423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-08-02 03:42:50 +08:00
Code Issues Packages Projects Releases Wiki Activity
pytorch3d/tutorials/implicitron_volumes/index.html
Jeremy Francis Reizenstein aa880b723b v0.7.5
2023-10-31 13:08:44 -07:00

655 lines
60 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!DOCTYPE html><html lang=""><head><meta charSet="utf-8"/><meta http-equiv="X-UA-Compatible" content="IE=edge"/><title>PyTorch3D · A library for deep learning with 3D data</title><meta name="viewport" content="width=device-width, initial-scale=1.0"/><meta name="generator" content="Docusaurus"/><meta name="description" content="A library for deep learning with 3D data"/><meta property="og:title" content="PyTorch3D · A library for deep learning with 3D data"/><meta property="og:type" content="website"/><meta property="og:url" content="https://pytorch3d.org/"/><meta property="og:description" content="A library for deep learning with 3D data"/><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><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=""><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="container 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></span></h2><div class="tocToggler" id="tocToggler"><i class="icon-toc"></i></div></div><div class="navGroups"><div class="navGroup"><h3 class="navGroupCategoryTitle">Tutorials</h3><ul class=""><li class="navListItem"><a class="navItem" href="/tutorials/">Overview</a></li></ul></div><div class="navGroup"><h3 class="navGroupCategoryTitle">3D operators</h3><ul class=""><li class="navListItem"><a class="navItem" href="/tutorials/deform_source_mesh_to_target_mesh">Fit Mesh</a></li><li class="navListItem"><a class="navItem" href="/tutorials/bundle_adjustment">Bundle Adjustment</a></li></ul></div><div class="navGroup"><h3 class="navGroupCategoryTitle">Rendering</h3><ul class=""><li class="navListItem"><a class="navItem" href="/tutorials/render_textured_meshes">Render Textured Meshes</a></li><li class="navListItem"><a class="navItem" href="/tutorials/render_densepose">Render DensePose Meshes</a></li><li class="navListItem"><a class="navItem" href="/tutorials/render_colored_points">Render Colored Pointclouds</a></li><li class="navListItem"><a class="navItem" href="/tutorials/fit_textured_mesh">Fit a Mesh with Texture via Rendering</a></li><li class="navListItem"><a class="navItem" href="/tutorials/camera_position_optimization_with_differentiable_rendering">Camera Position Optimization with Differentiable Rendering</a></li><li class="navListItem"><a class="navItem" href="/tutorials/fit_textured_volume">Fit a volume via raymarching</a></li><li class="navListItem"><a class="navItem" href="/tutorials/fit_simple_neural_radiance_field">Fit a simplified NeRF via raymarching</a></li></ul></div><div class="navGroup"><h3 class="navGroupCategoryTitle">Dataloaders</h3><ul class=""><li class="navListItem"><a class="navItem" href="/tutorials/dataloaders_ShapeNetCore_R2N2">Data loaders for ShapeNetCore and R2N2</a></li></ul></div><div class="navGroup"><h3 class="navGroupCategoryTitle">Implicitron</h3><ul class=""><li class="navListItem navListItemActive"><a class="navItem" href="/tutorials/implicitron_volumes">Training a custom volumes function with implicitron</a></li><li class="navListItem"><a class="navItem" href="/tutorials/implicitron_config_system">Implicitron config system deep dive</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"><div class="wrapper"><div class="tutorialButtonsWrapper"><div class="tutorialButtonWrapper buttonWrapper"><a class="tutorialButton button" download="" href="https://colab.research.google.com/github/facebookresearch/pytorch3d/blob/stable/docs/tutorials/implicitron_volumes.ipynb" target="_blank"><img class="colabButton" align="left" src="/img/colab_icon.png"/>Run in Google Colab</a></div><div class="tutorialButtonWrapper buttonWrapper"><a class="tutorialButton button" download="" href="/files/implicitron_volumes.ipynb" target="_blank"><svg aria-hidden="true" focusable="false" data-prefix="fas" data-icon="file-download" class="svg-inline--fa fa-file-download fa-w-12" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 384 512"><path fill="currentColor" d="M224 136V0H24C10.7 0 0 10.7 0 24v464c0 13.3 10.7 24 24 24h336c13.3 0 24-10.7 24-24V160H248c-13.2 0-24-10.8-24-24zm76.45 211.36l-96.42 95.7c-6.65 6.61-17.39 6.61-24.04 0l-96.42-95.7C73.42 337.29 80.54 320 94.82 320H160v-80c0-8.84 7.16-16 16-16h32c8.84 0 16 7.16 16 