transformers/main/ro/video_processors.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Procesatoare video&quot;,&quot;local&quot;:&quot;procesatoare-video&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Exemplu de utilizare&quot;,&quot;local&quot;:&quot;exemplu-de-utilizare&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
		<link href="/docs/transformers/main/ro/_app/immutable/entry/start.DwnOcLC_.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/chunks/CL87Xr5_.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/chunks/Cl6kX2N0.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/entry/app.Dw7RcaNl.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/chunks/BzzeShVL.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/chunks/DWwSmaYb.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/chunks/DM0RASQS.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/nodes/0.DMmsXSdS.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/chunks/C8aKV6he.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/nodes/34.sLA2P8u0.js" rel="modulepreload">
		<link href="/docs/transformers/main/ro/_app/immutable/chunks/CjTxHwdC.js" rel="modulepreload">
		<!--oivice--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Procesatoare video&quot;,&quot;local&quot;:&quot;procesatoare-video&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Exemplu de utilizare&quot;,&quot;local&quot;:&quot;exemplu-de-utilizare&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
		<link href="/docs/transformers/main/ro/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><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> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="procesatoare-video" 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="#procesatoare-video"><span><svg 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>Procesatoare video</span></h1><!--]--><!----> <p>Un <strong>procesator video</strong> este un utilitar responsabil cu pregătirea feature-urilor de input pentru modelele video, cât și cu post-procesarea output-urilor lor. Furnizează transformări precum redimensionarea, normalizarea și conversia în PyTorch.</p> <p>Procesatorul video extinde funcționalitatea procesatoarelor de imagini, permițând modelelor să gestioneze videoclipuri cu un set distinct de argumente față de imagini. Servește drept punte între datele video brute și model, asigurând că feature-urile de input sunt optimizate pentru VLM.</p> <p>Folosește <code>from_pretrained()</code> ca să încarci configurația unui procesator video (dimensiunea imaginii, dacă să normalizeze și rescaleze etc.) de la un model video de pe Hub-ul Hugging Face sau dintr-un director local. Configurația pentru fiecare model preantrenat ar trebui salvată într-un fișier [video_preprocessor_config.json], dar modelele mai vechi pot avea configurația salvată în fișierul <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>. Reține că acesta din urmă este mai puțin preferat și va fi eliminat în viitor.</p> <!--[1--><h2 class="relative group"><a id="exemplu-de-utilizare" 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="#exemplu-de-utilizare"><span><svg 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>Exemplu de utilizare</span></h2><!--]--><!----> <p>Iată un exemplu de cum să încarci un procesator video cu modelul <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>:</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 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-python "><!----><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoVideoProcessor

processor = AutoVideoProcessor.from_pretrained(<span class="hljs-string">&quot;llava-hf/llava-onevision-qwen2-0.5b-ov-hf&quot;</span>)<!----></pre></div><!----> <p>Dacă folosești un procesator de imagini de bază pentru videoclipuri, acesta procesează datele video tratând fiecare cadru ca o imagine individuală și aplică transformările cadru cu cadru. Deși funcțională, această abordare nu este foarte eficientă. Folosind <code>AutoVideoProcessor</code> poți să profiți de <strong>procesatoarele video rapide</strong>, care valorifică biblioteca <a href="https://pytorch.org/vision/stable/index.html" rel="nofollow">torchvision</a>. Procesatoarele rapide gestionează întregul batch de videoclipuri dintr-o dată, fără să itereze pe fiecare video sau cadru. Aceste actualizări introduc accelerarea GPU și cresc semnificativ viteza de procesare, mai ales pentru task-uri care necesită un throughput ridicat.</p> <p>Procesatoarele video rapide sunt disponibile pentru toate modelele și sunt încărcate implicit când se inițializează un <code>AutoVideoProcessor</code>. Când folosești un procesator video rapid, poți seta și argumentul <code>device</code> ca să specifici device-ul pe care se face procesarea. Implicit, procesarea se face pe același device ca input-urile dacă input-urile sunt tensori, altfel pe CPU. Ca să câștigi și mai multă viteză, poți compila procesatorul când folosești <code>cuda</code> ca 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 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-python "><!----><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">&quot;video.mp4&quot;</span>)
processor = AutoVideoProcessor.from_pretrained(<span class="hljs-string">&quot;llava-hf/llava-onevision-qwen2-0.5b-ov-hf&quot;</span>, device=<span class="hljs-string">&quot;cuda&quot;</span>)
processor = torch.<span class="hljs-built_in">compile</span>(processor)
processed_video = processor(video, return_tensors=<span class="hljs-string">&quot;pt&quot;</span>)<!----></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/ro/video_processors.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><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
			
			<script>
				{
					__sveltekit_10j3czc = {
						base: "/docs/transformers/main/ro",
						assets: "/docs/transformers/main/ro"
					};

					const element = document.currentScript.parentElement;

					Promise.all([
						import("/docs/transformers/main/ro/_app/immutable/entry/start.DwnOcLC_.js"),
						import("/docs/transformers/main/ro/_app/immutable/entry/app.Dw7RcaNl.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 34],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>