Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers /pr_33913 /en /tasks /zero_shot_object_detection.html

rtrm

29 days ago

download

raw

52 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Zero-shot object detection","local":"zero-shot-object-detection","sections":[{"title":"Zero-shot object detection pipeline","local":"zero-shot-object-detection-pipeline","sections":[],"depth":2},{"title":"Text-prompted zero-shot object detection by hand","local":"text-prompted-zero-shot-object-detection-by-hand","sections":[],"depth":2},{"title":"Batch processing","local":"batch-processing","sections":[],"depth":2},{"title":"Image-guided object detection","local":"image-guided-object-detection","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/pr_33913/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/entry/start.b67f883f.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/scheduler.25b97de1.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/singletons.62a184e0.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/index.e188933d.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/paths.51881b9e.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/entry/app.e436b1f2.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/index.d9030fc9.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/nodes/0.05e395f5.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/nodes/444.b9d16235.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/CodeBlock.e6cd0d95.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/DocNotebookDropdown.5ea6cb78.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/globals.7f7f1b26.js">
	<link rel="modulepreload" href="/docs/transformers/pr_33913/en/_app/immutable/chunks/EditOnGithub.91d95064.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Zero-shot object detection","local":"zero-shot-object-detection","sections":[{"title":"Zero-shot object detection pipeline","local":"zero-shot-object-detection-pipeline","sections":[],"depth":2},{"title":"Text-prompted zero-shot object detection by hand","local":"text-prompted-zero-shot-object-detection-by-hand","sections":[],"depth":2},{"title":"Batch processing","local":"batch-processing","sections":[],"depth":2},{"title":"Image-guided object detection","local":"image-guided-object-detection","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="zero-shot-object-detection" 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="#zero-shot-object-detection"><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>Zero-shot object detection</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0"> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"> </button> </div> <div class="relative colab-dropdown "> <button class=" " type="button"> <img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"> </button> </div></div> <p data-svelte-h="svelte-1g13my9">Traditionally, models used for <a href="object_detection">object detection</a> require labeled image datasets for training,
	and are limited to detecting the set of classes from the training data.</p> <p data-svelte-h="svelte-1l6ldib">Zero-shot object detection is supported by the <a href="../model_doc/owlvit">OWL-ViT</a> model which uses a different approach. OWL-ViT
	is an open-vocabulary object detector. It means that it can detect objects in images based on free-text queries without
	the need to fine-tune the model on labeled datasets.</p> <p data-svelte-h="svelte-17kqb94">OWL-ViT leverages multi-modal representations to perform open-vocabulary detection. It combines <a href="../model_doc/clip">CLIP</a> with
	lightweight object classification and localization heads. Open-vocabulary detection is achieved by embedding free-text queries with the text encoder of CLIP and using them as input to the object classification and localization heads,
	which associate images with their corresponding textual descriptions, while ViT processes image patches as inputs. The authors
	of OWL-ViT first trained CLIP from scratch and then fine-tuned OWL-ViT end to end on standard object detection datasets using
	a bipartite matching loss.</p> <p data-svelte-h="svelte-c41x80">With this approach, the model can detect objects based on textual descriptions without prior training on labeled datasets.</p> <p data-svelte-h="svelte-leihjc">In this guide, you will learn how to use OWL-ViT:</p> <ul data-svelte-h="svelte-v8ep8v"><li>to detect objects based on text prompts</li> <li>for batch object detection</li> <li>for image-guided object detection</li></ul> <p data-svelte-h="svelte-1c9nexd">Before you begin, make sure you have all the necessary libraries 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 -q transformers<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="zero-shot-object-detection-pipeline" 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="#zero-shot-object-detection-pipeline"><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>Zero-shot object detection pipeline</span></h2> <p data-svelte-h="svelte-1gjr0f4">The simplest way to try out inference with OWL-ViT is to use it in a <a href="/docs/transformers/pr_33913/en/main_classes/pipelines#transformers.pipeline">pipeline()</a>. Instantiate a pipeline
	for zero-shot object detection from a <a href="https://huggingface.co/models?other=owlvit" rel="nofollow">checkpoint on the Hugging Face Hub</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 --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

	<span class="hljs-meta">>>> </span>checkpoint = <span class="hljs-string">"google/owlv2-base-patch16-ensemble"</span>
	<span class="hljs-meta">>>> </span>detector = pipeline(model=checkpoint, task=<span class="hljs-string">"zero-shot-object-detection"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-henpll">Next, choose an image you’d like to detect objects in. Here we’ll use the image of astronaut Eileen Collins that is
	a part of the <a href="https://www.nasa.gov/multimedia/imagegallery/index.html" rel="nofollow">NASA</a> Great Images 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">>>> </span><span class="hljs-keyword">import</span> skimage
	<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">from</span> PIL <span class="hljs-keyword">import</span> Image

