Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / hub /pr_2521 /en /datasets-video.html
HuggingFaceDocBuilder's picture
HuggingFaceDocBuilder
download
raw
42.7 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Video Dataset&quot;,&quot;local&quot;:&quot;video-dataset&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Only videos&quot;,&quot;local&quot;:&quot;only-videos&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Additional columns&quot;,&quot;local&quot;:&quot;additional-columns&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Relative paths&quot;,&quot;local&quot;:&quot;relative-paths&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Video classification&quot;,&quot;local&quot;:&quot;video-classification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Large scale datasets&quot;,&quot;local&quot;:&quot;large-scale-datasets&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;WebDataset format&quot;,&quot;local&quot;:&quot;webdataset-format&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/hub/pr_2521/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/entry/start.d19e5ca7.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/scheduler.409792a1.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/singletons.1ece723a.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/index.0f0d9f26.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/paths.a67d9216.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/entry/app.98ab229a.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/preload-helper.78e52d9f.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/index.92d389ff.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/nodes/0.7799902b.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/nodes/65.d0f61a19.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/CopyLLMTxtMenu.dcf7fb47.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.0c189c7e.js">
 <link rel="modulepreload" href="/docs/hub/pr_2521/en/_app/immutable/chunks/CodeBlock.5ed269c1.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Video Dataset&quot;,&quot;local&quot;:&quot;video-dataset&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Only videos&quot;,&quot;local&quot;:&quot;only-videos&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Additional columns&quot;,&quot;local&quot;:&quot;additional-columns&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Relative paths&quot;,&quot;local&quot;:&quot;relative-paths&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Video classification&quot;,&quot;local&quot;:&quot;video-classification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Large scale datasets&quot;,&quot;local&quot;:&quot;large-scale-datasets&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;WebDataset format&quot;,&quot;local&quot;:&quot;webdataset-format&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div> <h1 class="relative group"><a id="video-dataset" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#video-dataset"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Video Dataset</span></h1> <p data-svelte-h="svelte-ruyvs2">This guide will show you how to configure your dataset repository with video files.</p> <p data-svelte-h="svelte-u1gdfq">A dataset with a supported structure and <a href="./datasets-adding#file-formats">file formats</a> automatically has a Dataset Viewer on its page on the Hub.</p> <p data-svelte-h="svelte-gs67nj">Additional information about your videos - such as captions or bounding boxes for object detection - is automatically loaded as long as you include this information in a metadata file (<code>metadata.csv</code>/<code>metadata.jsonl</code>/<code>metadata.parquet</code>).</p> <p data-svelte-h="svelte-1ctzmqu">Alternatively, videos can be in Parquet files or in TAR archives following the <a href="https://github.com/webdataset/webdataset" rel="nofollow">WebDataset</a> format.</p> <h2 class="relative group"><a id="only-videos" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#only-videos"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Only videos</span></h2> <p data-svelte-h="svelte-a55o50">If your dataset only consists of one column with videos, you can simply store your video files at the root:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
├── 1.mp4
├── 2.mp4
├── 3.mp4
└── 4.mp4<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-19pjkki">or in a subdirectory:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
└── videos
 ├── 1.mp4
 ├── 2.mp4
 ├── 3.mp4
 └── 4.mp4<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ppx257">Multiple <a href="./datasets-adding#file-formats">formats</a> are supported at the same time, including MP4, MOV and AVI.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
└── videos
 ├── <span class="hljs-number">1</span><span class="hljs-selector-class">.mp4</span>
 ├── <span class="hljs-number">2</span><span class="hljs-selector-class">.mov</span>
 └── <span class="hljs-number">3</span>.avi<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1wi2jdv">If you have several splits, you can put your videos into directories named accordingly:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
├── train
│   ├── 1.mp4
│   └── 2.mp4
└── test
 ├── 3.mp4