16v80h65.18c14.28 0 21.4 17.29 11.27 27.36zM377 105L279.1 7c-4.5-4.5-10.6-7-17-7H256v128h128v-6.1c0-6.3-2.5-12.4-7-16.9z"></path></svg>Download Tutorial Jupyter Notebook</a></div><div class="tutorialButtonWrapper buttonWrapper"><a class="tutorialButton button" download="" href="/files/implicitron_volumes.py" target="_blank"><svg aria-hidden="true" focusable="false" data-prefix="fas" data-icon="file-download" class="svg-inline--fa fa-file-download fa-w-12" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 384 512"><path fill="currentColor" d="M224 136V0H24C10.7 0 0 10.7 0 24v464c0 13.3 10.7 24 24 24h336c13.3 0 24-10.7 24-24V160H248c-13.2 0-24-10.8-24-24zm76.45 211.36l-96.42 95.7c-6.65 6.61-17.39 6.61-24.04 0l-96.42-95.7C73.42 337.29 80.54 320 94.82 320H160v-80c0-8.84 7.16-16 16-16h32c8.84 0 16 7.16 16 16v80h65.18c14.28 0 21.4 17.29 11.27 27.36zM377 105L279.1 7c-4.5-4.5-10.6-7-17-7H256v128h128v-6.1c0-6.3-2.5-12.4-7-16.9z"></path></svg>Download Tutorial Source Code</a></div></div><div class="tutorialBody">
<script
src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.1.10/require.min.js">
</script>
<script
src="https://cdnjs.cloudflare.com/ajax/libs/jquery/2.0.3/jquery.min.js">
</script>
<div class="notebook">
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="c1"># Copyright (c) Meta Platforms, Inc. and affiliates. All rights reserved.</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h1 id="A-simple-model-using-Implicitron">A simple model using Implicitron<a class="anchor-link" href="#A-simple-model-using-Implicitron"></a></h1><p>In this demo, we use the VolumeRenderer from PyTorch3D as a custom implicit function in Implicitron. We will see</p>
<ul>
<li>some of the main objects in Implicitron</li>
<li>how to plug in a custom part of a model</li>
</ul>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="0.-Install-and-import-modules">0. Install and import modules<a class="anchor-link" href="#0.-Install-and-import-modules"></a></h2><p>Ensure <code>torch</code> and <code>torchvision</code> are installed. If <code>pytorch3d</code> is not installed, install it using the following cell:</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">sys</span>
<span class="kn">import</span> <span class="nn">torch</span>
<span class="n">need_pytorch3d</span><span class="o">=</span><span class="kc">False</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">pytorch3d</span>
<span class="k">except</span> <span class="ne">ModuleNotFoundError</span><span class="p">:</span>
<span class="n">need_pytorch3d</span><span class="o">=</span><span class="kc">True</span>
<span class="k">if</span> <span class="n">need_pytorch3d</span><span class="p">:</span>
<span class="k">if</span> <span class="n">torch</span><span class="o">.</span><span class="n">__version__</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"2.1."</span><span class="p">)</span> <span class="ow">and</span> <span class="n">sys</span><span class="o">.</span><span class="n">platform</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"linux"</span><span class="p">):</span>
<span class="c1"># We try to install PyTorch3D via a released wheel.</span>
<span class="n">pyt_version_str</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">__version__</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"+"</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"."</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
<span class="n">version_str</span><span class="o">=</span><span class="s2">""</span><span class="o">.</span><span class="n">join</span><span class="p">([</span>
<span class="sa">f</span><span class="s2">"py3</span><span class="si">{</span><span class="n">sys</span><span class="o">.</span><span class="n">version_info</span><span class="o">.</span><span class="n">minor</span><span class="si">}</span><span class="s2">_cu"</span><span class="p">,</span>
<span class="n">torch</span><span class="o">.</span><span class="n">version</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"."</span><span class="p">,</span><span class="s2">""</span><span class="p">),</span>
<span class="sa">f</span><span class="s2">"_pyt</span><span class="si">{</span><span class="n">pyt_version_str</span><span class="si">}</span><span class="s2">"</span>
<span class="p">])</span>
<span class="o">!</span>pip<span class="w"> </span>install<span class="w"> </span>fvcore<span class="w"> </span>iopath
