span class="p">,</span> <span class="n">total_steps</span><span class="o">=</span><span class="n">c</span><span class="o">.</span><span class="n">total_steps</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 +1,583 @@
|
||||
<!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>
|
||||
@@ -0,0 +1,460 @@
|
||||
<!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="මෙය ප්රශස්තිකාරක පරීක්ෂා කිරීම සඳහා සීඑන්එන් ආකෘතියක් සහිත සරල MNIST උදාහරණයකි."/>
|
||||
|
||||
<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 පරීක්ෂා කිරීම සඳහා MNIST උදාහරණය"/>
|
||||
<meta name="twitter:description" content="මෙය ප්රශස්තිකාරක පරීක්ෂා කිරීම සඳහා සීඑන්එන් ආකෘතියක් සහිත සරල MNIST උදාහරණයකි."/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/mnist_experiment.html"/>
|
||||
<meta property="og:title" content="ප්රශස්තකරණය පරීක්ෂා කිරීම සඳහා MNIST උදාහරණය"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="ප්රශස්තකරණය පරීක්ෂා කිරීම සඳහා MNIST උදාහරණය"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="ප්රශස්තකරණය පරීක්ෂා කිරීම සඳහා MNIST උදාහරණය"/>
|
||||
<meta property="og:description" content="මෙය ප්රශස්තිකාරක පරීක්ෂා කිරීම සඳහා සීඑන්එන් ආකෘතියක් සහිත සරල MNIST උදාහරණයකි."/>
|
||||
|
||||
<title>ප්රශස්තකරණය පරීක්ෂා කිරීම සඳහා MNIST උදාහරණය</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/mnist_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">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/mnist_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>ප්රශස්තකරණයපරීක්ෂා කිරීම සඳහා MNIST උදාහරණය</h1>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">9</span><span></span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span>
|
||||
<span class="lineno">10</span><span class="kn">import</span> <span class="nn">torch.utils.data</span>
|
||||
<span class="lineno">11</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">12</span>
|
||||
<span class="lineno">13</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">experiment</span><span class="p">,</span> <span class="n">tracker</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_helpers.datasets.mnist</span> <span class="kn">import</span> <span class="n">MNISTConfigs</span>
|
||||
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">labml_helpers.device</span> <span class="kn">import</span> <span class="n">DeviceConfigs</span>
|
||||
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">labml_helpers.metrics.accuracy</span> <span class="kn">import</span> <span class="n">Accuracy</span>
|
||||
<span class="lineno">18</span><span class="kn">from</span> <span class="nn">labml_helpers.seed</span> <span class="kn">import</span> <span class="n">SeedConfigs</span>
|
||||
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">labml_helpers.train_valid</span> <span class="kn">import</span> <span class="n">TrainValidConfigs</span><span class="p">,</span> <span class="n">BatchIndex</span><span class="p">,</span> <span class="n">hook_model_outputs</span>
|
||||
<span class="lineno">20</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.configs</span> <span class="kn">import</span> <span class="n">OptimizerConfigs</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>ආකෘතිය</h2>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">23</span><span class="k">class</span> <span class="nc">Model</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'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-2'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">27</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="lineno">28</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="lineno">29</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv1</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="mi">1</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="lineno">30</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool1</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2d</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
|
||||
<span class="lineno">31</span> <span class="bp">self</span><span class="o">.</span><span class="n">conv2</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="mi">20</span><span class="p">,</span> <span class="mi">50</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
|
||||
<span class="lineno">32</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool2</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">MaxPool2d</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
|
||||
<span class="lineno">33</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc1</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="mi">16</span> <span class="o">*</span> <span class="mi">50</span><span class="p">,</span> <span class="mi">500</span><span class="p">)</span>
|
||||
<span class="lineno">34</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc2</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="mi">500</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
|
||||
<span class="lineno">35</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</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-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">37</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="lineno">38</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv1</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
|
||||
<span class="lineno">39</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool1</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
||||
<span class="lineno">40</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">conv2</span><span class="p">(</span><span class="n">x</span><span class="p">))</span>
|
||||
<span class="lineno">41</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pool2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
|
||||
<span class="lineno">42</span> <span class="n">x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">fc1</span><span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">view</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">16</span> <span class="o">*</span> <span class="mi">50</span><span class="p">)))</span>
