Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / transformers /pr_33913 /es /tasks /image_classification.html
rtrm's picture
rtrm
download
raw
35 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Clasificación de imágenes&quot;,&quot;local&quot;:&quot;clasificación-de-imágenes&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Carga el dataset Food-101&quot;,&quot;local&quot;:&quot;carga-el-dataset-food-101&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Preprocesa&quot;,&quot;local&quot;:&quot;preprocesa&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Entrena&quot;,&quot;local&quot;:&quot;entrena&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/transformers/pr_33913/es/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/entry/start.41996def.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/scheduler.36a0863c.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/singletons.be078126.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/index.733708bb.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/paths.9d726baf.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/entry/app.9ed505df.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/index.f891bdb2.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/nodes/0.cfca1b02.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/nodes/35.4b4446df.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/Tip.a8272f7f.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/Youtube.0cbacd3d.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/CodeBlock.3ec784ea.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/es/_app/immutable/chunks/EditOnGithub.a58e27a9.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Clasificación de imágenes&quot;,&quot;local&quot;:&quot;clasificación-de-imágenes&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Carga el dataset Food-101&quot;,&quot;local&quot;:&quot;carga-el-dataset-food-101&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Preprocesa&quot;,&quot;local&quot;:&quot;preprocesa&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Entrena&quot;,&quot;local&quot;:&quot;entrena&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="clasificación-de-imágenes" 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="#clasificación-de-imágenes"><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>Clasificación de imágenes</span></h1> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/tjAIM7BOYhw" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-1in2i61">La clasificación de imágenes asigna una etiqueta o clase a una imagen. A diferencia de la clasificación de texto o audio, las entradas son los valores de los píxeles que representan una imagen. La clasificación de imágenes tiene muchos usos, como la detección de daños tras una catástrofe, el control de la salud de los cultivos o la búsqueda de signos de enfermedad en imágenes médicas.</p> <p data-svelte-h="svelte-16asmdu">Esta guía te mostrará como hacer fine-tune al <a href="https://huggingface.co/docs/transformers/v4.16.2/en/model_doc/vit" rel="nofollow">ViT</a> en el dataset <a href="https://huggingface.co/datasets/food101" rel="nofollow">Food-101</a> para clasificar un alimento en una imagen.</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-x2f51r">Consulta la <a href="https://huggingface.co/tasks/audio-classification" rel="nofollow">página de la tarea</a> de clasificación de imágenes para obtener más información sobre sus modelos, datasets y métricas asociadas.</p></div> <h2 class="relative group"><a id="carga-el-dataset-food-101" 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="#carga-el-dataset-food-101"><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>Carga el dataset Food-101</span></h2> <p data-svelte-h="svelte-1i4xr2v">Carga solo las primeras 5000 imágenes del dataset Food-101 de la biblioteca 🤗 de Datasets ya que es bastante grande:</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-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset
<span class="hljs-meta">&gt;&gt;&gt; </span>food = load_dataset(<span class="hljs-string">&quot;food101&quot;</span>, split=<span class="hljs-string">&quot;train[:5000]&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-welj5e">Divide el dataset en un train y un test set:</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-meta">&gt;&gt;&gt; </span>food = food.train_test_split(test_size=<span class="hljs-number">0.2</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ccba5i">A continuación, observa un ejemplo:</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-meta">&gt;&gt;&gt; </span>food[<span class="hljs-string">&quot;train&quot;</span>][<span class="hljs-number">0</span>]
{<span class="hljs-string">&#x27;image&#x27;</span>: &lt;PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=512x512 at <span class="hljs-number">0x7F52AFC8AC50</span>&gt;,