<span class="o">!</span>pip<span class="w"> </span>install<span class="w"> </span>--no-index<span class="w"> </span>--no-cache-dir<span class="w"> </span>pytorch3d<span class="w"> </span>-f<span class="w"> </span>https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/<span class="o">{</span>version_str<span class="o">}</span>/download.html
<span class="k">else</span><span class="p">:</span>
<span class="c1"># We try to install PyTorch3D from source.</span>
<span class="o">!</span>pip<span class="w"> </span>install<span class="w"> </span><span class="s1">'git+https://github.com/facebookresearch/pytorch3d.git@stable'</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>Ensure omegaconf and visdom are installed. If not, run this cell. (It should not be necessary to restart the runtime.)</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="o">!</span>pip<span class="w"> </span>install<span class="w"> </span>omegaconf<span class="w"> </span>visdom
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span>
<span class="kn">import</span> <span class="nn">matplotlib.animation</span> <span class="k">as</span> <span class="nn">animation</span>
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
<span class="kn">import</span> <span class="nn">torch</span>
<span class="kn">import</span> <span class="nn">tqdm</span>
<span class="kn">from</span> <span class="nn">IPython.display</span> <span class="kn">import</span> <span class="n">HTML</span>
<span class="kn">from</span> <span class="nn">omegaconf</span> <span class="kn">import</span> <span class="n">OmegaConf</span>
<span class="kn">from</span> <span class="nn">PIL</span> <span class="kn">import</span> <span class="n">Image</span>
<span class="kn">from</span> <span class="nn">pytorch3d.implicitron.dataset.dataset_base</span> <span class="kn">import</span> <span class="n">FrameData</span>
<span class="kn">from</span> <span class="nn">pytorch3d.implicitron.dataset.rendered_mesh_dataset_map_provider</span> <span class="kn">import</span> <span class="n">RenderedMeshDatasetMapProvider</span>
<span class="kn">from</span> <span class="nn">pytorch3d.implicitron.models.generic_model</span> <span class="kn">import</span> <span class="n">GenericModel</span>
<span class="kn">from</span> <span class="nn">pytorch3d.implicitron.models.implicit_function.base</span> <span class="kn">import</span> <span class="n">ImplicitFunctionBase</span><span class="p">,</span> <span class="n">ImplicitronRayBundle</span>
<span class="kn">from</span> <span class="nn">pytorch3d.implicitron.models.renderer.base</span> <span class="kn">import</span> <span class="n">EvaluationMode</span>
<span class="kn">from</span> <span class="nn">pytorch3d.implicitron.tools.config</span> <span class="kn">import</span> <span class="n">get_default_args</span><span class="p">,</span> <span class="n">registry</span><span class="p">,</span> <span class="n">remove_unused_components</span>
<span class="kn">from</span> <span class="nn">pytorch3d.renderer.implicit.renderer</span> <span class="kn">import</span> <span class="n">VolumeSampler</span>
<span class="kn">from</span> <span class="nn">pytorch3d.structures</span> <span class="kn">import</span> <span class="n">Volumes</span>
<span class="kn">from</span> <span class="nn">pytorch3d.vis.plotly_vis</span> <span class="kn">import</span> <span class="n">plot_batch_individually</span><span class="p">,</span> <span class="n">plot_scene</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">output_resolution</span> <span class="o">=</span> <span class="mi">80</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">torch</span><span class="o">.</span><span class="n">set_printoptions</span><span class="p">(</span><span class="n">sci_mode</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="1.-Load-renders-of-a-mesh-(the-cow-mesh)-as-a-dataset">1. Load renders of a mesh (the cow mesh) as a dataset<a class="anchor-link" href="#1.-Load-renders-of-a-mesh-(the-cow-mesh)-as-a-dataset"></a></h2><p>A dataset's train, val and test parts in Implicitron are represented as a <code>dataset_map</code>, and provided by an implementation of <code>DatasetMapProvider</code>.
<code>RenderedMeshDatasetMapProvider</code> is one which generates a single-scene dataset with only a train component by taking a mesh and rendering it.
We use it with the cow mesh.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>If running this notebook using <strong>Google Colab</strong>, run the following cell to fetch the mesh obj and texture files and save it at the path data/cow_mesh.
