Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / datasets /main /en /image_classification.html

rtrm

28 days ago

download

raw

17.5 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Image classification","local":"image-classification","sections":[],"depth":1}">
	<link href="/docs/datasets/main/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/entry/start.4d44eea4.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/scheduler.bdbef820.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/singletons.36b689ad.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/index.8a885b74.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/paths.27092e28.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/entry/app.d83067e8.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/index.c0aea24a.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/nodes/0.bfb01985.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/nodes/21.21306850.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/Tip.31005f7d.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/CodeBlock.6ccca92e.js">
	<link rel="modulepreload" href="/docs/datasets/main/en/_app/immutable/chunks/EditOnGithub.725ee0c1.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Image classification","local":"image-classification","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="image-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="#image-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>Image classification</span></h1> <p data-svelte-h="svelte-sh7ab0">Image classification datasets are used to train a model to classify an entire image. There are a wide variety of applications enabled by these datasets such as identifying endangered wildlife species or screening for disease in medical images. This guide will show you how to apply transformations to an image classification dataset.</p> <p data-svelte-h="svelte-1qtuikq">Before you start, make sure you have up-to-date versions of <code>albumentations</code> and <code>cv2</code> installed:</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 -->pip install -U albumentations opencv-python<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1h05g43">This guide uses the <a href="https://huggingface.co/datasets/beans" rel="nofollow">Beans</a> dataset for identifying the type of bean plant disease based on an image of its leaf.</p> <p data-svelte-h="svelte-1yzvpv3">Load the dataset and take a look at an 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 --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset

	<span class="hljs-meta">>>> </span>dataset = load_dataset(<span class="hljs-string">"beans"</span>)
	<span class="hljs-meta">>>> </span>dataset[<span class="hljs-string">"train"</span>][<span class="hljs-number">10</span>]
	{<span class="hljs-string">'image'</span>: <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x500 at <span class="hljs-number">0x7F8D2F4D7A10</span>>,
	<span class="hljs-string">'image_file_path'</span>: <span class="hljs-string">'/root/.cache/huggingface/datasets/downloads/extracted/b0a21163f78769a2cf11f58dfc767fb458fc7cea5c05dccc0144a2c0f0bc1292/train/angular_leaf_spot/angular_leaf_spot_train.204.jpg'</span>,
	<span class="hljs-string">'labels'</span>: <span class="hljs-number">0</span>}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-jjwn46">The dataset has three fields:</p> <ul data-svelte-h="svelte-1aryjya"><li><code>image</code>: a PIL image object.</li> <li><code>image_file_path</code>: the path to the image file.</li> <li><code>labels</code>: the label or category of the image.</li></ul> <p data-svelte-h="svelte-z9j9vb">Next, check out an image:</p> <div class="flex justify-center" data-svelte-h="svelte-1fbgic4"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/img_clf.png"></div> <p data-svelte-h="svelte-1jan26m">Now apply some augmentations with <code>albumentations</code>. You’ll randomly crop the image, flip it horizontally, and adjust its brightness.</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">>>> </span><span class="hljs-keyword">import</span> cv2
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> albumentations
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np

	<span class="hljs-meta">>>> </span>transform = albumentations.Compose([
	<span class="hljs-meta">... </span> albumentations.RandomCrop(width=<span class="hljs-number">256</span>, height=<span class="hljs-number">256</span>),
	<span class="hljs-meta">... </span> albumentations.HorizontalFlip(p=<span class="hljs-number">0.5</span>),
	<span class="hljs-meta">... </span> albumentations.RandomBrightnessContrast(p=<span class="hljs-number">0.2</span>),
	<span class="hljs-meta">... </span>])<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-50733g">Create a function to apply the transformation to the images:</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">>>> </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">"pixel_values"</span>] = [
	<span class="hljs-meta">... </span> transform(image=np.array(image))[<span class="hljs-string">"image"</span>] <span class="hljs-keyword">for</span> image <span class="hljs-keyword">in</span> examples[<span class="hljs-string">"image"</span>]
	<span class="hljs-meta">... </span> ]
	<span class="hljs-meta">... </span>
	<span class="hljs-meta">... </span> <span class="hljs-keyword">return</span> examples<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1x4vpj6">Use the <a href="/docs/datasets/main/en/package_reference/main_classes#datasets.Dataset.set_transform">set_transform()</a> function to apply the transformation on-the-fly to batches of the dataset to consume less disk space:</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">>>> </span>dataset.set_transform(transforms)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-vr227m">You can verify the transformation worked by indexing into the <code>pixel_values</code> of the first 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 --><span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt

	<span class="hljs-meta">>>> </span>img = dataset[<span class="hljs-string">"train"</span>][<span class="hljs-number">0</span>][<span class="hljs-string">"pixel_values"</span>]
	<span class="hljs-meta">>>> </span>plt.imshow(img)<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-123w0ig"><img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/img_clf_aug.png"> <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/img_clf_aug.png"></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-rd509y">Now that you know how to process a dataset for image classification, learn
	<a href="https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/image_classification.ipynb" rel="nofollow">how to train an image classification model</a>
	and use it for inference.</p></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/datasets/blob/main/docs/source/image_classification.mdx" 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_w3org2 = {
	assets: "/docs/datasets/main/en",
	base: "/docs/datasets/main/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/datasets/main/en/_app/immutable/entry/start.4d44eea4.js"),
	import("/docs/datasets/main/en/_app/immutable/entry/app.d83067e8.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 21],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 17.5 kB
Xet hash:: 590d4a5f838a2ed12b3cde6aa644f4c82856d23a4018940a268990d2603f914e

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