|
||||
<span class="lineno">43</span> <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fc2</span><span class="p">(</span><span class="n">x</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<h2>සැකසූඅත්හදා බැලීමේ අර්ථ දැක්වීම</h2>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">46</span><span class="k">class</span> <span class="nc">Configs</span><span class="p">(</span><span class="n">MNISTConfigs</span><span class="p">,</span> <span class="n">TrainValidConfigs</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">50</span> <span class="n">optimizer</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Adam</span>
|
||||
<span class="lineno">51</span> <span class="n">model</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span>
|
||||
<span class="lineno">52</span> <span class="n">set_seed</span> <span class="o">=</span> <span class="n">SeedConfigs</span><span class="p">()</span>
|
||||
<span class="lineno">53</span> <span class="n">device</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span> <span class="o">=</span> <span class="n">DeviceConfigs</span><span class="p">()</span>
|
||||
<span class="lineno">54</span> <span class="n">epochs</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">10</span>
|
||||
<span class="lineno">55</span>
|
||||
<span class="lineno">56</span> <span class="n">is_save_models</span> <span class="o">=</span> <span class="kc">True</span>
|
||||
<span class="lineno">57</span> <span class="n">model</span><span class="p">:</span> <span class="n">nn</span><span class="o">.</span><span class="n">Module</span>
|
||||
<span class="lineno">58</span> <span class="n">inner_iterations</span> <span class="o">=</span> <span class="mi">10</span>
|
||||
<span class="lineno">59</span>
|
||||
<span class="lineno">60</span> <span class="n">accuracy_func</span> <span class="o">=</span> <span class="n">Accuracy</span><span class="p">()</span>
|
||||
<span class="lineno">61</span> <span class="n">loss_func</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">CrossEntropyLoss</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-6'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-6'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">63</span> <span class="k">def</span> <span class="nf">init</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="lineno">64</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_queue</span><span class="p">(</span><span class="s2">"loss.*"</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
|
||||
<span class="lineno">65</span> <span class="n">tracker</span><span class="o">.</span><span class="n">set_scalar</span><span class="p">(</span><span class="s2">"accuracy.*"</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
|
||||
<span class="lineno">66</span> <span class="n">hook_model_outputs</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">,</span> <span class="s1">'model'</span><span class="p">)</span>
|
||||
<span class="lineno">67</span> <span class="bp">self</span><span class="o">.</span><span class="n">state_modules</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">accuracy_func</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">69</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">batch</span><span class="p">:</span> <span class="nb">any</span><span class="p">,</span> <span class="n">batch_idx</span><span class="p">:</span> <span class="n">BatchIndex</span><span class="p">):</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
<p>කණ්ඩායමලබා ගන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">71</span> <span class="n">data</span><span class="p">,</span> <span class="n">target</span> <span class="o">=</span> <span class="n">batch</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">),</span> <span class="n">batch</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">device</span><span class="p">)</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-9'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-9'>#</a>
|
||||
</div>
|
||||
<p>අපපුහුණු මාදිලියේ සිටී නම් ගෝලීය පියවර එක් කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">74</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</span><span class="p">:</span>
|
||||
<span class="lineno">75</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add_global_step</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">data</span><span class="p">))</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-10'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-10'>#</a>
|
||||
</div>
|
||||
<p>ආකෘතියධාවනය කර සක්රිය කිරීම් ලොග් කළ යුතුද යන්න සඳහන් කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">78</span> <span class="k">with</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">is_log_activations</span><span class="o">=</span><span class="n">batch_idx</span><span class="o">.</span><span class="n">is_last</span><span class="p">):</span>
|
||||
<span class="lineno">79</span> <span class="n">output</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">(</span><span class="n">data</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>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">82</span> <span class="n">loss</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">loss_func</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">target</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>නිරවද්යතාවයගණනය කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">84</span> <span class="bp">self</span><span class="o">.</span><span class="n">accuracy_func</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">target</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>අලාභයලොග් කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">86</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s2">"loss."</span><span class="p">,</span> <span class="n">loss</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>අපපුහුණු මාදිලියේ සිටී නම් ප්රශස්තිකරණය කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">89</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">mode</span><span class="o">.</span><span class="n">is_train</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>අනුක්රමිකගණනය </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">91</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</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>ප්රශස්තිකරණපියවර ගන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">94</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">step</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>පරාමිතියසහ ශ්රේණියේ L2 සම්මතයන් එක් වරක් ලොග් කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">96</span> <span class="k">if</span> <span class="n">batch_idx</span><span class="o">.</span><span class="n">is_last</span><span class="p">:</span>