If running locally, the data is already available at the correct path.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="o">!</span>mkdir<span class="w"> </span>-p<span class="w"> </span>data/cow_mesh
<span class="o">!</span>wget<span class="w"> </span>-P<span class="w"> </span>data/cow_mesh<span class="w"> </span>https://dl.fbaipublicfiles.com/pytorch3d/data/cow_mesh/cow.obj
<span class="o">!</span>wget<span class="w"> </span>-P<span class="w"> </span>data/cow_mesh<span class="w"> </span>https://dl.fbaipublicfiles.com/pytorch3d/data/cow_mesh/cow.mtl
<span class="o">!</span>wget<span class="w"> </span>-P<span class="w"> </span>data/cow_mesh<span class="w"> </span>https://dl.fbaipublicfiles.com/pytorch3d/data/cow_mesh/cow_texture.png
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">cow_provider</span> <span class="o">=</span> <span class="n">RenderedMeshDatasetMapProvider</span><span class="p">(</span>
<span class="n">data_file</span><span class="o">=</span><span class="s2">"data/cow_mesh/cow.obj"</span><span class="p">,</span>
<span class="n">use_point_light</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">resolution</span><span class="o">=</span><span class="n">output_resolution</span><span class="p">,</span>
<span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">dataset_map</span> <span class="o">=</span> <span class="n">cow_provider</span><span class="o">.</span><span class="n">get_dataset_map</span><span class="p">()</span>
<span class="n">tr_cameras</span> <span class="o">=</span> <span class="p">[</span><span class="n">training_frame</span><span class="o">.</span><span class="n">camera</span> <span class="k">for</span> <span class="n">training_frame</span> <span class="ow">in</span> <span class="n">dataset_map</span><span class="o">.</span><span class="n">train</span><span class="p">]</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="c1"># The cameras are all in the XZ plane, in a circle about 2.7 from the origin</span>
<span class="n">centers</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">([</span><span class="n">i</span><span class="o">.</span><span class="n">get_camera_center</span><span class="p">()</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">tr_cameras</span><span class="p">])</span>
<span class="nb">print</span><span class="p">(</span><span class="n">centers</span><span class="o">.</span><span class="n">min</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">values</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">centers</span><span class="o">.</span><span class="n">max</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">values</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="c1"># visualization of the cameras</span>
<span class="n">plot</span> <span class="o">=</span> <span class="n">plot_scene</span><span class="p">({</span><span class="s2">"k"</span><span class="p">:</span> <span class="p">{</span><span class="n">i</span><span class="p">:</span> <span class="n">camera</span> <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">camera</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">tr_cameras</span><span class="p">)}},</span> <span class="n">camera_scale</span><span class="o">=</span><span class="mf">0.25</span><span class="p">)</span>
<span class="n">plot</span><span class="o">.</span><span class="n">layout</span><span class="o">.</span><span class="n">scene</span><span class="o">.</span><span class="n">aspectmode</span> <span class="o">=</span> <span class="s2">"data"</span>
<span class="n">plot</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="2.-Custom-implicit-function-🧊">2. Custom implicit function 🧊<a class="anchor-link" href="#2.-Custom-implicit-function-🧊"></a></h2><p>At the core of neural rendering methods are functions of spatial coordinates called implicit functions, which are used in some kind of rendering process.
(Often those functions can additionally take other data as well, such as view direction.)
A common rendering process is ray marching over densities and colors provided by an implicit function.
In our case, taking samples from a 3D volume grid is a very simple function of spatial coordinates.</p>
<p>Here we define our own implicit function, which uses PyTorch3D's existing functionality for sampling from a volume grid.
We do this by subclassing <code>ImplicitFunctionBase</code>.
We need to register our subclass with a special decorator.
We use Python's dataclass annotations for configuring the module.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="nd">@registry</span><span class="o">.</span><span class="n">register</span>
<span class="k">class</span> <span class="nc">MyVolumes</span><span class="p">(</span><span class="n">ImplicitFunctionBase</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">Module</span><span class="p">):</span>
<span class="n">grid_resolution</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">50</span> <span class="c1"># common HWD of volumes, the number of voxels in each direction</span>
<span class="n">extent</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span> <span class="c1"># In world coordinates, the volume occupies is [-extent, extent] along each axis</span>
<span class="k">def</span> <span class="nf">__post_init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># We have to call this explicitly if there are other base classes like Module</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="c1"># We define parameters like other torch.nn.Module objects.</span>
<span class="c1"># In this case, both our parameter tensors are trainable; they govern the contents of the volume grid.</span>
