mirror of
https://github.com/facebookresearch/pytorch3d.git
synced 2025-08-02 03:42:50 +08:00
79 lines
13 KiB
HTML
79 lines
13 KiB
HTML
<!DOCTYPE html><html lang="en"><head><meta charSet="utf-8"/><meta http-equiv="X-UA-Compatible" content="IE=edge"/><title>batching · PyTorch3D</title><meta name="viewport" content="width=device-width"/><meta name="generator" content="Docusaurus"/><meta name="description" content="# Batching"/><meta name="docsearch:language" content="en"/><meta property="og:title" content="batching · PyTorch3D"/><meta property="og:type" content="website"/><meta property="og:url" content="https://pytorch3d.org/"/><meta property="og:description" content="# Batching"/><meta property="og:image" content="https://pytorch3d.org/img/pytorch3dlogoicon.svg"/><meta name="twitter:card" content="summary"/><meta name="twitter:image" content="https://pytorch3d.org/img/pytorch3dlogoicon.svg"/><link rel="shortcut icon" href="/img/pytorch3dfavicon.png"/><link rel="stylesheet" href="//cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/default.min.css"/><script>
|
||
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
|
||
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
|
||
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
|
||
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
|
||
|
||
ga('create', 'UA-157376881-1', 'auto');
|
||
ga('send', 'pageview');
|
||
</script><script type="text/javascript" src="https://buttons.github.io/buttons.js"></script><script src="/js/scrollSpy.js"></script><link rel="stylesheet" href="/css/main.css"/><script src="/js/codetabs.js"></script></head><body class="sideNavVisible separateOnPageNav"><div class="fixedHeaderContainer"><div class="headerWrapper wrapper"><header><a href="/"><img class="logo" src="/img/pytorch3dfavicon.png" alt="PyTorch3D"/><h2 class="headerTitleWithLogo">PyTorch3D</h2></a><div class="navigationWrapper navigationSlider"><nav class="slidingNav"><ul class="nav-site nav-site-internal"><li class="siteNavGroupActive"><a href="/docs/why_pytorch3d" target="_self">Docs</a></li><li class=""><a href="/tutorials" target="_self">Tutorials</a></li><li class=""><a href="https://pytorch3d.readthedocs.io/" target="_self">API</a></li><li class=""><a href="https://github.com/facebookresearch/pytorch3d" target="_self">GitHub</a></li></ul></nav></div></header></div></div><div class="navPusher"><div class="docMainWrapper wrapper"><div class="docsNavContainer" id="docsNav"><nav class="toc"><div class="toggleNav"><section class="navWrapper wrapper"><div class="navBreadcrumb wrapper"><div class="navToggle" id="navToggler"><div class="hamburger-menu"><div class="line1"></div><div class="line2"></div><div class="line3"></div></div></div><h2><i>›</i><span>Data</span></h2><div class="tocToggler" id="tocToggler"><i class="icon-toc"></i></div></div><div class="navGroups"><div class="navGroup"><h3 class="navGroupCategoryTitle">Introduction</h3><ul class=""><li class="navListItem"><a class="navItem" href="/docs/why_pytorch3d">Why PyTorch3D</a></li></ul></div><div class="navGroup"><h3 class="navGroupCategoryTitle">Data</h3><ul class=""><li class="navListItem"><a class="navItem" href="/docs/meshes_io">Loading from file</a></li><li class="navListItem"><a class="navItem" href="/docs/datasets">Data loaders</a></li><li class="navListItem navListItemActive"><a class="navItem" href="/docs/batching">Batching</a></li></ul></div><div class="navGroup"><h3 class="navGroupCategoryTitle">Ops</h3><ul class=""><li class="navListItem"><a class="navItem" href="/docs/cubify">Cubify</a></li></ul></div><div class="navGroup"><h3 class="navGroupCategoryTitle">Renderer</h3><ul class=""><li class="navListItem"><a class="navItem" href="/docs/renderer">Overview</a></li><li class="navListItem"><a class="navItem" href="/docs/renderer_getting_started">Getting Started</a></li><li class="navListItem"><a class="navItem" href="/docs/cameras">Cameras</a></li></ul></div></div></section></div><script>