|
||||
<span class="lineno">97</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'model'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</span><span class="p">)</span>
|
||||
<span class="lineno">98</span> <span class="n">tracker</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="s1">'optimizer'</span><span class="p">,</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="p">,</span> <span class="p">{</span><span class="s1">'model'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">model</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>අනුක්රමිකඉවත් </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">100</span> <span class="bp">self</span><span class="o">.</span><span class="n">optimizer</span><span class="o">.</span><span class="n">zero_grad</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>ලොග්සුරකින්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">103</span> <span class="n">tracker</span><span class="o">.</span><span class="n">save</span><span class="p">()</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-20'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-20'>#</a>
|
||||
</div>
|
||||
<p> වින්යාසගතකළ හැකි ප්රශස්තිකරණයක් සාදන්න. වින්යාසයන් භාවිතා කරමින් අපට ප්රශස්තිකරණ වර්ගය සහ අධි පරාමිතීන් වෙනස් කළ හැකිය. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">106</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">107</span><span class="k">def</span> <span class="nf">model</span><span class="p">(</span><span class="n">c</span><span class="p">:</span> <span class="n">Configs</span><span class="p">):</span>
|
||||
<span class="lineno">108</span> <span class="k">return</span> <span class="n">Model</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>
|
||||
<span class="lineno">109</span>
|
||||
<span class="lineno">110</span>
|
||||
<span class="lineno">111</span><span class="nd">@option</span><span class="p">(</span><span class="n">Configs</span><span class="o">.</span><span class="n">optimizer</span><span class="p">)</span>
|
||||
<span class="lineno">112</span><span class="k">def</span> <span class="nf">_optimizer</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-21'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-21'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">117</span> <span class="n">opt_conf</span> <span class="o">=</span> <span class="n">OptimizerConfigs</span><span class="p">()</span>
|
||||
<span class="lineno">118</span> <span class="n">opt_conf</span><span class="o">.</span><span class="n">parameters</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">()</span>
|
||||
<span class="lineno">119</span> <span class="k">return</span> <span class="n">opt_conf</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-22'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-22'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">122</span><span class="k">def</span> <span class="nf">main</span><span class="p">():</span>
|
||||
<span class="lineno">123</span> <span class="n">conf</span> <span class="o">=</span> <span class="n">Configs</span><span class="p">()</span>
|
||||
<span class="lineno">124</span> <span class="n">conf</span><span class="o">.</span><span class="n">inner_iterations</span> <span class="o">=</span> <span class="mi">10</span>
|
||||
<span class="lineno">125</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">'mnist_ada_belief'</span><span class="p">)</span>
|
||||
<span class="lineno">126</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><span class="s1">'inner_iterations'</span><span class="p">:</span> <span class="mi">10</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>ප්රශස්තකරණයසඳහන් කරන්න </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">128</span> <span class="s1">'optimizer.optimizer'</span><span class="p">:</span> <span class="s1">'Adam'</span><span class="p">,</span>
|
||||
<span class="lineno">129</span> <span class="s1">'optimizer.learning_rate'</span><span class="p">:</span> <span class="mf">1.5e-4</span><span class="p">})</span>
|
||||
<span class="lineno">130</span> <span class="n">conf</span><span class="o">.</span><span class="n">set_seed</span><span class="o">.</span><span class="n">set</span><span class="p">()</span>
|
||||
<span class="lineno">131</span> <span class="n">experiment</span><span class="o">.</span><span class="n">add_pytorch_models</span><span class="p">(</span><span class="nb">dict</span><span class="p">(</span><span class="n">model</span><span class="o">=</span><span class="n">conf</span><span class="o">.</span><span class="n">model</span><span class="p">))</span>
|
||||
<span class="lineno">132</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">133</span> <span class="n">conf</span><span class="o">.</span><span class="n">run</span><span class="p">()</span>
|
||||
<span class="lineno">134</span>
|
||||
<span class="lineno">135</span>
|
||||
<span class="lineno">136</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">137</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 +1,328 @@
|
||||
<!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="මෙය Noam ප්රශස්තිකරණයේ නිබන්ධනයක්/ක්රියාත්මක කිරීමකි. Noam ප්රශස්තිකරණයට උණුසුම් කාල පරිච්ඡේදයක් ඇති අතර පසුව on ාතීය ලෙස දිරාපත් වන ඉගෙනුම් අනුපාතයක් ඇත."/>
|
||||
|
||||
<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="අවධානය සිට Noam ප්රශස්තකරණය ඔබ කඩදාසි අවශ්ය සියලු වේ"/>
|
||||
