Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers /main /ja /tasks /zero_shot_image_classification.html

rtrm

26 days ago

download

raw

28 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Zero-shot image classification","local":"zero-shot-image-classification","sections":[{"title":"Zero-shot image classification pipeline","local":"zero-shot-image-classification-pipeline","sections":[],"depth":2},{"title":"Zero-shot image classification by hand","local":"zero-shot-image-classification-by-hand","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/main/ja/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/entry/start.1486e459.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/scheduler.9bc65507.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/singletons.eee55cbf.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/index.3b203c72.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/paths.59da1547.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/entry/app.d9ae818f.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/index.707bf1b6.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/nodes/0.c06aa070.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/nodes/158.642b4434.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/CodeBlock.54a9f38d.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/DocNotebookDropdown.41f65cb5.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/globals.7f7f1b26.js">
	<link rel="modulepreload" href="/docs/transformers/main/ja/_app/immutable/chunks/EditOnGithub.922df6ba.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Zero-shot image classification","local":"zero-shot-image-classification","sections":[{"title":"Zero-shot image classification pipeline","local":"zero-shot-image-classification-pipeline","sections":[],"depth":2},{"title":"Zero-shot image classification by hand","local":"zero-shot-image-classification-by-hand","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="zero-shot-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="#zero-shot-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>Zero-shot image classification</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-753hod">ゼロショット画像分類は、次のモデルを使用して画像をさまざまなカテゴリに分類するタスクです。
	これらの特定のカテゴリのラベル付きの例を含むデータに対して明示的にトレーニングされていない。</p> <p data-svelte-h="svelte-1pvht9m">従来、画像分類には、ラベル付き画像の特定のセットでモデルをトレーニングする必要があり、このモデルは次のことを学習します。
	特定の画像の特徴をラベルに「マッピング」します。分類タスクにそのようなモデルを使用する必要がある場合、
	新しいラベルのセットでは、モデルを “再調整” するために微調整が必要です。</p> <p data-svelte-h="svelte-1pwpmsj">対照的に、ゼロショットまたはオープン語彙画像分類モデルは、通常、大規模なシステムでトレーニングされたマルチモーダルモデルです。
	画像と関連する説明のデータセット。これらのモデルは、ゼロショット画像分類を含む多くの下流タスクに使用できる、調整された視覚言語表現を学習します。</p> <p data-svelte-h="svelte-1izek7c">これは、画像分類に対するより柔軟なアプローチであり、モデルを新しいまだ見たことのないカテゴリに一般化できるようになります。
	追加のトレーニングデータを必要とせず、ユーザーはターゲットオブジェクトの自由形式のテキスト説明を含む画像をクエリできるようになります。</p> <p data-svelte-h="svelte-tlz6vm">このガイドでは、次の方法を学びます。</p> <ul data-svelte-h="svelte-x7hnkc"><li>ゼロショット画像分類パイプラインを作成する</li> <li>手動でゼロショット画像分類推論を実行します</li></ul> <p data-svelte-h="svelte-1lya3k8">始める前に、必要なライブラリがすべてインストールされていることを確認してください。</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-image-classification-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-image-classification-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 image classification pipeline</span></h2> <p data-svelte-h="svelte-1yjcekc">ゼロショット画像分類をサポートするモデルで推論を試す最も簡単な方法は、対応する <code>パイプライン</code> を使用することです。
	<a href="https://huggingface.co/models?pipeline_tag=zero-shot-image-classification&sort=downloads" rel="nofollow">Hugging Face Hub のチェックポイント</a> からパイプラインをインスタンス化します。</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">"openai/clip-vit-large-patch14"</span>
	<span class="hljs-meta">>>> </span>detector = pipeline(model=checkpoint, task=<span class="hljs-string">"zero-shot-image-classification"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-stzvzh">次に、分類したい画像を選択します。</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> Image
	<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/g8oS8-82DxI/download?ixid=MnwxMjA3fDB8MXx0b3BpY3x8SnBnNktpZGwtSGt8fHx8fDJ8fDE2NzgxMDYwODc&force=true&w=640"</span>
	<span class="hljs-meta">>>> </span>image = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw)

