mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-20 13:10:29 +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=" 补丁是你所需要的吗？"/>
<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/conv_mixer/readme.html"/>
<meta property="og:title" content=" 补丁是你所需要的吗？"/>
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
<meta property="og:site_name" content=" 补丁是你所需要的吗？"/>
<meta property="og:type" content="object"/>
<meta property="og:title" content=" 补丁是你所需要的吗？"/>
<meta property="og:description" content=""/>
<title> 补丁是你所需要的吗？</title>
<link rel="shortcut icon" href="/icon.png"/>
<link rel="stylesheet" href="../pylit.css?v=1">
<link rel="canonical" href="https://nn.labml.ai/conv_mixer/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">conv_mixer</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/conv_mixer/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/conv_mixer/index.html">你只需要补丁吗？</a></h1>
<p>这是 <a href="https://pytorch.org">PyTorch</a> 对论文《<a href="https://arxiv.org/abs/2201.09792">补丁就是你所需要的？</a>》的实现</p>。
<p>convMixer 类似于 <a href="https://nn.labml.ai/transformers/mlp_mixer/index.html">MLP 混音器</a>。MLP-Mixer 通过在空间维度上应用 MLP，然后在信道维度上应用 MLP 来分离空间维度和信道维度的混音（空间 MLP 取代 <a href="https://nn.labml.ai/transformers/vit/index.html">vIT</a> 注意力，信道 MLP 是 ViT 的 <a href="https://nn.labml.ai/transformers/feed_forward.html">FFN</a>）。</p>
<p>ConvMixer 使用 1x1 卷积进行通道混合，使用深度卷积进行空间混合。由于它是卷积而不是整个空间的完整的 MLP，因此与 vIT 或 MLP-Mixer 相比，它只混合附近的批次。此外，MLP-Mixer 每次混合使用两层 MLP，ConvMixer 每次混合使用单层。</p>
<p>该论文建议删除信道混合（逐点卷积）上的剩余连接，在空间混合（深度卷积）上仅使用残差连接。他们还使用<a href="https://nn.labml.ai/normalization/batch_norm/index.html">批量标准化</a>而不是<a href="../normalization/layer_norm/index.html">图层标准化</a>。</p>
<p>这是<a href="https://nn.labml.ai/conv_mixer/experiment.html">一项在 CIFAR-10 上训练 ConvMixer 的实验</a>。</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>