<meta name="twitter:description" content="මෙය Noam ප්රශස්තිකරණයේ නිබන්ධනයක්/ක්රියාත්මක කිරීමකි. Noam ප්රශස්තිකරණයට උණුසුම් කාල පරිච්ඡේදයක් ඇති අතර පසුව on ාතීය ලෙස දිරාපත් වන ඉගෙනුම් අනුපාතයක් ඇත."/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/noam.html"/>
|
||||
<meta property="og:title" content="අවධානය සිට Noam ප්රශස්තකරණය ඔබ කඩදාසි අවශ්ය සියලු වේ"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="අවධානය සිට Noam ප්රශස්තකරණය ඔබ කඩදාසි අවශ්ය සියලු වේ"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="අවධානය සිට Noam ප්රශස්තකරණය ඔබ කඩදාසි අවශ්ය සියලු වේ"/>
|
||||
<meta property="og:description" content="මෙය Noam ප්රශස්තිකරණයේ නිබන්ධනයක්/ක්රියාත්මක කිරීමකි. Noam ප්රශස්තිකරණයට උණුසුම් කාල පරිච්ඡේදයක් ඇති අතර පසුව on ාතීය ලෙස දිරාපත් වන ඉගෙනුම් අනුපාතයක් ඇත."/>
|
||||
|
||||
<title>අවධානය සිට Noam ප්රශස්තකරණය ඔබ කඩදාසි අවශ්ය සියලු වේ</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/noam.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/noam.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>නවප්රශස්තකරණය</h1>
|
||||
<p>කඩදාසිතුළ හඳුන්වා දී ඇති ප්රශස්තකරණයේ <a href="https://pytorch.org">PyTorch</a> ක්රියාත්මක කිරීම <a href="https://papers.labml.ai/paper/1706.03762">මෙයයි අවධානය ඔබට අවශ්ය සියල්ල</a> . </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">14</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="lineno">15</span>
|
||||
<span class="lineno">16</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers</span> <span class="kn">import</span> <span class="n">WeightDecay</span>
|
||||
<span class="lineno">17</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.amsgrad</span> <span class="kn">import</span> <span class="n">AMSGrad</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>නවප්රශස්තකරණය</h2>
|
||||
<p>මෙමපන්තිය අර්ථ දක්වා ඇති ආදම් ප්රශස්තකරණයෙන් විහිදේ <a href="adam.html"><code class="highlight"><span></span><span class="n">adam</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a>. </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">20</span><span class="k">class</span> <span class="nc">Noam</span><span class="p">(</span><span class="n">AMSGrad</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>ප්රශස්තකරණයආරම්භ කරන්න</h3>
|
||||
<ul><li><code class="highlight"><span></span><span class="n">params</span></code>
|
||||
යනු පරාමිතීන් ලැයිස්තුවයි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">lr</span></code>
|
||||
යනු ඉගෙනුම් අනුපාතයයි <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 coloredeq eqg" style=""><span class="mord mathnormal" style="margin-right:0.0037em">α</span></span></span></span></span></span> </li>
|
||||
<li><code class="highlight"><span></span><span class="n">betas</span></code>
|
||||
(<span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></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></span></span></span>, <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.8888799999999999em;vertical-align:-0.19444em;"></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></span></span></span>) ක tuple වේ </li>
|
||||
<li><code class="highlight"><span></span><span class="n">eps</span></code>
|
||||
<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 accent"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.69444em;"><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord coloredeq eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span><span style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="accent-body" style="left:-0.19444em;"><span class="mord">^</span></span></span></span></span></span></span></span></span></span></span> හෝ මත <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 coloredeq eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span> පදනම් වේ <code class="highlight"><span></span><span class="n">optimized_update</span></code>
|
||||
</li>
|
||||
<li><code class="highlight"><span></span><span class="n">weight_decay</span></code>
|
||||
<code class="highlight"><span></span><span class="n">WeightDecay</span></code>
|
||||
අර්ථ දක්වා ඇති පන්තියේ අවස්ථාවකි <a href="index.html"><code class="highlight"><span></span><span class="fm">__init__</span><span class="o">.</span><span class="n">py</span></code>
|
||||
</a> </li>
|
||||
<li>'optimized_update'යනු එකතු කිරීමෙන් පසු එය කිරීමෙන් දෙවන මොහොතේ පක්ෂග්රාහීව නිවැරදි කිරීම ප්රශස්ත කිරීම සඳහා ද යන්න ධජයකි <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 coloredeq eqd" style=""><span class="mord mathnormal" style="">ϵ</span></span></span></span></span></span> </li>
|
||||
<li><code class="highlight"><span></span><span class="n">amsgrad</span></code>
|
||||
ආදම් සරල කිරීම සඳහා AMSGrad හෝ වැටීම භාවිතා කළ යුතුද යන්න දැක්වෙන ධජයකි </li>
|
||||
<li><code class="highlight"><span></span><span class="n">warmup</span></code>
|
||||
උනුසුම් පියවර ගණන </li>
|
||||
<li><code class="highlight"><span></span><span class="n">d_model</span></code>
|
||||
ආදර්ශ ප්රමාණය; i.e. ට්රාන්ස්ෆෝමරයේ මානයන් ගණන </li>
|
||||
<li><code class="highlight"><span></span><span class="n">defaults</span></code>
|
||||
කණ්ඩායම් අගයන් සඳහා පෙරනිමි ශබ්ද කෝෂයකි. ඔබට පන්තිය දීර් extend කිරීමට අවශ්ය විට මෙය ප්රයෝජනවත් <code class="highlight"><span></span><span class="n">AdamWarmup</span></code>
|
||||
වේ. </li></ul>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">27</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">lr</span><span class="o">=</span><span class="mf">1e-3</span><span class="p">,</span> <span class="n">betas</span><span class="o">=</span><span class="p">(</span><span class="mf">0.9</span><span class="p">,</span> <span class="mf">0.999</span><span class="p">),</span> <span class="n">eps</span><span class="o">=</span><span class="mf">1e-16</span><span class="p">,</span>
|
||||
<span class="lineno">28</span> <span class="n">weight_decay</span><span class="p">:</span> <span class="n">WeightDecay</span> <span class="o">=</span> <span class="n">WeightDecay</span><span class="p">(),</span>
|
||||
<span class="lineno">29</span> <span class="n">optimized_update</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="lineno">30</span> <span class="n">amsgrad</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