<span class="n">density</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">full</span><span class="p">((</span><span class="bp">self</span><span class="o">.</span><span class="n">grid_resolution</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">grid_resolution</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">grid_resolution</span><span class="p">),</span> <span class="o">-</span><span class="mf">2.0</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">density</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">Parameter</span><span class="p">(</span><span class="n">density</span><span class="p">)</span>
<span class="n">color</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">full</span><span class="p">((</span><span class="mi">3</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">grid_resolution</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">grid_resolution</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">grid_resolution</span><span class="p">),</span> <span class="mf">0.0</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">color</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">Parameter</span><span class="p">(</span><span class="n">color</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">density_activation</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">Softplus</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">forward</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">ray_bundle</span><span class="p">:</span> <span class="n">ImplicitronRayBundle</span><span class="p">,</span>
<span class="n">fun_viewpool</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">global_code</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="p">):</span>
<span class="n">densities</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">density_activation</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">density</span><span class="p">[</span><span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">])</span>
<span class="n">voxel_size</span> <span class="o">=</span> <span class="mf">2.0</span> <span class="o">*</span> <span class="nb">float</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">extent</span><span class="p">)</span> <span class="o">/</span> <span class="bp">self</span><span class="o">.</span><span class="n">grid_resolution</span>
<span class="n">features</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">color</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">()[</span><span class="kc">None</span><span class="p">]</span>
<span class="c1"># Like other PyTorch3D structures, the actual Volumes object should only exist as long</span>
<span class="c1"># as one iteration of training. It is local to this function.</span>
<span class="n">volume</span> <span class="o">=</span> <span class="n">Volumes</span><span class="p">(</span><span class="n">densities</span><span class="o">=</span><span class="n">densities</span><span class="p">,</span> <span class="n">features</span><span class="o">=</span><span class="n">features</span><span class="p">,</span> <span class="n">voxel_size</span><span class="o">=</span><span class="n">voxel_size</span><span class="p">)</span>
<span class="n">sampler</span> <span class="o">=</span> <span class="n">VolumeSampler</span><span class="p">(</span><span class="n">volumes</span><span class="o">=</span><span class="n">volume</span><span class="p">)</span>
<span class="n">densities</span><span class="p">,</span> <span class="n">features</span> <span class="o">=</span> <span class="n">sampler</span><span class="p">(</span><span class="n">ray_bundle</span><span class="p">)</span>
<span class="c1"># When an implicit function is used for raymarching, i.e. for MultiPassEmissionAbsorptionRenderer,</span>
<span class="c1"># it must return (densities, features, an auxiliary tuple)</span>
<span class="k">return</span> <span class="n">densities</span><span class="p">,</span> <span class="n">features</span><span class="p">,</span> <span class="p">{}</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="3.-Construct-the-model-object.">3. Construct the model object.<a class="anchor-link" href="#3.-Construct-the-model-object."></a></h2><p>The main model object in PyTorch3D is <code>GenericModel</code>, which has pluggable components for the major steps, including the renderer and the implicit function(s).
There are two ways to construct it which are equivalent here.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">CONSTRUCT_MODEL_FROM_CONFIG</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">if</span> <span class="n">CONSTRUCT_MODEL_FROM_CONFIG</span><span class="p">:</span>
<span class="c1"># Via a DictConfig - this is how our training loop with hydra works</span>
<span class="n">cfg</span> <span class="o">=</span> <span class="n">get_default_args</span><span class="p">(</span><span class="n">GenericModel</span><span class="p">)</span>
<span class="n">cfg</span><span class="o">.</span><span class="n">implicit_function_class_type</span> <span class="o">=</span> <span class="s2">"MyVolumes"</span>
<span class="n">cfg</span><span class="o">.</span><span class="n">render_image_height</span><span class="o">=</span><span class="n">output_resolution</span>
<span class="n">cfg</span><span class="o">.</span><span class="n">render_image_width</span><span class="o">=</span><span class="n">output_resolution</span>
<span class="n">cfg</span><span class="o">.</span><span class="n">loss_weights</span><span class="o">=</span><span class="p">{</span><span class="s2">"loss_rgb_huber"</span><span class="p">:</span> <span class="mf">1.0</span><span class="p">}</span>
<span class="n">cfg</span><span class="o">.</span><span class="n">tqdm_trigger_threshold</span><span class="o">=</span><span class="mi">19000</span>
<span class="n">cfg</span><span class="o">.</span><span class="n">raysampler_AdaptiveRaySampler_args</span><span class="o">.</span><span class="n">scene_extent</span><span class="o">=</span> <span class="mf">4.0</span>
<span class="n">gm</span> <span class="o">=</span> <span class="n">GenericModel</span><span class="p">(</span><span class="o">**</span><span class="n">cfg</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># constructing GenericModel directly</span>
