mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-16 10:51:23 +08:00
<!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="සම්පීඩ්යතා ට්රාන්ස්ෆෝමර්"/>
<meta name="twitter:description" content=""/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/transformers/compressive/readme.html"/>
<meta property="og:title" content="සම්පීඩ්යතා ට්රාන්ස්ෆෝමර්"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
<meta property="og:site_name" content="සම්පීඩ්යතා ට්රාන්ස්ෆෝමර්"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content="සම්පීඩ්යතා ට්රාන්ස්ෆෝමර්"/>
<meta property="og:description" content=""/>
<title>සම්පීඩ්යතා ට්රාන්ස්ෆෝමර්</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/transformers/compressive/readme.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.18/dist/katex.min.css" integrity="sha384-zTROYFVGOfTw7JV7KUu8udsvW2fx4lWOsCEDqhBreBwlHI4ioVRtmIvEThzJHGET" crossorigin="anonymous">
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag() {
dataLayer.push(arguments);
}
gtag('js', new Date());
gtag('config', 'G-4V3HC8HBLH');
</script>
</head>
<body>
<div id='container'>
<div id="background"></div>
<div class='section'>
<div class='docs'>
<p>
<a class="parent" href="/">home</a>
<a class="parent" href="../index.html">transformers</a>
<a class="parent" href="index.html">compressive</a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
<img alt="Github"
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
style="max-width:100%;"/></a>
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
<img alt="Twitter"
src="https://img.shields.io/twitter/follow/labmlai?style=social"
style="max-width:100%;"/></a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/transformers/compressive/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/transformers/compressive/index.html">සම්පීඩ්යතා ට්රාන්ස්ෆෝමර්</a></h1>
<p>මෙය <a href="https://pytorch.org">PyTorch</a> හි <a href="https://papers.labml.ai/paper/1911.05507">දිගු පරාස අනුක්රමික ආකෘති නිර්මාණය සඳහා සම්පීඩ්යතා ට්රාන්ස්ෆෝමර්</a> ක්රියාත්මක කිරීමයි. </p>
<p>මෙය <a href="https://nn.labml.ai/transformers/xl/index.html">ට්රාන්ස්ෆෝමර් එක්ස්එල්</a> හි දිගුවකි, එහිදී අතීත මතකයන් දිගු අවධානයක් ලබා දීම සඳහා සම්පීඩිත වේ. එනම්, furthest <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="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><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 mtight" style=""><span class="mord mathnormal mtight coloredeq eqf" style="">c</span></span><span class="mord mathnormal mtight" style="">m</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 class="mord coloredeq eqf" style=""><span class="mord mathnormal" style="">c</span></span></span></span></span></span> මතකයන් <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="">n</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><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 mtight" style=""><span class="mord mathnormal mtight coloredeq eqf" style="">c</span></span><span class="mord mathnormal mtight" style="">m</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> මතකයන් බවට සම්පීඩනය කරනු ලැබේ, සම්පීඩන අනුපාතය කොහෙද <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="">c</span></span></span></span></span></span> . </p>
<h2>සම්පීඩනමෙහෙයුම</h2>
<p>සම්පීඩනමෙහෙයුම ලෙස අර්ථ දැක්වේ <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 coloredeq eqe" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.10764em">f</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.10764em;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 eqf" style="">c</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 class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">:</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.8491079999999999em;vertical-align:0em;"></span><span class="mord"><span class="mord mathbb">R</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8491079999999999em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">n</span><span class="mord mtight coloredeq eqf" style=""><span class="mord mathnormal mtight" style="">c</span></span><span class="mbin mtight">×</span><span class="mord mathnormal mtight">d</span></span></span></span></span></span></span></span></span><span class="mspace" style="margin-right:0.2777777777777778em;"></span><span class="mrel">→</span><span class="mspace" style="margin-right:0.2777777777777778em;"></span></span><span class="base"><span class="strut" style="height:0.8491079999999999em;vertical-align:0em;"></span><span class="mord"><span class="mord mathbb">R</span><span