	<span class="hljs-meta">>>> </span>image = skimage.data.astronaut()
	<span class="hljs-meta">>>> </span>image = Image.fromarray(np.uint8(image)).convert(<span class="hljs-string">"RGB"</span>)

	<span class="hljs-meta">>>> </span>image<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-17qmfee"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_1.png" alt="Astronaut Eileen Collins"></div> <p data-svelte-h="svelte-baa5my">Pass the image and the candidate object labels to look for to the pipeline.
	Here we pass the image directly; other suitable options include a local path to an image or an image url. We also pass text descriptions for all items we want to query the image for.</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>predictions = detector(
	<span class="hljs-meta">... </span> image,
	<span class="hljs-meta">... </span> candidate_labels=[<span class="hljs-string">"human face"</span>, <span class="hljs-string">"rocket"</span>, <span class="hljs-string">"nasa badge"</span>, <span class="hljs-string">"star-spangled banner"</span>],
	<span class="hljs-meta">... </span>)
	<span class="hljs-meta">>>> </span>predictions
	[{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.3571370542049408</span>,
	<span class="hljs-string">'label'</span>: <span class="hljs-string">'human face'</span>,
	<span class="hljs-string">'box'</span>: {<span class="hljs-string">'xmin'</span>: <span class="hljs-number">180</span>, <span class="hljs-string">'ymin'</span>: <span class="hljs-number">71</span>, <span class="hljs-string">'xmax'</span>: <span class="hljs-number">271</span>, <span class="hljs-string">'ymax'</span>: <span class="hljs-number">178</span>}},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.28099656105041504</span>,
	<span class="hljs-string">'label'</span>: <span class="hljs-string">'nasa badge'</span>,
	<span class="hljs-string">'box'</span>: {<span class="hljs-string">'xmin'</span>: <span class="hljs-number">129</span>, <span class="hljs-string">'ymin'</span>: <span class="hljs-number">348</span>, <span class="hljs-string">'xmax'</span>: <span class="hljs-number">206</span>, <span class="hljs-string">'ymax'</span>: <span class="hljs-number">427</span>}},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.2110239565372467</span>,
	<span class="hljs-string">'label'</span>: <span class="hljs-string">'rocket'</span>,
	<span class="hljs-string">'box'</span>: {<span class="hljs-string">'xmin'</span>: <span class="hljs-number">350</span>, <span class="hljs-string">'ymin'</span>: -<span class="hljs-number">1</span>, <span class="hljs-string">'xmax'</span>: <span class="hljs-number">468</span>, <span class="hljs-string">'ymax'</span>: <span class="hljs-number">288</span>}},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.13790413737297058</span>,
	<span class="hljs-string">'label'</span>: <span class="hljs-string">'star-spangled banner'</span>,
	<span class="hljs-string">'box'</span>: {<span class="hljs-string">'xmin'</span>: <span class="hljs-number">1</span>, <span class="hljs-string">'ymin'</span>: <span class="hljs-number">1</span>, <span class="hljs-string">'xmax'</span>: <span class="hljs-number">105</span>, <span class="hljs-string">'ymax'</span>: <span class="hljs-number">509</span>}},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.11950037628412247</span>,
	<span class="hljs-string">'label'</span>: <span class="hljs-string">'nasa badge'</span>,
	<span class="hljs-string">'box'</span>: {<span class="hljs-string">'xmin'</span>: <span class="hljs-number">277</span>, <span class="hljs-string">'ymin'</span>: <span class="hljs-number">338</span>, <span class="hljs-string">'xmax'</span>: <span class="hljs-number">327</span>, <span class="hljs-string">'ymax'</span>: <span class="hljs-number">380</span>}},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.10649408400058746</span>,
	<span class="hljs-string">'label'</span>: <span class="hljs-string">'rocket'</span>,
	<span class="hljs-string">'box'</span>: {<span class="hljs-string">'xmin'</span>: <span class="hljs-number">358</span>, <span class="hljs-string">'ymin'</span>: <span class="hljs-number">64</span>, <span class="hljs-string">'xmax'</span>: <span class="hljs-number">424</span>, <span class="hljs-string">'ymax'</span>: <span class="hljs-number">280</span>}}]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-af5rkc">Let’s visualize the predictions:</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> PIL <span class="hljs-keyword">import</span> ImageDraw

