Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Video Processor","local":"video-processor","sections":[{"title":"Usage Example","local":"usage-example","sections":[],"depth":3}],"depth":1}"> | |
| <link href="/docs/transformers/pr_37763/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/entry/start.36ad83a9.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/scheduler.18a86fab.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/singletons.40043f21.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/index.40ab8126.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/paths.c0bc9c78.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/entry/app.f97cd749.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/index.98837b22.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/nodes/0.1ed37a02.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/nodes/524.a6c5e1e0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/CodeBlock.8d0c2e8a.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/Heading.7e7e0c5b.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_37763/en/_app/immutable/chunks/index.499f366c.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Video Processor","local":"video-processor","sections":[{"title":"Usage Example","local":"usage-example","sections":[],"depth":3}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="video-processor" 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-processor"><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 Processor</span></h1> <p data-svelte-h="svelte-1bnodsr">A <strong>Video Processor</strong> is a utility responsible for preparing input features for video models, as well as handling the post-processing of their outputs. It provides transformations such as resizing, normalization, and conversion into PyTorch.</p> <p data-svelte-h="svelte-1mm69ua">The video processor extends the functionality of image processors by allowing the models to handle videos with a distinct set of arguments compared to images. It serves as the bridge between raw video data and the model, ensuring that input features are optimized for the VLM.</p> <p data-svelte-h="svelte-h4ncrp">Use <a href="/docs/transformers/pr_37763/en/main_classes/video_processor#transformers.BaseVideoProcessor.from_pretrained">from_pretrained()</a> to load a video processors configuration (image size, whether to normalize and rescale, etc.) from a video model on the Hugging Face <a href="https://hf.co" rel="nofollow">Hub</a> or local directory. The configuration for each pretrained model should be saved in a [video_preprocessor_config.json] file but older models might have the config saved in <a href="https://huggingface.co/llava-hf/llava-onevision-qwen2-0.5b-ov-hf/blob/main/preprocessor_config.json" rel="nofollow">preprocessor_config.json</a> file. Note that the latter is less preferred and will be removed in the future.</p> <h3 class="relative group"><a id="usage-example" 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="#usage-example"><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>Usage Example</span></h3> <p data-svelte-h="svelte-1ukoepa">Here’s an example of how to load a video processor with <a href="https://huggingface.co/llava-hf/llava-onevision-qwen2-0.5b-ov-hf" rel="nofollow"><code>llava-hf/llava-onevision-qwen2-0.5b-ov-hf</code></a> model:</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 --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoVideoProcessor | |
| processor = AutoVideoProcessor.from_pretrained(<span class="hljs-string">"llava-hf/llava-onevision-qwen2-0.5b-ov-hf"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-157dwxe">Currently, if using base image processor for videos, it processes video data by treating each frame as an individual image and applying transformations frame-by-frame. While functional, this approach is not highly efficient. Using <code>AutoVideoProcessor</code> allows us to take advantage of <strong>fast video processors</strong>, leveraging the <a href="https://pytorch.org/vision/stable/index.html" rel="nofollow">torchvision</a> library. Fast processors handle the whole batch of videos at once, without iterating over each video or frame. These updates introduce GPU acceleration and significantly enhance processing speed, especially for tasks requiring high throughput.</p> <p data-svelte-h="svelte-1wmclx8">Fast video processors are available for all models and are loaded by default when an <code>AutoVideoProcessor</code> is initialized. When using a fast video processor, you can also set the <code>device</code> argument to specify the device on which the processing should be done. By default, the processing is done on the same device as the inputs if the inputs are tensors, or on the CPU otherwise. For even more speed improvement, we can compile the processor when using ‘cuda’ as device.</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 --><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> transformers.video_utils <span class="hljs-keyword">import</span> load_video | |
| <span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoVideoProcessor | |
| video = load_video(<span class="hljs-string">"video.mp4"</span>) | |
| processor = AutoVideoProcessor.from_pretrained(<span class="hljs-string">"llava-hf/llava-onevision-qwen2-0.5b-ov-hf"</span>, device=<span class="hljs-string">"cuda"</span>) | |
| processor = torch.<span class="hljs-built_in">compile</span>(processor) | |
| processed_video = processor(video, return_tensors=<span class="hljs-string">"pt"</span>)<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/en/video_processors.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_l60gbg = { | |
| assets: "/docs/transformers/pr_37763/en", | |
| base: "/docs/transformers/pr_37763/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/pr_37763/en/_app/immutable/entry/start.36ad83a9.js"), | |
| import("/docs/transformers/pr_37763/en/_app/immutable/entry/app.f97cd749.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 524], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 11.7 kB
- Xet hash:
- 6594d67b4558def21e86fdec67c4a041a86aa85962981ef40405075fc95b8e34
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.