class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.8491079999999999em;"><span style="top:-3.063em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mord mathnormal mtight">n</span><span class="mbin mtight">×</span><span class="mord mathnormal mtight">d</span></span></span></span></span></span></span></span></span></span></span></span></span>. කඩදාසි සඳහා බහු තේරීම් හඳුන්වා දෙන <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 coloredeq eqe" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.10764em">f</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.10764em;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 eqf" style="">c</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> අතර අප ක්රියාත්මක කර ඇත්තේ 1D කැටි ගැස්ම පමණක් වන අතර එය හොඳම ප්රති. ල ලබා දෙන බව පෙනේ. සෑම ස්ථරයකම වෙනම සම්පීඩන මෙහෙයුමක් <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:1.16678em;vertical-align:-0.19444em;"></span><span class="mord"><span class="mord coloredeq eqe" style=""><span class="mord" style=""><span class="mord mathnormal" style="margin-right:0.10764em">f</span><span class="msupsub"><span class="vlist-t vlist-t2"><span class="vlist-r"><span class="vlist" style="height:0.151392em;"><span style="top:-2.5500000000000003em;margin-left:-0.10764em;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 eqf" style="">c</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 class="msupsub"><span class="vlist-t"><span class="vlist-r"><span class="vlist" style="height:0.97234em;"><span style="top:-3.14734em;margin-right:0.05em;"><span class="pstrut" style="height:2.7em;"></span><span class="sizing reset-size6 size3 mtight"><span class="mord mtight"><span class="mopen mtight">(</span><span class="mord mtight coloredeq eqg" style=""><span class="mord mathnormal mtight" style="">i</span></span><span class="mclose mtight">)</span></span></span></span></span></span></span></span></span></span></span></span></span> ඇත. <span ><span class="katex"><span aria-hidden="true" class="katex-html"><span class="base"><span class="strut" style="height:0.65952em;vertical-align:0em;"></span><span class="mord coloredeq eqg" style=""><span class="mord mathnormal" style="">i</span></span></span></span></span></span> </p>
<h2>සම්පීඩනමෙහෙයුම පුහුණු කිරීම</h2>
<p>බීපීටීටීසමඟ සම්පීඩන පුහුණු කිරීම සඳහා ඉතා විශාල පරිගණකමය ප්රස්ථාරයක් (බොහෝ කාල පියවර) පවත්වා ගැනීම අවශ්ය වන බැවින්, කඩදාසි <em>ස්වයංක්රීයව කේතීකරණ අලාභයක්</em> සහ <em>අවධානය ප්රතිනිර්මාණය කිරීමේ අලාභයක්</em> යෝජනා කරයි. ස්වයංක්රීය කේතීකරණ අලාභය සම්පීඩිත මතකයන් වලින් මුල් මතකයන් විකේතනය කර අලාභය ගණනය කරයි. අවධානය ප්රතිනිර්මාණය අහිමි සම්පීඩිත මතකය මත සහ සම්පීඩිත නොවන මතකය මත බහු-ප්රධානත්වයෙන් අවධානය යොමු ප්රතිඵල ගණනය හා ඔවුන් අතර මධ්යන්ය වර්ග දෝෂයක් ලැබෙන. වඩා හොඳ ප්රති. ල ලබා දෙන බැවින් අපි මෙහි දෙවැන්න ක්රියාත්මක කර ඇත්තෙමු. </p>
<p>මෙමක්රියාත්මක කිරීම පූර්ව ස්ථර සාමාන්යකරණය භාවිතා කරන අතර කඩදාසි පශ්චාත්-ස්ථර සාමාන්යකරණය භාවිතා කරයි. පූර්ව ස්ථර සම්මතය <a href="../feedforward.html">FFN</a> සහ ස්වයං අවධානයට පෙර ස්ථර සම්මතය සිදු කරයි, සහ අවශේෂ සම්බන්ධතාවයේ ගමන් කිරීම සාමාන්ය තත්වයට පත් නොවේ. සම්මත ට්රාන්ස්ෆෝමර් සැකසුම්වලදී මෙය වඩාත් ස්ථායී විය යුතුය. </p>
<p>කුඩාෂේක්ස්පියර් දත්ත කට්ටලයේ සම්පීඩ්යතා ට්රාන්ස්ෆෝමර් ආකෘතියක් පුහුණු කිරීම සඳහා පුහුණු <a href="https://nn.labml.ai/transformers/compressive/experiment.html">කේතය</a> සහ සටහන් පොතක් මෙන්න. </p>
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/transformers/compressive/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://app.labml.ai/run/0d9b5338726c11ebb7c80242ac1c0002"> <img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen"></a> </p>
</div>
<div class='code'>
</div>
</div>
<div class='footer'>
<a href="https://papers.labml.ai">Trending Research Papers</a>
<a href="https://labml.ai">labml.ai</a>
</div>
</div>
<script src=../../interactive.js?v=1"></script>
<script>
function handleImages() {
var images = document.querySelectorAll('p>img')
for (var i = 0; i < images.length; ++i) {
handleImage(images[i])
}
}
function handleImage(img) {
img.parentElement.style.textAlign = 'center'
var modal = document.createElement('div')
modal.id = 'modal'
var modalContent = document.createElement('div')
modal.appendChild(modalContent)
var modalImage = document.createElement('img')
modalContent.appendChild(modalImage)
var span = document.createElement('span')
span.classList.add('close')
span.textContent = 'x'
modal.appendChild(span)
img.onclick = function () {
console.log('clicked')
document.body.appendChild(modal)
modalImage.src = img.src
}
span.onclick = function () {
document.body.removeChild(modal)
}
}
handleImages()
</script>
</body>
</html>