mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-10-28 20:53:41 +08:00
<!DOCTYPE html>
<html lang="zh">
<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=" 视觉变压器 (ViT)"/>
<meta name="twitter:description" content=""/>
<meta name="twitter:site" content="@labmlai"/>
<meta name="twitter:creator" content="@labmlai"/>
<meta property="og:url" content="https://nn.labml.ai/transformers/vit/readme.html"/>
<meta property="og:title" content=" 视觉变压器 (ViT)"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
<meta property="og:site_name" content=" 视觉变压器 (ViT)"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content=" 视觉变压器 (ViT)"/>
<meta property="og:description" content=""/>
<title> 视觉变压器 (ViT)</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/transformers/vit/readme.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.18/dist/katex.min.css" integrity="sha384-zTROYFVGOfTw7JV7KUu8udsvW2fx4lWOsCEDqhBreBwlHI4ioVRtmIvEThzJHGET" crossorigin="anonymous">
<!-- Global site tag (gtag.js) - Google Analytics -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag() {
dataLayer.push(arguments);
}
gtag('js', new Date());
gtag('config', 'G-4V3HC8HBLH');
</script>
</head>
<body>
<div id='container'>
<div id="background"></div>
<div class='section'>
<div class='docs'>
<p>
<a class="parent" href="/">home</a>
<a class="parent" href="../index.html">transformers</a>
<a class="parent" href="index.html">vit</a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations" target="_blank">
<img alt="Github"
src="https://img.shields.io/github/stars/labmlai/annotated_deep_learning_paper_implementations?style=social"
style="max-width:100%;"/></a>
<a href="https://twitter.com/labmlai" rel="nofollow" target="_blank">
<img alt="Twitter"
src="https://img.shields.io/twitter/follow/labmlai?style=social"
style="max-width:100%;"/></a>
</p>
<p>
<a href="https://github.com/labmlai/annotated_deep_learning_paper_implementations/tree/master/labml_nn/transformers/vit/readme.md" target="_blank">
View code on Github</a>
</p>
</div>
</div>
<div class='section' id='section-0'>
<div class='docs'>
<div class='section-link'>
<a href='#section-0'>#</a>
</div>
<h1><a href="https://nn.labml.ai/transformer/vit/index.html">视觉变压器 (ViT)</a></h1>
<p>这是论文《图像<a href="https://arxiv.org/abs/2010.11929">值得 16x16 Words：大规模图像识别的变形金刚》的 PyTorc</a> <a href="https://pytorch.org">h</a> 实现。</p>
<p>视觉变换器将纯变换器应用于没有任何卷积层的图像。他们将图像拆分为补丁，然后在补丁嵌入上应用变换器。<a href="https://nn.labml.ai/transformer/vit/index.html#PathEmbeddings">补丁嵌入</a>是通过对面片的扁平化像素值应用简单的线性变换来生成的。然后将标准变压器编码器与补丁嵌入以及分类令牌一起馈送<code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
。<code class="highlight"><span></span><span class="p">[</span><span class="n">CLS</span><span class="p">]</span></code>
令牌上的编码用于使用 MLP 对图像进行分类。</p>
向@@ <p>变压器提供补丁时，学习的位置嵌入会添加到补丁嵌入中，因为补丁嵌入没有关于补丁来自何处的任何信息。位置嵌入是每个面片位置的一组向量，这些向量通过梯度下降以及其他参数进行训练。</p>
<p>VIT 在大型数据集上进行预训练时表现良好。本文建议使用 MLP 分类头对它们进行预训练，然后在微调时使用单个线性层。该论文在3亿张图像数据集上预先训练了ViT，击败了SOTA。它们还在推理过程中使用更高分辨率的图像，同时保持补丁大小不变。新面片位置的位置嵌入是通过插值学习位置嵌入来计算的。</p>
<p><a href="https://nn.labml.ai/transformer/vit/experiment.html">这是一个在 CIFAR-10 上训练 ViT 的实验</a>。这样做不太好，因为它是在一个小数据集上训练的。这是一个简单的实验，任何人都可以运行和玩VIT。</p>
</div>
<div class='code'>
</div>
</div>
<div class='footer'>
<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>