	<span class="hljs-meta">>>> </span>draw = ImageDraw.Draw(image)

	<span class="hljs-meta">>>> </span><span class="hljs-keyword">for</span> prediction <span class="hljs-keyword">in</span> predictions:
	<span class="hljs-meta">... </span> box = prediction[<span class="hljs-string">"box"</span>]
	<span class="hljs-meta">... </span> label = prediction[<span class="hljs-string">"label"</span>]
	<span class="hljs-meta">... </span> score = prediction[<span class="hljs-string">"score"</span>]

	<span class="hljs-meta">... </span> xmin, ymin, xmax, ymax = box.values()
	<span class="hljs-meta">... </span> draw.rectangle((xmin, ymin, xmax, ymax), outline=<span class="hljs-string">"red"</span>, width=<span class="hljs-number">1</span>)
	<span class="hljs-meta">... </span> draw.text((xmin, ymin), <span class="hljs-string">f"<span class="hljs-subst">{label}</span>: <span class="hljs-subst">{<span class="hljs-built_in">round</span>(score,<span class="hljs-number">2</span>)}</span>"</span>, fill=<span class="hljs-string">"white"</span>)

	<span class="hljs-meta">>>> </span>image<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-1fwpqdn"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_2.png" alt="Visualized predictions on NASA image"></div> <h2 class="relative group"><a id="text-prompted-zero-shot-object-detection-by-hand" 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="#text-prompted-zero-shot-object-detection-by-hand"><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>Text-prompted zero-shot object detection by hand</span></h2> <p data-svelte-h="svelte-xqdy1u">Now that you’ve seen how to use the zero-shot object detection pipeline, let’s replicate the same
	result manually.</p> <p data-svelte-h="svelte-x1kygm">Start by loading the model and associated processor from a <a href="https://huggingface.co/models?other=owlvit" rel="nofollow">checkpoint on the Hugging Face Hub</a>.
	Here we’ll use the same checkpoint as before:</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> transformers <span class="hljs-keyword">import</span> AutoProcessor, AutoModelForZeroShotObjectDetection

	<span class="hljs-meta">>>> </span>model = AutoModelForZeroShotObjectDetection.from_pretrained(checkpoint)
	<span class="hljs-meta">>>> </span>processor = AutoProcessor.from_pretrained(checkpoint)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1g7c1zc">Let’s take a different image to switch things up.</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> requests

	<span class="hljs-meta">>>> </span>url = <span class="hljs-string">"https://unsplash.com/photos/oj0zeY2Ltk4/download?ixid=MnwxMjA3fDB8MXxzZWFyY2h8MTR8fHBpY25pY3xlbnwwfHx8fDE2Nzc0OTE1NDk&force=true&w=640"</span>
	<span class="hljs-meta">>>> </span>im = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw)
	<span class="hljs-meta">>>> </span>im<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-owux8y"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_3.png" alt="Beach photo"></div> <p data-svelte-h="svelte-16pebbq">Use the processor to prepare the inputs for the model. The processor combines an image processor that prepares the
	image for the model by resizing and normalizing it, and a <a href="/docs/transformers/pr_33913/en/model_doc/clip#transformers.CLIPTokenizer">CLIPTokenizer</a> that takes care of the text inputs.</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>text_queries = [<span class="hljs-string">"hat"</span>, <span class="hljs-string">"book"</span>, <span class="hljs-string">"sunglasses"</span>, <span class="hljs-string">"camera"</span>]
	<span class="hljs-meta">>>> </span>inputs = processor(text=text_queries, images=im, return_tensors=<span class="hljs-string">"pt"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1wlf71d">Pass the inputs through the model, post-process, and visualize the results. Since the image processor resized images before
	feeding them to the model, you need to use the <a href="/docs/transformers/pr_33913/en/model_doc/owlvit#transformers.OwlViTImageProcessor.post_process_object_detection">post_process_object_detection()</a> method to make sure the predicted bounding
	boxes have the correct coordinates relative to the original image:</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> torch

	<span class="hljs-meta">>>> </span><span class="hljs-keyword">with</span> torch.no_grad():
	<span class="hljs-meta">... </span> outputs = model(**inputs)
	<span class="hljs-meta">... </span> target_sizes = torch.tensor([im.size[::-<span class="hljs-number">1</span>]])
	<span class="hljs-meta">... </span> results = processor.post_process_object_detection(outputs, threshold=<span class="hljs-number">0.1</span>, target_sizes=target_sizes)[<span class="hljs-number">0</span>]