|
||||
<span class="lineno">31</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">d_model</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">defaults</span><span class="o">=</span><span class="kc">None</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">49</span> <span class="n">defaults</span> <span class="o">=</span> <span class="p">{}</span> <span class="k">if</span> <span class="n">defaults</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">defaults</span>
|
||||
<span class="lineno">50</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">warmup</span><span class="o">=</span><span class="n">warmup</span><span class="p">))</span>
|
||||
<span class="lineno">51</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">lr</span><span class="p">,</span> <span class="n">betas</span><span class="p">,</span> <span class="n">eps</span><span class="p">,</span> <span class="n">weight_decay</span><span class="p">,</span> <span class="n">optimized_update</span><span class="p">,</span> <span class="n">amsgrad</span><span class="p">,</span> <span class="n">defaults</span><span class="p">)</span>
|
||||
<span class="lineno">52</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_model</span> <span class="o">=</span> <span class="n">d_model</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-4'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-4'>#</a>
|
||||
</div>
|
||||
<h3>ඉගෙනීම-අනුපාතයලබා ගන්න</h3>
|
||||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqg" style="margin-right:0.0037em">α</span></span><span class="mord" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.25278em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.85722em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord" style=""><span class="mord mathnormal" style="">d</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.33610799999999996em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="">m</span><span class="mord mathnormal mtight" style="">o</span><span class="mord mathnormal mtight" style="">d</span><span class="mord mathnormal mtight" style="">e</span><span class="mord mathnormal mtight" style="margin-right:0.01968em">l</span></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 style="top:-2.81722em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.18278000000000005em;"><span></span></span></span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord" style=""><span class="mop coloredeq eqb" style=""><span style="">m</span><span style="">i</span><span style="">n</span></span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mord coloredeq eqb" style=""><span class="delimsizing size3" style=""><span style="">(</span></span></span><span class="mord coloredeq eqb" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.21746em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.89254em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord mathnormal" style="">t</span></span></span><span style="top:-2.85254em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.14746000000000004em;"><span></span></span></span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mpunct coloredeq eqb" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mord coloredeq eqb" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.29208em;"><span style="top:-2.2960000000000003em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqh" style="margin-right:0.02691em">w</span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.814em;"><span style="top:-2.989em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style="">3/2</span></span></span></span></span></span></span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord mathnormal" style="">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.704em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord coloredeq eqb" style=""><span class="delimsizing size3" style=""><span style="">)</span></span></span></span></span></span></span></span></span></span> උණුසුම් කිරීමේ පියවර ගණන <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 coloredeq eqh" style=""><span class="mord mathnormal" style="margin-right:0.02691em">w</span></span></span></span></span></span> කොහේද? </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">54</span> <span class="k">def</span> <span class="nf">get_lr</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></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-5'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-5'>#</a>
|
||||
</div>
|
||||
<p><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqb" style=""><span class="mop" style=""><span style="">m</span><span style="">i</span><span style="">n</span></span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord" style=""><span class="delimsizing size3" style=""><span style="">(</span></span></span><span class="mord" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.21746em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.89254em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord mathnormal" style="">t</span></span></span><span style="top:-2.85254em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.14746000000000004em;"><span></span></span></span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mpunct" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em;"></span><span class="mord" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.29208em;"><span style="top:-2.2960000000000003em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqh" style="margin-right:0.02691em">w</span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.814em;"><span style="top:-2.989em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style="">3/2</span></span></span></span></span></span></span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord mathnormal" style="">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.704em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord" style=""><span class="delimsizing size3" style=""><span style="">)</span></span></span></span></span></span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">62</span> <span