 └── 4.mp4<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-kefeul">See <a href="./datasets-file-names-and-splits">File names and splits</a> for more information and other ways to organize data by splits.</p> <h2 class="relative group"><a id="additional-columns" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#additional-columns"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Additional columns</span></h2> <p data-svelte-h="svelte-1pmu5k4">If there is additional information you’d like to include about your dataset, like text captions or bounding boxes, add it as a <code>metadata.csv</code> file in your repository. This lets you quickly create datasets for different computer vision tasks like <a href="https://huggingface.co/tasks/text-to-video" rel="nofollow">video generation</a> or <a href="https://huggingface.co/tasks/object-detection" rel="nofollow">object detection</a>.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
└── train
 ├── 1.mp4
 ├── 2.mp4
 ├── 3.mp4
 ├── 4.mp4
 └── metadata.csv<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-d633kt">Your <code>metadata.csv</code> file must have a <code>file_name</code> column which links video files with their metadata:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class="language-csv "><!-- HTML_TAG_START -->file_name,<span class="hljs-keyword">text</span>
<span class="hljs-number">1.</span>mp4,<span class="hljs-keyword">an</span> animation <span class="hljs-keyword">of</span> <span class="hljs-keyword">a</span> green pokemon <span class="hljs-keyword">with</span> red eyes
<span class="hljs-number">2.</span>mp4,<span class="hljs-keyword">a</span> <span class="hljs-keyword">short</span> video <span class="hljs-keyword">of</span> <span class="hljs-keyword">a</span> green <span class="hljs-keyword">and</span> yellow toy <span class="hljs-keyword">with</span> <span class="hljs-keyword">a</span> red nose
<span class="hljs-number">3.</span>mp4,<span class="hljs-keyword">a</span> red <span class="hljs-keyword">and</span> white ball shows <span class="hljs-keyword">an</span> angry look <span class="hljs-keyword">on</span> <span class="hljs-title">its</span> <span class="hljs-title">face</span>
<span class="hljs-number">4.</span>mp4,<span class="hljs-keyword">a</span> cartoon ball is smiling<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1md2l6g">You can also use a <a href="https://jsonlines.org/" rel="nofollow">JSONL</a> file <code>metadata.jsonl</code>:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class="language-jsonl "><!-- HTML_TAG_START -->{<span class="hljs-comment">&quot;file_name&quot;</span>: <span class="hljs-comment">&quot;1.mp4&quot;</span>,<span class="hljs-comment">&quot;text&quot;</span>: <span class="hljs-comment">&quot;an animation of a green pokemon with red eyes&quot;</span>}
{<span class="hljs-comment">&quot;file_name&quot;</span>: <span class="hljs-comment">&quot;2.mp4&quot;</span>,<span class="hljs-comment">&quot;text&quot;</span>: <span class="hljs-comment">&quot;a short video of a green and yellow toy with a red nose&quot;</span>}
{<span class="hljs-comment">&quot;file_name&quot;</span>: <span class="hljs-comment">&quot;3.mp4&quot;</span>,<span class="hljs-comment">&quot;text&quot;</span>: <span class="hljs-comment">&quot;a red and white ball shows an angry look on its face&quot;</span>}
{<span class="hljs-comment">&quot;file_name&quot;</span>: <span class="hljs-comment">&quot;4.mp4&quot;</span>,<span class="hljs-comment">&quot;text&quot;</span>: <span class="hljs-comment">&quot;a cartoon ball is smiling&quot;</span>}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-17vzj19">And for bigger datasets or if you are interested in advanced data retrieval features, you can use a <a href="https://parquet.apache.org/" rel="nofollow">Parquet</a> file <code>metadata.parquet</code>.</p> <h2 class="relative group"><a id="relative-paths" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#relative-paths"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Relative paths</span></h2> <p data-svelte-h="svelte-xowpes">Metadata file must be located either in the same directory with the videos it is linked to, or in any parent directory, like in this example:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
└── train
 ├── videos
 │   ├── 1.mp4
 │   ├── 2.mp4
 │   ├── 3.mp4
 │   └── 4.mp4
 └── metadata.csv<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-18wqlz9">In this case, the <code>file_name</code> column must be a full relative path to the videos, not just the filename:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class="language-csv "><!-- HTML_TAG_START -->file_name,<span class="hljs-keyword">text</span>
videos/<span class="hljs-number">1.</span>mp4,<span class="hljs-keyword">an</span> animation <span class="hljs-keyword">of</span> <span class="hljs-keyword">a</span> green pokemon <span class="hljs-keyword">with</span> red eyes
videos/<span class="hljs-number">2.</span>mp4,<span class="hljs-keyword">a</span> <span class="hljs-keyword">short</span> video <span class="hljs-keyword">of</span> <span class="hljs-keyword">a</span> green <span class="hljs-keyword">and</span> yellow toy <span class="hljs-keyword">with</span> <span class="hljs-keyword">a</span> red nose
videos/<span class="hljs-number">3.</span>mp4,<span class="hljs-keyword">a</span> red <span class="hljs-keyword">and</span> white ball shows <span class="hljs-keyword">an</span> angry look <span class="hljs-keyword">on</span> <span class="hljs-title">its</span> <span class="hljs-title">face</span>
