mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-11-01 03:43:09 +08:00
247 lines
22 KiB
HTML
247 lines
22 KiB
HTML
<!DOCTYPE html>
|
||
<html lang="si">
|
||
<head>
|
||
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
||
<meta name="description" content="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/sponsors/labmlai" target="_blank">
|
||
<img alt="Sponsor"
|
||
src="https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86"
|
||
style="max-width:100%;"/></a>
|
||
<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> |