class="n">factor</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">**</span> <span class="p">(</span><span class="o">-</span><span class="mf">0.5</span><span class="p">),</span> <span class="n">state</span><span class="p">[</span><span class="s1">'step'</span><span class="p">]</span> <span class="o">*</span> <span class="n">group</span><span class="p">[</span><span class="s1">'warmup'</span><span class="p">]</span> <span class="o">**</span> <span class="p">(</span><span class="o">-</span><span class="mf">1.5</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><span ><span class="katex-display"><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:2.40003em;vertical-align:-0.95003em;"></span><span class="mord coloredeq eqa" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqg" style="margin-right:0.0037em">α</span></span><span class="mord" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.25278em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.85722em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord" style=""><span class="mord mathnormal" style="">d</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.33610799999999996em;"><span style="top:-2.5500000000000003em;margin-left:0em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mathnormal mtight" style="">m</span><span class="mord mathnormal mtight" style="">o</span><span class="mord mathnormal mtight" style="">d</span><span class="mord mathnormal mtight" style="">e</span><span class="mord mathnormal mtight" style="margin-right:0.01968em">l</span></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 style="top:-2.81722em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.18278000000000005em;"><span></span></span></span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord" style=""><span class="mop coloredeq eqb" style=""><span style="">m</span><span style="">i</span><span style="">n</span></span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mord coloredeq eqb" style=""><span class="delimsizing size3" style=""><span style="">(</span></span></span><span class="mord coloredeq eqb" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.32144em;"><span style="top:-2.21746em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord sqrt" style=""><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.89254em;"><span class="svg-align" style="top:-3em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style="padding-left:0.833em"><span class="mord mathnormal" style="">t</span></span></span><span style="top:-2.85254em;"><span class="pstrut" style="height:3em;"></span><span class="hide-tail" style="min-width:0.853em;height:1.08em"><svg height="1.08em" preserveaspectratio="xMinYMin slice" viewbox="0 0 400000 1080" width="400em" xmlns="http://www.w3.org/2000/svg"><path d="M95,702
|
||||
c-2.7,0,-7.17,-2.7,-13.5,-8c-5.8,-5.3,-9.5,-10,-9.5,-14
|
||||
c0,-2,0.3,-3.3,1,-4c1.3,-2.7,23.83,-20.7,67.5,-54
|
||||
c44.2,-33.3,65.8,-50.3,66.5,-51c1.3,-1.3,3,-2,5,-2c4.7,0,8.7,3.3,12,10
|
||||
s173,378,173,378c0.7,0,35.3,-71,104,-213c68.7,-142,137.5,-285,206.5,-429
|
||||
c69,-144,104.5,-217.7,106.5,-221
|
||||
l0 -0
|
||||
c5.3,-9.3,12,-14,20,-14
|
||||
H400000v40H845.2724
|
||||
s-225.272,467,-225.272,467s-235,486,-235,486c-2.7,4.7,-9,7,-19,7
|
||||
c-6,0,-10,-1,-12,-3s-194,-422,-194,-422s-65,47,-65,47z
|
||||
M834 80h400000v40h-400000z"></path></svg></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.14746000000000004em;"><span></span></span></span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style="">1</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.93em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mpunct coloredeq eqb" style="">,</span><span class="mspace" style="margin-right:0.16666666666666666em"></span><span class="mord coloredeq eqb" style=""><span class="mopen nulldelimiter"></span><span class="mfrac"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:1.29208em;"><span style="top:-2.2960000000000003em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord" style=""><span class="mord" style=""><span class="mord mathnormal coloredeq eqh" style="margin-right:0.02691em">w</span></span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.814em;"><span style="top:-2.989em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight" style=""><span class="mord mtight" style=""><span class="mord mtight" style="">3/2</span></span></span></span></span></span></span></span></span></span></span><span style="top:-3.23em;"><span class="pstrut" style="height:3em;"></span><span class="frac-line" style="border-bottom-width:0.04em"></span></span><span style="top:-3.677em;"><span class="pstrut" style="height:3em;"></span><span class="mord" style=""><span class="mord mathnormal" style="">t</span></span></span></span><span class="vlist-s"></span></span><span class="vlist-r"><span class="vlist" style="height:0.704em;"><span></span></span></span></span></span><span class="mclose nulldelimiter"></span></span><span class="mord coloredeq eqb" style=""><span class="delimsizing size3" style=""><span style="">)</span></span></span></span></span></span></span></span></span></span> </p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">64</span> <span class="k">return</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="bp">self</span><span class="o">.</span><span class="n">d_model</span> <span class="o">**</span> <span class="p">(</span><span class="o">-</span><span class="mf">0.5</span><span class="p">)</span> <span class="o">*</span> <span class="n">factor</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-7'>
|
||||
<div class='docs doc-strings'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-7'>#</a>
|
||||
</div>
|
||||
<h3>විවිධඋනුසුම් සහ ආකෘති ප්රමාණ සඳහා ප්ලොට් ඉගෙනුම් අනුපාතය</h3>
|
||||
<p><img alt="Plot of learning rate" src="noam_lr.png"></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">67</span><span class="k">def</span> <span class="nf">_test_noam_lr</span><span class="p">():</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-8'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-8'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">73</span> <span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