 <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-number">79</span>}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1cy1r9x">El campo <code>image</code> contiene una imagen PIL, y cada <code>label</code> es un número entero que representa una clase. Crea un diccionario que asigne un nombre de label a un entero y viceversa. El mapeo ayudará al modelo a recuperar el nombre de label a partir del número de la misma:</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-meta">&gt;&gt;&gt; </span>labels = food[<span class="hljs-string">&quot;train&quot;</span>].features[<span class="hljs-string">&quot;label&quot;</span>].names
<span class="hljs-meta">&gt;&gt;&gt; </span>label2id, id2label = <span class="hljs-built_in">dict</span>(), <span class="hljs-built_in">dict</span>()
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">for</span> i, label <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(labels):
<span class="hljs-meta">... </span> label2id[label] = <span class="hljs-built_in">str</span>(i)
<span class="hljs-meta">... </span> id2label[<span class="hljs-built_in">str</span>(i)] = label<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-dj6pq1">Ahora puedes convertir el número de label en un nombre de label para obtener más información:</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-meta">&gt;&gt;&gt; </span>id2label[<span class="hljs-built_in">str</span>(<span class="hljs-number">79</span>)]
<span class="hljs-string">&#x27;prime_rib&#x27;</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1enyby9">Cada clase de alimento - o label - corresponde a un número; <code>79</code> indica una costilla de primera en el ejemplo anterior.</p> <h2 class="relative group"><a id="preprocesa" 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="#preprocesa"><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>Preprocesa</span></h2> <p data-svelte-h="svelte-b7wzno">Carga el image processor de ViT para procesar la imagen en un tensor:</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-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoImageProcessor
<span class="hljs-meta">&gt;&gt;&gt; </span>image_processor = AutoImageProcessor.from_pretrained(<span class="hljs-string">&quot;google/vit-base-patch16-224-in21k&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-oh33tg">Aplica varias transformaciones de imagen al dataset para hacer el modelo más robusto contra el overfitting. En este caso se utilizará el módulo <a href="https://pytorch.org/vision/stable/transforms.html" rel="nofollow"><code>transforms</code></a> de torchvision. Recorta una parte aleatoria de la imagen, cambia su tamaño y normalízala con la media y la desviación estándar de la imagen:</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-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> torchvision.transforms <span class="hljs-keyword">import</span> RandomResizedCrop, Compose, Normalize, ToTensor
<span class="hljs-meta">&gt;&gt;&gt; </span>normalize = Normalize(mean=image_processor.image_mean, std=image_processor.image_std)
<span class="hljs-meta">&gt;&gt;&gt; </span>_transforms = Compose([RandomResizedCrop(image_processor.size[<span class="hljs-string">&quot;height&quot;</span>]), ToTensor(), normalize])<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1tpprs0">Crea una función de preprocesamiento que aplique las transformaciones y devuelva los <code>pixel_values</code> - los inputs al modelo - de la imagen:</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-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">transforms</span>(<span class="hljs-params">examples</span>):
<span class="hljs-meta">... </span> examples[<span class="hljs-string">&quot;pixel_values&quot;</span>] = [_transforms(img.convert(<span class="hljs-string">&quot;RGB&quot;</span>)) <span class="hljs-keyword">for</span> img <span class="hljs-keyword">in</span> examples[<span class="hljs-string">&quot;image&quot;</span>]]
<span class="hljs-meta">... </span> <span class="hljs-keyword">del</span> examples[<span class="hljs-string">&quot;image&quot;</span>]
<span class="hljs-meta">... </span> <span class="hljs-keyword">return</span> examples<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-838aua">Utiliza el método <a href="https://huggingface.co/docs/datasets/package_reference/main_classes?#datasets.Dataset.with_transform" rel="nofollow"><code>with_transform</code></a> de 🤗 Dataset para aplicar las transformaciones sobre todo el dataset. Las transformaciones se aplican sobre la marcha cuando se carga un elemento del dataset:</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-meta">&gt;&gt;&gt; </span>food = food.with_transform(transforms)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1qktm8g">Utiliza <code>DefaultDataCollator</code> para crear un batch de ejemplos. A diferencia de otros data collators en 🤗 Transformers, el DefaultDataCollator no aplica un preprocesamiento adicional como el padding.</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-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> DefaultDataCollator