<span class="n">gm</span> <span class="o">=</span> <span class="n">GenericModel</span><span class="p">(</span>
<span class="n">implicit_function_class_type</span><span class="o">=</span><span class="s2">"MyVolumes"</span><span class="p">,</span>
<span class="n">render_image_height</span><span class="o">=</span><span class="n">output_resolution</span><span class="p">,</span>
<span class="n">render_image_width</span><span class="o">=</span><span class="n">output_resolution</span><span class="p">,</span>
<span class="n">loss_weights</span><span class="o">=</span><span class="p">{</span><span class="s2">"loss_rgb_huber"</span><span class="p">:</span> <span class="mf">1.0</span><span class="p">},</span>
<span class="n">tqdm_trigger_threshold</span><span class="o">=</span><span class="mi">19000</span><span class="p">,</span>
<span class="n">raysampler_AdaptiveRaySampler_args</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"scene_extent"</span><span class="p">:</span> <span class="mf">4.0</span><span class="p">}</span>
<span class="p">)</span>
<span class="c1"># In this case we can get the equivalent DictConfig cfg object to the way gm is configured as follows</span>
<span class="n">cfg</span> <span class="o">=</span> <span class="n">OmegaConf</span><span class="o">.</span><span class="n">structured</span><span class="p">(</span><span class="n">gm</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>The default renderer is an emission-absorbtion raymarcher. We keep that default.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="c1"># We can display the configuration in use as follows.</span>
<span class="n">remove_unused_components</span><span class="p">(</span><span class="n">cfg</span><span class="p">)</span>
<span class="n">yaml</span> <span class="o">=</span> <span class="n">OmegaConf</span><span class="o">.</span><span class="n">to_yaml</span><span class="p">(</span><span class="n">cfg</span><span class="p">,</span> <span class="n">sort_keys</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="o">%</span><span class="k">page</span> -r yaml
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">device</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">device</span><span class="p">(</span><span class="s2">"cuda:0"</span><span class="p">)</span>
<span class="n">gm</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</span><span class="p">)</span>
<span class="k">assert</span> <span class="nb">next</span><span class="p">(</span><span class="n">gm</span><span class="o">.</span><span class="n">parameters</span><span class="p">())</span><span class="o">.</span><span class="n">is_cuda</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="4.-train-the-model">4. train the model<a class="anchor-link" href="#4.-train-the-model"></a></h2>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">train_data_collated</span> <span class="o">=</span> <span class="p">[</span><span class="n">FrameData</span><span class="o">.</span><span class="n">collate</span><span class="p">([</span><span class="n">frame</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</span><span class="p">)])</span> <span class="k">for</span> <span class="n">frame</span> <span class="ow">in</span> <span class="n">dataset_map</span><span class="o">.</span><span class="n">train</span><span class="p">]</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">gm</span><span class="o">.</span><span class="n">train</span><span class="p">()</span>
<span class="n">optimizer</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">optim</span><span class="o">.</span><span class="n">Adam</span><span class="p">(</span><span class="n">gm</span><span class="o">.</span><span class="n">parameters</span><span class="p">(),</span> <span class="n">lr</span><span class="o">=</span><span class="mf">0.1</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">iterator</span> <span class="o">=</span> <span class="n">tqdm</span><span class="o">.</span><span class="n">tqdm</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="mi">2000</span><span class="p">))</span>
<span class="k">for</span> <span class="n">n_batch</span> <span class="ow">in</span> <span class="n">iterator</span><span class="p">:</span>
<span class="n">optimizer</span><span class="o">.</span><span class="n">zero_grad</span><span class="p">()</span>
<span class="n">frame</span> <span class="o">=</span> <span class="n">train_data_collated</span><span class="p">[</span><span class="n">n_batch</span> <span class="o">%</span> <span class="nb">len</span><span class="p">(</span><span class="n">dataset_map</span><span class="o">.</span><span class="n">train</span><span class="p">)]</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">gm</span><span class="p">(</span><span class="o">**</span><span class="n">frame</span><span class="p">,</span> <span class="n">evaluation_mode</span><span class="o">=</span><span class="n">EvaluationMode</span><span class="o">.</span><span class="n">TRAINING</span><span class="p">)</span>
<span class="n">out</span><span class="p">[</span><span class="s2">"objective"</span><span class="p">]</span><span class="o">.</span><span class="n">backward</span><span class="p">()</span>
<span class="k">if</span> <span class="n">n_batch</span> <span class="o">%</span> <span class="mi">100</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
<span class="n">iterator</span><span class="o">.</span><span class="n">set_postfix_str</span><span class="p">(</span><span class="sa">f</span><span class="s2">"loss: </span><span class="si">{</span><span class="nb">float</span><span class="p">(</span><span class="n">out</span><span class="p">[</span><span class="s1">'objective'</span><span class="p">])</span><span class="si">:</span><span class="s2">.5f</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