|
||
var coll = document.getElementsByClassName('collapsible');
|
||
var checkActiveCategory = true;
|
||
for (var i = 0; i < coll.length; i++) {
|
||
var links = coll[i].nextElementSibling.getElementsByTagName('*');
|
||
if (checkActiveCategory){
|
||
for (var j = 0; j < links.length; j++) {
|
||
if (links[j].classList.contains('navListItemActive')){
|
||
coll[i].nextElementSibling.classList.toggle('hide');
|
||
coll[i].childNodes[1].classList.toggle('rotate');
|
||
checkActiveCategory = false;
|
||
break;
|
||
}
|
||
}
|
||
}
|
||
|
||
coll[i].addEventListener('click', function() {
|
||
var arrow = this.childNodes[1];
|
||
arrow.classList.toggle('rotate');
|
||
var content = this.nextElementSibling;
|
||
content.classList.toggle('hide');
|
||
});
|
||
}
|
||
|
||
document.addEventListener('DOMContentLoaded', function() {
|
||
createToggler('#navToggler', '#docsNav', 'docsSliderActive');
|
||
createToggler('#tocToggler', 'body', 'tocActive');
|
||
|
||
var headings = document.querySelector('.toc-headings');
|
||
headings && headings.addEventListener('click', function(event) {
|
||
var el = event.target;
|
||
while(el !== headings){
|
||
if (el.tagName === 'A') {
|
||
document.body.classList.remove('tocActive');
|
||
break;
|
||
} else{
|
||
el = el.parentNode;
|
||
}
|
||
}
|
||
}, false);
|
||
|
||
function createToggler(togglerSelector, targetSelector, className) {
|
||
var toggler = document.querySelector(togglerSelector);
|
||
var target = document.querySelector(targetSelector);
|
||
|
||
if (!toggler) {
|
||
return;
|
||
}
|
||
|
||
toggler.onclick = function(event) {
|
||
event.preventDefault();
|
||
|
||
target.classList.toggle(className);
|
||
};
|
||
}
|
||
});
|
||
</script></nav></div><div class="container mainContainer docsContainer"><div class="wrapper"><div class="post"><header class="postHeader"></header><article><div><span><h1><a class="anchor" aria-hidden="true" id="batching"></a><a href="#batching" aria-hidden="true" class="hash-link"><svg class="hash-link-icon" aria-hidden="true" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>Batching</h1>
|
||
<p>In deep learning, every optimization step operates on multiple input examples for robust training. Thus, efficient batching is crucial. For image inputs, batching is straighforward; N images are resized to the same height and width and stacked as a 4 dimensional tensor of shape <code>N x 3 x H x W</code>. For meshes, batching is less straighforward.</p>
|
||
<p><img src="assets/batch_intro.png" alt="batch_intro" align="middle"/></p>
|
||
<h2><a class="anchor" aria-hidden="true" id="batch-modes-for-meshes"></a><a href="#batch-modes-for-meshes" aria-hidden="true" class="hash-link"><svg class="hash-link-icon" aria-hidden="true" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>Batch modes for meshes</h2>
|
||
<p>Assume you want to construct a batch containing two meshes, with <code>mesh1 = (v1: V1 x 3, f1: F1 x 3)</code> containing <code>V1</code> vertices and <code>F1</code> faces, and <code>mesh2 = (v2: V2 x 3, f2: F2 x 3)</code> with <code>V2 (!= V1)</code> vertices and <code>F2 (!= F1)</code> faces. The <a href="https://github.com/facebookresearch/pytorch3d/blob/master/pytorch3d/structures/meshes.py">Meshes</a> data structure provides three different ways to batch <em>heterogeneous</em> meshes. If <code>meshes = Meshes(verts = [v1, v2], faces = [f1, f2])</code> is an instantiation of the data structure, then</p>
|
||
<ul>
|
||
<li>List: Returns the examples in the batch as a list of tensors. Specifically, <code>meshes.verts_list()</code> returns the list of vertices <code>[v1, v2]</code>. Similarly, <code>meshes.faces_list()</code> returns the list of faces <code>[f1, f2]</code>.</li>
|
||