	<span class="hljs-meta">>>> </span>image<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-10yxso1"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/owl.jpg" alt="Photo of an owl"></div> <p data-svelte-h="svelte-6ob2q8">画像と候補オブジェクトのラベルをパイプラインに渡します。ここでは画像を直接渡します。他の適切なオプション
	画像へのローカルパスまたは画像 URL を含めます。
	候補ラベルは、この例のように単純な単語にすることも、より説明的な単語にすることもできます。</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(image, candidate_labels=[<span class="hljs-string">"fox"</span>, <span class="hljs-string">"bear"</span>, <span class="hljs-string">"seagull"</span>, <span class="hljs-string">"owl"</span>])
	<span class="hljs-meta">>>> </span>predictions
	[{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.9996670484542847</span>, <span class="hljs-string">'label'</span>: <span class="hljs-string">'owl'</span>},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.000199399160919711</span>, <span class="hljs-string">'label'</span>: <span class="hljs-string">'seagull'</span>},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">7.392891711788252e-05</span>, <span class="hljs-string">'label'</span>: <span class="hljs-string">'fox'</span>},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">5.96074532950297e-05</span>, <span class="hljs-string">'label'</span>: <span class="hljs-string">'bear'</span>}]<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="zero-shot-image-classification-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="#zero-shot-image-classification-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>Zero-shot image classification by hand</span></h2> <p data-svelte-h="svelte-1lbavmm">ゼロショット画像分類パイプラインの使用方法を理解したところで、ゼロショットを実行する方法を見てみましょう。
	画像を手動で分類します。</p> <p data-svelte-h="svelte-s5sfsz">まず、<a href="https://huggingface.co/models?pipeline_tag=zero-shot-image-classification&sort=downloads" rel="nofollow">Hugging Face Hub のチェックポイント</a> からモデルと関連プロセッサをロードします。
	ここでは、前と同じチェックポイントを使用します。</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, AutoModelForZeroShotImageClassification

	<span class="hljs-meta">>>> </span>model = AutoModelForZeroShotImageClassification.from_pretrained(checkpoint)
	<span class="hljs-meta">>>> </span>processor = AutoProcessor.from_pretrained(checkpoint)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-vbbgku">気分を変えて、別の画像を撮ってみましょう。</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> Image
	<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/xBRQfR2bqNI/download?ixid=MnwxMjA3fDB8MXxhbGx8fHx8fHx8fHwxNjc4Mzg4ODEx&force=true&w=640"</span>
	<span class="hljs-meta">>>> </span>image = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw)

	<span class="hljs-meta">>>> </span>image<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-1kfxibh"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg" alt="Photo of a car"></div> <p data-svelte-h="svelte-h1u4we">プロセッサを使用してモデルの入力を準備します。プロセッサーは、
	サイズ変更と正規化によるモデルの画像、およびテキスト入力を処理するトークナイザー。</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>candidate_labels = [<span class="hljs-string">"tree"</span>, <span class="hljs-string">"car"</span>, <span class="hljs-string">"bike"</span>, <span class="hljs-string">"cat"</span>]
	<span class="hljs-meta">>>> </span>inputs = processor(images=image, text=candidate_labels, return_tensors=<span class="hljs-string">"pt"</span>, padding=<span class="hljs-literal">True</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1mekvsu">入力をモデルに渡し、結果を後処理します。</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>logits = outputs.logits_per_image[<span class="hljs-number">0</span>]
	<span class="hljs-meta">>>> </span>probs = logits.softmax(dim=-<span class="hljs-number">1</span>).numpy()
	<span class="hljs-meta">>>> </span>scores = probs.tolist()

	<span class="hljs-meta">>>> </span>result = [
	<span class="hljs-meta">... </span> {<span class="hljs-string">"score"</span>: score, <span class="hljs-string">"label"</span>: candidate_label}
	<span class="hljs-meta">... </span> <span class="hljs-keyword">for</span> score, candidate_label <span class="hljs-keyword">in</span> <span class="hljs-built_in">sorted</span>(<span class="hljs-built_in">zip</span>(probs, candidate_labels), key=<span class="hljs-keyword">lambda</span> x: -x[<span class="hljs-number">0</span>])
	<span class="hljs-meta">... </span>]

	<span class="hljs-meta">>>> </span>result
	[{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.998572</span>, <span class="hljs-string">'label'</span>: <span class="hljs-string">'car'</span>},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.0010570387</span>, <span class="hljs-string">'label'</span>: <span class="hljs-string">'bike'</span>},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">0.0003393686</span>, <span class="hljs-string">'label'</span>: <span class="hljs-string">'tree'</span>},
	{<span class="hljs-string">'score'</span>: <span class="hljs-number">3.1572064e-05</span>, <span class="hljs-string">'label'</span>: <span class="hljs-string">'cat'</span>}]<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/ja/tasks/zero_shot_image_classification.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_jement = {
	assets: "/docs/transformers/main/ja",
	base: "/docs/transformers/main/ja",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/main/ja/_app/immutable/entry/start.1486e459.js"),
	import("/docs/transformers/main/ja/_app/immutable/entry/app.d9ae818f.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 158],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 28 kB
Xet hash:: 2e48bd3d33e14d06d7abd58a051c48849907a8713a5583344bf79b596a9dac8d

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