	<span class="hljs-meta">>>> </span>draw = ImageDraw.Draw(im)

	<span class="hljs-meta">>>> </span>scores = results[<span class="hljs-string">"scores"</span>].tolist()
	<span class="hljs-meta">>>> </span>labels = results[<span class="hljs-string">"labels"</span>].tolist()
	<span class="hljs-meta">>>> </span>boxes = results[<span class="hljs-string">"boxes"</span>].tolist()

	<span class="hljs-meta">>>> </span><span class="hljs-keyword">for</span> box, score, label <span class="hljs-keyword">in</span> <span class="hljs-built_in">zip</span>(boxes, scores, labels):
	<span class="hljs-meta">... </span> xmin, ymin, xmax, ymax = box
	<span class="hljs-meta">... </span> draw.rectangle((xmin, ymin, xmax, ymax), outline=<span class="hljs-string">"red"</span>, width=<span class="hljs-number">1</span>)
	<span class="hljs-meta">... </span> draw.text((xmin, ymin), <span class="hljs-string">f"<span class="hljs-subst">{text_queries[label]}</span>: <span class="hljs-subst">{<span class="hljs-built_in">round</span>(score,<span class="hljs-number">2</span>)}</span>"</span>, fill=<span class="hljs-string">"white"</span>)

	<span class="hljs-meta">>>> </span>im<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-1m863ar"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_4.png" alt="Beach photo with detected objects"></div> <h2 class="relative group"><a id="batch-processing" 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="#batch-processing"><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>Batch processing</span></h2> <p data-svelte-h="svelte-16j89af">You can pass multiple sets of images and text queries to search for different (or same) objects in several images.
	Let’s use both an astronaut image and the beach image together.
	For batch processing, you should pass text queries as a nested list to the processor and images as lists of PIL images,
	PyTorch tensors, or NumPy arrays.</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>images = [image, im]
	<span class="hljs-meta">>>> </span>text_queries = [
	<span class="hljs-meta">... </span> [<span class="hljs-string">"human face"</span>, <span class="hljs-string">"rocket"</span>, <span class="hljs-string">"nasa badge"</span>, <span class="hljs-string">"star-spangled banner"</span>],
	<span class="hljs-meta">... </span> [<span class="hljs-string">"hat"</span>, <span class="hljs-string">"book"</span>, <span class="hljs-string">"sunglasses"</span>, <span class="hljs-string">"camera"</span>],
	<span class="hljs-meta">... </span>]
	<span class="hljs-meta">>>> </span>inputs = processor(text=text_queries, images=images, return_tensors=<span class="hljs-string">"pt"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1si811t">Previously for post-processing you passed the single image’s size as a tensor, but you can also pass a tuple, or, in case
	of several images, a list of tuples. Let’s create predictions for the two examples, and visualize the second one (<code>image_idx = 1</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=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">with</span> torch.no_grad():
	<span class="hljs-meta">... </span> outputs = model(**inputs)
	<span class="hljs-meta">... </span> target_sizes = [x.size[::-<span class="hljs-number">1</span>] <span class="hljs-keyword">for</span> x <span class="hljs-keyword">in</span> images]
	<span class="hljs-meta">... </span> results = processor.post_process_object_detection(outputs, threshold=<span class="hljs-number">0.1</span>, target_sizes=target_sizes)

	<span class="hljs-meta">>>> </span>image_idx = <span class="hljs-number">1</span>
	<span class="hljs-meta">>>> </span>draw = ImageDraw.Draw(images[image_idx])

	<span class="hljs-meta">>>> </span>scores = results[image_idx][<span class="hljs-string">"scores"</span>].tolist()
	<span class="hljs-meta">>>> </span>labels = results[image_idx][<span class="hljs-string">"labels"</span>].tolist()
	<span class="hljs-meta">>>> </span>boxes = results[image_idx][<span class="hljs-string">"boxes"</span>].tolist()

	<span class="hljs-meta">>>> </span><span class="hljs-keyword">for</span> box, score, label <span class="hljs-keyword">in</span> <span class="hljs-built_in">zip</span>(boxes, scores, labels):
	<span class="hljs-meta">... </span> xmin, ymin, xmax, ymax = box
	<span class="hljs-meta">... </span> draw.rectangle((xmin, ymin, xmax, ymax), outline=<span class="hljs-string">"red"</span>, width=<span class="hljs-number">1</span>)
	<span class="hljs-meta">... </span> draw.text((xmin, ymin), <span class="hljs-string">f"<span class="hljs-subst">{text_queries[image_idx][label]}</span>: <span class="hljs-subst">{<span class="hljs-built_in">round</span>(score,<span class="hljs-number">2</span>)}</span>"</span>, fill=<span class="hljs-string">"white"</span>)