|
||||
<span class="lineno">74</span> <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
|
||||
<span class="lineno">75</span> <span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
||||
<span class="lineno">76</span>
|
||||
<span class="lineno">77</span> <span class="n">model</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="mi">10</span><span class="p">,</span> <span class="mi">10</span><span class="p">)</span>
|
||||
<span class="lineno">78</span> <span class="n">opts</span> <span class="o">=</span> <span class="p">[</span><span class="n">Noam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">d_model</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">4000</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
|
||||
<span class="lineno">79</span> <span class="n">Noam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">d_model</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">8000</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span>
|
||||
<span class="lineno">80</span> <span class="n">Noam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">d_model</span><span class="o">=</span><span class="mi">2048</span><span class="p">,</span> <span class="n">warmup</span><span class="o">=</span><span class="mi">2000</span><span class="p">,</span> <span class="n">lr</span><span class="o">=</span><span class="mi">1</span><span class="p">)]</span>
|
||||
<span class="lineno">81</span> <span class="n">plt</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">20000</span><span class="p">),</span> <span class="p">[[</span><span class="n">opt</span><span class="o">.</span><span class="n">get_lr</span><span class="p">({</span><span class="s1">'step'</span><span class="p">:</span> <span class="n">i</span><span class="p">},</span> <span class="n">opt</span><span class="o">.</span><span class="n">defaults</span><span class="p">)</span> <span class="k">for</span> <span class="n">opt</span> <span class="ow">in</span> <span class="n">opts</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">20000</span><span class="p">)])</span>
|
||||
<span class="lineno">82</span> <span class="n">plt</span><span class="o">.</span><span class="n">legend</span><span class="p">([</span><span class="s2">"512:4000"</span><span class="p">,</span> <span class="s2">"512:8000"</span><span class="p">,</span> <span class="s2">"2048:2000"</span><span class="p">])</span>
|
||||
<span class="lineno">83</span> <span class="n">plt</span><span class="o">.</span><span class="n">title</span><span class="p">(</span><span class="s2">"Learning Rate"</span><span class="p">)</span>
|
||||
<span class="lineno">84</span> <span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
|
||||
<span class="lineno">85</span>
|
||||
<span class="lineno">86</span>
|
||||
<span class="lineno">87</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">88</span> <span class="n">_test_noam_lr</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>
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 35 KiB |
@@ -0,0 +1,175 @@
|
||||
<!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="මෙම අත්හදා බැලීම ආදම් ක්රියාත්මක කිරීමේ කාර්ය සාධනය සංසන්දනය කරයි."/>
|
||||
|
||||
<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="ආදම් ක්රියාත්මක කිරීමේ පරීක්ෂණ කාර්ය සාධනය"/>
|
||||
<meta name="twitter:description" content="මෙම අත්හදා බැලීම ආදම් ක්රියාත්මක කිරීමේ කාර්ය සාධනය සංසන්දනය කරයි."/>
|
||||
<meta name="twitter:site" content="@labmlai"/>
|
||||
<meta name="twitter:creator" content="@labmlai"/>
|
||||
|
||||
<meta property="og:url" content="https://nn.labml.ai/optimizers/performance_test.html"/>
|
||||
<meta property="og:title" content="ආදම් ක්රියාත්මක කිරීමේ පරීක්ෂණ කාර්ය සාධනය"/>
|
||||
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
||||
<meta property="og:site_name" content="ආදම් ක්රියාත්මක කිරීමේ පරීක්ෂණ කාර්ය සාධනය"/>
|
||||
<meta property="og:type" content="object"/>
|
||||
<meta property="og:title" content="ආදම් ක්රියාත්මක කිරීමේ පරීක්ෂණ කාර්ය සාධනය"/>
|
||||
<meta property="og:description" content="මෙම අත්හදා බැලීම ආදම් ක්රියාත්මක කිරීමේ කාර්ය සාධනය සංසන්දනය කරයි."/>
|
||||
|
||||
<title>ආදම් ක්රියාත්මක කිරීමේ පරීක්ෂණ කාර්ය සාධනය</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/performance_test.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/performance_test.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>කාර්යසාධන පරීක්ෂාව ආදම්</h1>
|
||||
<pre class="highlight lang-text"><code><span></span>TorchAdam warmup...[DONE] 222.59ms
|
||||
TorchAdam...[DONE] 1,356.01ms
|
||||
MyAdam warmup...[DONE] 119.15ms
|
||||
MyAdam...[DONE] 1,192.89ms</code></pre>
|
||||
<p><a href="https://colab.research.google.com/drive/1ngowaAsADj8VdZfBifu_6L6rtjGoEeoR?usp=sharing"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a></p>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">19</span><span></span><span class="kn">import</span> <span class="nn">torch</span>
|
||||
<span class="lineno">20</span><span class="kn">import</span> <span class="nn">torch.nn</span> <span class="k">as</span> <span class="nn">nn</span>
|
||||
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml_helpers.device</span> <span class="kn">import</span> <span class="n">DeviceInfo</span>
|
||||
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">torch.optim</span> <span class="kn">import</span> <span class="n">Adam</span> <span class="k">as</span> <span class="n">TorchAdam</span>
|
||||
<span class="lineno">23</span>
|
||||
<span class="lineno">24</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">monit</span>
|
||||
<span class="lineno">25</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.adam</span> <span class="kn">import</span> <span class="n">Adam</span> <span class="k">as</span> <span class="n">MyAdam</span>
|
||||
<span class="lineno">26</span><span class="kn">from</span> <span class="nn">labml_nn.optimizers.mnist_experiment</span> <span class="kn">import</span> <span class="n">Model</span></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