<span class="n">optimizer</span><span class="o">.</span><span class="n">step</span><span class="p">()</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="5.-Evaluate-the-module">5. Evaluate the module<a class="anchor-link" href="#5.-Evaluate-the-module"></a></h2><p>We generate complete images from all the viewpoints to see how they look.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="k">def</span> <span class="nf">to_numpy_image</span><span class="p">(</span><span class="n">image</span><span class="p">):</span>
<span class="c1"># Takes an image of shape (C, H, W) in [0,1], where C=3 or 1</span>
<span class="c1"># to a numpy uint image of shape (H, W, 3)</span>
<span class="k">return</span> <span class="p">(</span><span class="n">image</span> <span class="o">*</span> <span class="mi">255</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span><span class="o">.</span><span class="n">permute</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span><span class="o">.</span><span class="n">detach</span><span class="p">()</span><span class="o">.</span><span class="n">cpu</span><span class="p">()</span><span class="o">.</span><span class="n">expand</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span><span class="o">.</span><span class="n">numpy</span><span class="p">()</span>
<span class="k">def</span> <span class="nf">resize_image</span><span class="p">(</span><span class="n">image</span><span class="p">):</span>
<span class="c1"># Takes images of shape (B, C, H, W) to (B, C, output_resolution, output_resolution)</span>
<span class="k">return</span> <span class="n">torch</span><span class="o">.</span><span class="n">nn</span><span class="o">.</span><span class="n">functional</span><span class="o">.</span><span class="n">interpolate</span><span class="p">(</span><span class="n">image</span><span class="p">,</span> <span class="n">size</span><span class="o">=</span><span class="p">(</span><span class="n">output_resolution</span><span class="p">,</span> <span class="n">output_resolution</span><span class="p">))</span>
<span class="n">gm</span><span class="o">.</span><span class="n">eval</span><span class="p">()</span>
<span class="n">images</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">expected</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">masks</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">masks_expected</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">frame</span> <span class="ow">in</span> <span class="n">tqdm</span><span class="o">.</span><span class="n">tqdm</span><span class="p">(</span><span class="n">train_data_collated</span><span class="p">):</span>
<span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span>
<span class="n">out</span> <span class="o">=</span> <span class="n">gm</span><span class="p">(</span><span class="o">**</span><span class="n">frame</span><span class="p">,</span> <span class="n">evaluation_mode</span><span class="o">=</span><span class="n">EvaluationMode</span><span class="o">.</span><span class="n">EVALUATION</span><span class="p">)</span>
<span class="n">image_rgb</span> <span class="o">=</span> <span class="n">to_numpy_image</span><span class="p">(</span><span class="n">out</span><span class="p">[</span><span class="s2">"images_render"</span><span class="p">][</span><span class="mi">0</span><span class="p">])</span>
<span class="n">mask</span> <span class="o">=</span> <span class="n">to_numpy_image</span><span class="p">(</span><span class="n">out</span><span class="p">[</span><span class="s2">"masks_render"</span><span class="p">][</span><span class="mi">0</span><span class="p">])</span>
<span class="n">expd</span> <span class="o">=</span> <span class="n">to_numpy_image</span><span class="p">(</span><span class="n">resize_image</span><span class="p">(</span><span class="n">frame</span><span class="o">.</span><span class="n">image_rgb</span><span class="p">)[</span><span class="mi">0</span><span class="p">])</span>
<span class="n">mask_expected</span> <span class="o">=</span> <span class="n">to_numpy_image</span><span class="p">(</span><span class="n">resize_image</span><span class="p">(</span><span class="n">frame</span><span class="o">.</span><span class="n">fg_probability</span><span class="p">)[</span><span class="mi">0</span><span class="p">])</span>
<span class="n">images</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">image_rgb</span><span class="p">)</span>
<span class="n">masks</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">mask</span><span class="p">)</span>
<span class="n">expected</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">expd</span><span class="p">)</span>
<span class="n">masks_expected</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">mask_expected</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<p>We draw a grid showing predicted image and expected image, followed by predicted mask and expected mask, from each viewpoint.
This is a grid of four rows of images, wrapped in to several large rows, i.e..
<small><center></center></small></p>
<pre><code>┌────────┬────────┐ ┌────────┐
│pred │pred │ │pred │
│image │image │ │image │
│1 │2 │ │n │
├────────┼────────┤ ├────────┤
│expected│expected│ │expected│
│image │image │ ... │image │
│1 │2 │ │n │
├────────┼────────┤ ├────────┤
│pred │pred │ │pred │
│mask │mask │ │mask │
│1 │2 │ │n │
├────────┼────────┤ ├────────┤
│expected│expected│ │expected│
│mask │mask │ │mask │
│1 │2 │ │n │
├────────┼────────┤ ├────────┤
│pred │pred │ │pred │
│image │image │ │image │
│n+1 │n+1 │ │2n │
├────────┼────────┤ ├────────┤
│expected│expected│ │expected│
│image │image │ ... │image │
│n+1 │n+2 │ │2n │
├────────┼────────┤ ├────────┤
│pred │pred │ │pred │
│mask │mask │ │mask │
│n+1 │n+2 │ │2n │
├────────┼────────┤ ├────────┤
│expected│expected│ │expected│
│mask │mask │ │mask │
│n+1 │n+2 │ │2n │
└────────┴────────┘ └────────┘