	<span class="hljs-meta">>>> </span>images[image_idx]<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-1m863ar"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_4.png" alt="Beach photo with detected objects"></div> <h2 class="relative group"><a id="image-guided-object-detection" 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-guided-object-detection"><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-guided object detection</span></h2> <p data-svelte-h="svelte-c78gkh">In addition to zero-shot object detection with text queries, OWL-ViT offers image-guided object detection. This means
	you can use an image query to find similar objects in the target image.
	Unlike text queries, only a single example image is allowed.</p> <p data-svelte-h="svelte-1kqxako">Let’s take an image with two cats on a couch as a target image, and an image of a single cat
	as a query:</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>url = <span class="hljs-string">"http://images.cocodataset.org/val2017/000000039769.jpg"</span>
	<span class="hljs-meta">>>> </span>image_target = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw)

	<span class="hljs-meta">>>> </span>query_url = <span class="hljs-string">"http://images.cocodataset.org/val2017/000000524280.jpg"</span>
	<span class="hljs-meta">>>> </span>query_image = Image.<span class="hljs-built_in">open</span>(requests.get(query_url, stream=<span class="hljs-literal">True</span>).raw)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1yw5ubp">Let’s take a quick look at 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">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt

	<span class="hljs-meta">>>> </span>fig, ax = plt.subplots(<span class="hljs-number">1</span>, <span class="hljs-number">2</span>)
	<span class="hljs-meta">>>> </span>ax[<span class="hljs-number">0</span>].imshow(image_target)
	<span class="hljs-meta">>>> </span>ax[<span class="hljs-number">1</span>].imshow(query_image)<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-y78yu"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_5.png" alt="Cats"></div> <p data-svelte-h="svelte-34zysh">In the preprocessing step, instead of text queries, you now need to use <code>query_images</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=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>inputs = processor(images=image_target, query_images=query_image, return_tensors=<span class="hljs-string">"pt"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1dtojvf">For predictions, instead of passing the inputs to the model, pass them to <a href="/docs/transformers/pr_33913/en/model_doc/owlvit#transformers.OwlViTForObjectDetection.image_guided_detection">image_guided_detection()</a>. Draw the predictions
	as before except now there are no labels.</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">with</span> torch.no_grad():
	<span class="hljs-meta">... </span> outputs = model.image_guided_detection(**inputs)
	<span class="hljs-meta">... </span> target_sizes = torch.tensor([image_target.size[::-<span class="hljs-number">1</span>]])
	<span class="hljs-meta">... </span> results = processor.post_process_image_guided_detection(outputs=outputs, target_sizes=target_sizes)[<span class="hljs-number">0</span>]

	<span class="hljs-meta">>>> </span>draw = ImageDraw.Draw(image_target)

	<span class="hljs-meta">>>> </span>scores = results[<span class="hljs-string">"scores"</span>].tolist()
	<span class="hljs-meta">>>> </span>boxes = results[<span class="hljs-string">"boxes"</span>].tolist()

	<span class="hljs-meta">>>> </span><span class="hljs-keyword">for</span> box, score, label <span class="hljs-keyword">in</span> <span class="hljs-built_in">zip</span>(boxes, scores, labels):
	<span class="hljs-meta">... </span> xmin, ymin, xmax, ymax = box
	<span class="hljs-meta">... </span> draw.rectangle((xmin, ymin, xmax, ymax), outline=<span class="hljs-string">"white"</span>, width=<span class="hljs-number">4</span>)

	<span class="hljs-meta">>>> </span>image_target<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-1f4dev0"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_6.png" alt="Cats with bounding boxes"></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/tasks/zero_shot_object_detection.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_z647wz = {
	assets: "/docs/transformers/pr_33913/en",
	base: "/docs/transformers/pr_33913/en",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/pr_33913/en/_app/immutable/entry/start.b67f883f.js"),
	import("/docs/transformers/pr_33913/en/_app/immutable/entry/app.e436b1f2.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 444],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 52 kB
Xet hash:: 35338f75796f37a45d695d6546dfd23c04cb6a3d6dd8162ad0bdb9e4cb14364a

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