<li>Padded: The padded representation constructs a tensor by padding the extra values. Specifically, <code>meshes.verts_padded()</code> returns a tensor of shape <code>2 x max(V1, V2) x 3</code> and pads the extra vertices with <code>0</code>s. Similarly, <code>meshes.faces_padded()</code> returns a tensor of shape <code>2 x max(F1, F2) x 3</code> and pads the extra faces with <code>-1</code>s.</li>
|
||
<li>Packed: The packed representation concatenates the examples in the batch into a tensor. In particular, <code>meshes.verts_packed()</code> returns a tensor of shape <code>(V1 + V2) x 3</code>. Similarly, <code>meshes.faces_packed()</code> returns a tensor of shape <code>(F1 + F2) x 3</code> for the faces. In the packed mode, auxiliary variables are computed that enable efficient conversion between packed and padded or list modes.</li>
|
||
</ul>
|
||
<p><img src="assets/batch_modes.gif" alt="batch_modes" height="450" align="middle" /></p>
|
||
<h2><a class="anchor" aria-hidden="true" id="use-cases-for-batch-modes"></a><a href="#use-cases-for-batch-modes" aria-hidden="true" class="hash-link"><svg class="hash-link-icon" aria-hidden="true" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path fill-rule="evenodd" d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>Use cases for batch modes</h2>
|
||
<p>The need for different mesh batch modes is inherent to the way pytorch operators are implemented. To fully utilize the optimized pytorch ops, the <a href="https://github.com/facebookresearch/pytorch3d/blob/master/pytorch3d/structures/meshes.py">Meshes</a> data structure allows for efficient conversion between the different batch modes. This is crucial when aiming for a fast and efficient training cycle. An example of this is <a href="https://github.com/facebookresearch/meshrcnn">Mesh R-CNN</a>. Here, in the same forward pass different parts of the network assume different inputs, which are computed by converting between the different batch modes. In particular, <a href="https://github.com/facebookresearch/pytorch3d/blob/master/pytorch3d/ops/vert_align.py">vert_align</a> assumes a <em>padded</em> input tensor while immediately after <a href="https://github.com/facebookresearch/pytorch3d/blob/master/pytorch3d/ops/graph_conv.py">graph_conv</a> assumes a <em>packed</em> input tensor.</p>
|
||
<p><img src="assets/meshrcnn.png" alt="meshrcnn" width="700" align="middle" /></p>
|
||
</span></div></article></div><div class="docLastUpdate"><em>Last updated by Nikhila Ravi</em></div><div class="docs-prevnext"><a class="docs-prev button" href="/docs/datasets"><span class="arrow-prev">← </span><span>Data loaders</span></a><a class="docs-next button" href="/docs/cubify"><span>Cubify</span><span class="arrow-next"> →</span></a></div></div></div><nav class="onPageNav"><ul class="toc-headings"><li><a href="#batch-modes-for-meshes">Batch modes for meshes</a></li><li><a href="#use-cases-for-batch-modes">Use cases for batch modes</a></li></ul></nav></div><footer class="nav-footer" id="footer"><section class="sitemap"><div class="footerSection"><div class="social"><a class="github-button" href="https://github.com/facebookresearch/pytorch3d" data-count-href="https://github.com/facebookresearch/pytorch3d/stargazers" data-show-count="true" data-count-aria-label="# stargazers on GitHub" aria-label="Star PyTorch3D on GitHub">pytorch3d</a></div></div></section><a href="https://opensource.facebook.com/" target="_blank" rel="noreferrer noopener" class="fbOpenSource"><img src="/img/oss_logo.png" alt="Facebook Open Source" width="170" height="45"/></a><section class="copyright">Copyright © 2020 Facebook Inc<br/>Legal:<a href="https://opensource.facebook.com/legal/privacy/" target="_blank" rel="noreferrer noopener">Privacy</a><a href="https://opensource.facebook.com/legal/terms/" target="_blank" rel="noreferrer noopener">Terms</a></section></footer></div></body></html> |