...</code></pre>
<p>&lt;/center&gt;&lt;/small&gt;</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">images_to_display</span> <span class="o">=</span> <span class="p">[</span><span class="n">images</span><span class="o">.</span><span class="n">copy</span><span class="p">(),</span> <span class="n">expected</span><span class="o">.</span><span class="n">copy</span><span class="p">(),</span> <span class="n">masks</span><span class="o">.</span><span class="n">copy</span><span class="p">(),</span> <span class="n">masks_expected</span><span class="o">.</span><span class="n">copy</span><span class="p">()]</span>
<span class="n">n_rows</span> <span class="o">=</span> <span class="mi">4</span>
<span class="n">n_images</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">images</span><span class="p">)</span>
<span class="n">blank_image</span> <span class="o">=</span> <span class="n">images</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="mi">0</span>
<span class="n">n_per_row</span> <span class="o">=</span> <span class="mi">1</span><span class="o">+</span><span class="p">(</span><span class="n">n_images</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span><span class="o">//</span><span class="n">n_rows</span>
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_per_row</span><span class="o">*</span><span class="n">n_rows</span> <span class="o">-</span> <span class="n">n_images</span><span class="p">):</span>
<span class="k">for</span> <span class="n">group</span> <span class="ow">in</span> <span class="n">images_to_display</span><span class="p">:</span>
<span class="n">group</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">blank_image</span><span class="p">)</span>
<span class="n">images_to_display_listed</span> <span class="o">=</span> <span class="p">[[[</span><span class="n">i</span><span class="p">]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">j</span><span class="p">]</span> <span class="k">for</span> <span class="n">j</span> <span class="ow">in</span> <span class="n">images_to_display</span><span class="p">]</span>
<span class="n">split</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_rows</span><span class="p">):</span>
<span class="k">for</span> <span class="n">group</span> <span class="ow">in</span> <span class="n">images_to_display_listed</span><span class="p">:</span>
<span class="n">split</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">group</span><span class="p">[</span><span class="n">row</span><span class="o">*</span><span class="n">n_per_row</span><span class="p">:(</span><span class="n">row</span><span class="o">+</span><span class="mi">1</span><span class="p">)</span><span class="o">*</span><span class="n">n_per_row</span><span class="p">])</span>
<span class="n">Image</span><span class="o">.</span><span class="n">fromarray</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">block</span><span class="p">(</span><span class="n">split</span><span class="p">))</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="c1"># Print the maximum channel intensity in the first image.</span>
<span class="nb">print</span><span class="p">(</span><span class="n">images</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">max</span><span class="p">()</span><span class="o">/</span><span class="mi">255</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">plt</span><span class="o">.</span><span class="n">ioff</span><span class="p">()</span>
<span class="n">fig</span><span class="p">,</span> <span class="n">ax</span> <span class="o">=</span> <span class="n">plt</span><span class="o">.</span><span class="n">subplots</span><span class="p">(</span><span class="n">figsize</span><span class="o">=</span><span class="p">(</span><span class="mi">3</span><span class="p">,</span><span class="mi">3</span><span class="p">))</span>
<span class="n">ax</span><span class="o">.</span><span class="n">grid</span><span class="p">(</span><span class="kc">None</span><span class="p">)</span>
<span class="n">ims</span> <span class="o">=</span> <span class="p">[[</span><span class="n">ax</span><span class="o">.</span><span class="n">imshow</span><span class="p">(</span><span class="n">im</span><span class="p">,</span> <span class="n">animated</span><span class="o">=</span><span class="kc">True</span><span class="p">)]</span> <span class="k">for</span> <span class="n">im</span> <span class="ow">in</span> <span class="n">images</span><span class="p">]</span>
<span class="n">ani</span> <span class="o">=</span> <span class="n">animation</span><span class="o">.</span><span class="n">ArtistAnimation</span><span class="p">(</span><span class="n">fig</span><span class="p">,</span> <span class="n">ims</span><span class="p">,</span> <span class="n">interval</span><span class="o">=</span><span class="mi">80</span><span class="p">,</span> <span class="n">blit</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">ani_html</span> <span class="o">=</span> <span class="n">ani</span><span class="o">.</span><span class="n">to_jshtml</span><span class="p">()</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="n">HTML</span><span class="p">(</span><span class="n">ani_html</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In [ ]:</div>
<div class="inner_cell">
<div class="input_area">
<div class="highlight hl-ipython3"><pre><span></span><span class="c1"># If you want to see the output of the model with the volume forced to opaque white, run this and re-evaluate</span>
<span class="c1"># with torch.no_grad():</span>
<span class="c1"># gm._implicit_functions[0]._fn.density.fill_(9.0)</span>
<span class="c1"># gm._implicit_functions[0]._fn.color.fill_(9.0)</span>
</pre></div>
</div>
</div>
</div>
</div>
</div></div></div></div></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 © 2023 Meta Platforms, 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>
Reference in New Issue View Git Blame Copy Permalink