<div class='section' id='section-1'>
|
||||
<div class='docs'>
|
||||
<div class='section-link'>
|
||||
<a href='#section-1'>#</a>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
<div class='code'>
|
||||
<div class="highlight"><pre><span class="lineno">29</span><span class="k">def</span> <span class="nf">test</span><span class="p">():</span>
|
||||
<span class="lineno">30</span> <span class="n">device_info</span> <span class="o">=</span> <span class="n">DeviceInfo</span><span class="p">(</span><span class="n">use_cuda</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">cuda_device</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="lineno">31</span> <span class="nb">print</span><span class="p">(</span><span class="n">device_info</span><span class="p">)</span>
|
||||
<span class="lineno">32</span> <span class="n">inp</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">randn</span><span class="p">((</span><span class="mi">64</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="mi">28</span><span class="p">,</span> <span class="mi">28</span><span class="p">),</span> <span class="n">device</span><span class="o">=</span><span class="n">device_info</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
||||
<span class="lineno">33</span> <span class="n">target</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">ones</span><span class="p">(</span><span class="mi">64</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">long</span><span class="p">,</span> <span class="n">device</span><span class="o">=</span><span class="n">device_info</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
||||
<span class="lineno">34</span> <span class="n">loss_func</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">CrossEntropyLoss</span><span class="p">()</span>
|
||||
<span class="lineno">35</span> <span class="n">model</span> <span class="o">=</span> <span class="n">Model</span><span class="p">()</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device_info</span><span class="o">.</span><span class="n">device</span><span class="p">)</span>
|
||||
<span class="lineno">36</span> <span class="n">my_adam</span> <span class="o">=</span> <span class="n">MyAdam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">())</span>
|
||||
<span class="lineno">37</span> <span class="n">torch_adam</span> <span class="o">=</span> <span class="n">TorchAdam</span><span class="p">(</span><span class="n">model</span><span class="o">.</span><span class="n">parameters</span><span class="p">())</span>
|
||||
<span class="lineno">38</span> <span class="n">loss</span> <span class="o">=</span> <span class="n">loss_func</span><span class="p">(</span><span class="n">model</span><span class="p">(</span><span class="n">inp</span><span class="p">),</span> <span class="n">target</span><span class="p">)</span>
|
||||
<span class="lineno">39</span> <span class="n">loss</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span>
|
||||
<span class="lineno">40</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'MyAdam warmup'</span><span class="p">):</span>
|
||||
<span class="lineno">41</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">100</span><span class="p">):</span>
|
||||
<span class="lineno">42</span> <span class="n">my_adam</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
||||
<span class="lineno">43</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'MyAdam'</span><span class="p">):</span>
|
||||
<span class="lineno">44</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1000</span><span class="p">):</span>
|
||||
<span class="lineno">45</span> <span class="n">my_adam</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
||||
<span class="lineno">46</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'TorchAdam warmup'</span><span class="p">):</span>
|
||||
<span class="lineno">47</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">100</span><span class="p">):</span>
|
||||
<span class="lineno">48</span> <span class="n">torch_adam</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
||||
<span class="lineno">49</span> <span class="k">with</span> <span class="n">monit</span><span class="o">.</span><span class="n">section</span><span class="p">(</span><span class="s1">'TorchAdam'</span><span class="p">):</span>
|
||||
<span class="lineno">50</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1000</span><span class="p">):</span>
|
||||
<span class="lineno">51</span> <span class="n">torch_adam</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
|
||||
<span class="lineno">52</span>
|
||||
<span class="lineno">53</span>
|
||||
<span class="lineno">54</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">55</span> <span class="n">test</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>
|
||||
File diff suppressed because one or more lines are too long
Binary file not shown.
|
After Width: | Height: | Size: 30 KiB |
@@ -0,0 +1,133 @@
|
||||
<!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="ප්රශස්තකරණය"/>
|
||||
<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/optimizers/readme.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=""/>
|
||||
|
||||
<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/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">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/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/optimizers/index.html">ප්රශස්තකරණය</a></h1>
|
||||
<h2>ප්රශස්තිකරණක්රියාත්මක කිරීම්</h2>
|
||||
<ul><li><a href="https://nn.labml.ai/optimizers/adam.html">ආදම් ප්රශස්තකරණය</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/amsgrad.html">AMSGrad ප්රශස්තකරණය</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/adam_warmup.html">උණුසුම් කිරීම සමඟ ආදම් ප්රශස්තකරණය</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/noam.html">නව ප්රශස්තකරණය</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/radam.html">නිවැරදි කරන ලද ආදම් ප්රශස්තකරණය</a> </li>
|
||||
<li><a href="https://nn.labml.ai/optimizers/ada_belief.html">ADABelief ප්රශස්තකරණය</a> </li></ul>
|
||||
|
||||
</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