<span class="hljs-meta">&gt;&gt;&gt; </span>data_collator = DefaultDataCollator()<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="entrena" 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="#entrena"><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>Entrena</span></h2> <p data-svelte-h="svelte-1lx22e">Carga ViT con <code>AutoModelForImageClassification</code>. Especifica el número de labels, y pasa al modelo el mapping entre el número de label y la clase de label:</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-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForImageClassification, TrainingArguments, Trainer
<span class="hljs-meta">&gt;&gt;&gt; </span>model = AutoModelForImageClassification.from_pretrained(
<span class="hljs-meta">... </span> <span class="hljs-string">&quot;google/vit-base-patch16-224-in21k&quot;</span>,
<span class="hljs-meta">... </span> num_labels=<span class="hljs-built_in">len</span>(labels),
<span class="hljs-meta">... </span> id2label=id2label,
<span class="hljs-meta">... </span> label2id=label2id,
<span class="hljs-meta">... </span>)<!-- HTML_TAG_END --></pre></div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-vd1d0s">Si no estás familiarizado con el fine-tuning de un modelo con el <code>Trainer</code>, echa un vistazo al tutorial básico <a href="../training#finetune-with-trainer">aquí</a>!</p></div> <p data-svelte-h="svelte-yip3uv">Al llegar a este punto, solo quedan tres pasos:</p> <ol data-svelte-h="svelte-2mt88g"><li>Define tus hiperparámetros de entrenamiento en <code>TrainingArguments</code>. Es importante que no elimines las columnas que no se utilicen, ya que esto hará que desaparezca la columna <code>image</code>. Sin la columna <code>image</code> no puedes crear <code>pixel_values</code>. Establece <code>remove_unused_columns=False</code> para evitar este comportamiento.</li> <li>Pasa los training arguments al <code>Trainer</code> junto con el modelo, los datasets, tokenizer y data collator.</li> <li>Llama <code>train()</code> para hacer fine-tune de tu modelo.</li></ol> <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-meta">&gt;&gt;&gt; </span>training_args = TrainingArguments(
<span class="hljs-meta">... </span> output_dir=<span class="hljs-string">&quot;./results&quot;</span>,
<span class="hljs-meta">... </span> per_device_train_batch_size=<span class="hljs-number">16</span>,
<span class="hljs-meta">... </span> eval_strategy=<span class="hljs-string">&quot;steps&quot;</span>,
<span class="hljs-meta">... </span> num_train_epochs=<span class="hljs-number">4</span>,
<span class="hljs-meta">... </span> fp16=<span class="hljs-literal">True</span>,
<span class="hljs-meta">... </span> save_steps=<span class="hljs-number">100</span>,
<span class="hljs-meta">... </span> eval_steps=<span class="hljs-number">100</span>,
<span class="hljs-meta">... </span> logging_steps=<span class="hljs-number">10</span>,
<span class="hljs-meta">... </span> learning_rate=<span class="hljs-number">2e-4</span>,
<span class="hljs-meta">... </span> save_total_limit=<span class="hljs-number">2</span>,
<span class="hljs-meta">... </span> remove_unused_columns=<span class="hljs-literal">False</span>,
<span class="hljs-meta">... </span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>trainer = Trainer(
<span class="hljs-meta">... </span> model=model,
<span class="hljs-meta">... </span> args=training_args,
<span class="hljs-meta">... </span> data_collator=data_collator,
<span class="hljs-meta">... </span> train_dataset=food[<span class="hljs-string">&quot;train&quot;</span>],
<span class="hljs-meta">... </span> eval_dataset=food[<span class="hljs-string">&quot;test&quot;</span>],
<span class="hljs-meta">... </span> processing_class=image_processor,
<span class="hljs-meta">... </span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>trainer.train()<!-- HTML_TAG_END --></pre></div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-1qqa7s7">Para ver un ejemplo más a profundidad de cómo hacer fine-tune a un modelo para clasificación de imágenes, echa un vistazo al correspondiente <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb" rel="nofollow">PyTorch notebook</a>.</p></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/es/tasks/image_classification.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_yx9cql = {
 assets: "/docs/transformers/pr_33913/es",
 base: "/docs/transformers/pr_33913/es",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/transformers/pr_33913/es/_app/immutable/entry/start.41996def.js"),
 import("/docs/transformers/pr_33913/es/_app/immutable/entry/app.9ed505df.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 35],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
35 kB
·
Xet hash:
7712c5377ecc9b9a8c81a434e3429f66c0b74e04e229c0af0dba6181bc56df33

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