videos/<span class="hljs-number">4.</span>mp4,<span class="hljs-keyword">a</span> cartoon ball is smiling<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-qenyy7">Metadata files cannot be put in subdirectories of a directory with the videos.</p> <p data-svelte-h="svelte-19dvg1v">More generally, any column named <code>file_name</code> or <code>*_file_name</code> should contain the full relative path to the videos.</p> <h2 class="relative group"><a id="video-classification" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#video-classification"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Video classification</span></h2> <p data-svelte-h="svelte-1u3l8ib">For video classification datasets, you can also use a simple setup: use directories to name the video classes. Store your video files in a directory structure like:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
├── green
│   ├── 1.mp4
│   └── 2.mp4
└── red
 ├── 3.mp4
 └── 4.mp4<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-jgm2yq">The dataset created with this structure contains two columns: <code>video</code> and <code>label</code> (with values <code>green</code> and <code>red</code>).</p> <p data-svelte-h="svelte-jxxgnh">You can also provide multiple splits. To do so, your dataset directory should have the following structure (see <a href="./datasets-file-names-and-splits">File names and splits</a> for more information):</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
├── test
│   ├── <span class="hljs-built_in">green</span>
│   │   └── <span class="hljs-number">2.</span>mp4
│   └── <span class="hljs-built_in">red</span>
│   └── <span class="hljs-number">4.</span>mp4
└── train
 ├── <span class="hljs-built_in">green</span>
 │   └── <span class="hljs-number">1.</span>mp4
 └── <span class="hljs-built_in">red</span>
 └── <span class="hljs-number">3.</span>mp4<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-op9ivs">You can disable this automatic addition of the <code>label</code> column in the <a href="./datasets-manual-configuration">YAML configuration</a>. If your directory names have no special meaning, set <code>drop_labels: true</code> in the README header:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class="language-yaml "><!-- HTML_TAG_START --><span class="hljs-attr">configs:</span>
 <span class="hljs-bullet">-</span> <span class="hljs-attr">config_name:</span> <span class="hljs-string">default</span> <span class="hljs-comment"># Name of the dataset subset, if applicable.</span>
 <span class="hljs-attr">drop_labels:</span> <span class="hljs-literal">true</span><!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="large-scale-datasets" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#large-scale-datasets"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Large scale datasets</span></h2> <h3 class="relative group"><a id="webdataset-format" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#webdataset-format"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>WebDataset format</span></h3> <p data-svelte-h="svelte-zm55y0">The <a href="./datasets-webdataset">WebDataset</a> format is well suited for large scale video datasets.
It consists of TAR archives containing videos and their metadata and is optimized for streaming. It is useful if you have a large number of videos and to get streaming data loaders for large scale training.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->my_dataset_repository/
├── train<span class="hljs-string">-0000</span>.tar
├── train<span class="hljs-string">-0001</span>.tar
├── ...
└── train<span class="hljs-string">-1023</span>.tar<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1d0rexv">To make a WebDataset TAR archive, create a directory containing the videos and metadata files to be archived and create the TAR archive using e.g. the <code>tar</code> command.
The usual size per archive is generally around 1GB.
Make sure each video and metadata pair share the same file prefix, for example:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=" "><!-- HTML_TAG_START -->train-<span class="hljs-number">0000</span>/
├── <span class="hljs-number">000</span><span class="hljs-selector-class">.mp4</span>
├── <span class="hljs-number">000</span><span class="hljs-selector-class">.json</span>
├── <span class="hljs-number">001</span><span class="hljs-selector-class">.mp4</span>
├── <span class="hljs-number">001</span><span class="hljs-selector-class">.json</span>
├── ...
├── <span class="hljs-number">999</span><span class="hljs-selector-class">.mp4</span>
└── <span class="hljs-number">999</span>.json<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-6vjnbz">Note that for user convenience and to enable the <a href="./data-studio">Dataset Viewer</a>, every dataset hosted in the Hub is automatically converted to Parquet format up to 5GB. Since videos can be quite large, the URLs to the videos are stored in the converted Parquet data without the video bytes themselves. Read more about it in the <a href="./data-studio#access-the-parquet-files">Parquet format</a> documentation.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hub-docs/blob/main/docs/hub/datasets-video.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_1bollga = {
 assets: "/docs/hub/pr_2521/en",
 base: "/docs/hub/pr_2521/en",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/hub/pr_2521/en/_app/immutable/entry/start.d19e5ca7.js"),
 import("/docs/hub/pr_2521/en/_app/immutable/entry/app.98ab229a.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 65],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
42.7 kB
·
Xet hash:
1a3992c35e5d29593536161543677043313eb8ec14f44f86e514d7e477c15c17

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.