Buckets:

hf-doc-build
/

doc

Files
xet
hf-doc-build/doc / transformers /main /ko /tasks /zero_shot_image_classification.html
HuggingFaceDocBuilder
35 minutes ago
download
raw
29.7 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;제로샷(zero-shot) 이미지 분류&quot;,&quot;local&quot;:&quot;zeroshot-image-classification&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;제로샷(zero-shot) 이미지 분류 파이프라인&quot;,&quot;local&quot;:&quot;zeroshot-image-classification-pipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;직접 제로샷(zero-shot) 이미지 분류하기&quot;,&quot;local&quot;:&quot;zeroshot-image-classification-by-hand&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
		<link href="/docs/transformers/main/ko/_app/immutable/entry/start.yqDdfIah.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/L0MID6Lt.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/BkyfusOu.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/entry/app.Caw9CuWs.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/CDRgxHoV.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/1EV5EJPW.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/CKPTQsoU.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/nodes/0.CiqegfoO.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/BoVSaMb7.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/nodes/181.jsvBaCjz.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/cFKPlByr.js" rel="modulepreload">
		<link href="/docs/transformers/main/ko/_app/immutable/chunks/juS24bn6.js" rel="modulepreload">
		<!--n60jny--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;제로샷(zero-shot) 이미지 분류&quot;,&quot;local&quot;:&quot;zeroshot-image-classification&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;제로샷(zero-shot) 이미지 분류 파이프라인&quot;,&quot;local&quot;:&quot;zeroshot-image-classification-pipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;직접 제로샷(zero-shot) 이미지 분류하기&quot;,&quot;local&quot;:&quot;zeroshot-image-classification-by-hand&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
		<link href="/docs/transformers/main/ko/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <div class="flex space-x-1 " style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><!----> <!--[1--><div class="relative colab-dropdown "><button class="   " type="button"><!--[0--><!--[-1--><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"/><!--]--><!----><!--]--></button>  <!--[-1--><!--]--></div><!--]--> <!--[1--><div class="relative colab-dropdown "><button class="   " type="button"><!--[0--><!--[-1--><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"/><!--]--><!----><!--]--></button>  <!--[-1--><!--]--></div><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="zeroshot-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="#zeroshot-image-classification"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>제로샷(zero-shot) 이미지 분류</span></h1><!--]--><!----> <p>제로샷(zero-shot) 이미지 분류는 특정 카테고리의 예시가 포함된 데이터를 학습되지 않은 모델을 사용해 이미지 분류를 수행하는 작업입니다.</p> <p>일반적으로 이미지 분류를 위해서는 레이블이 달린 특정 이미지 데이터로 모델 학습이 필요하며, 이 모델은 특정 이미지의 특징을 레이블에 “매핑”하는 방법을 학습합니다.
새로운 레이블이 있는 분류 작업에 이러한 모델을 사용해야 하는 경우에는, 모델을 “재보정”하기 위해 미세 조정이 필요합니다.</p> <p>이와 대조적으로, 제로샷 또는 개방형 어휘(open vocabulary) 이미지 분류 모델은 일반적으로 대규모 이미지 데이터와 해당 설명에 대해 학습된 멀티모달(multimodal) 모델입니다.
이러한 모델은 제로샷 이미지 분류를 포함한 많은 다운스트림 작업에 사용할 수 있는 정렬된(aligned) 비전 언어 표현을 학습합니다.</p> <p>이는 이미지 분류에 대한 보다 유연한 접근 방식으로, 추가 학습 데이터 없이 새로운 레이블이나 학습하지 못한 카테고리에 대해 모델을 일반화할 수 있습니다.
또한, 사용자가 대상 개체에 대한 자유 형식의 텍스트 설명으로 이미지를 검색할 수 있습니다.</p> <p>이번 가이드에서 배울 내용은 다음과 같습니다:</p> <ul><li>제로샷 이미지 분류 파이프라인 만들기</li> <li>직접 제로샷 이미지 분류 모델 추론 실행하기</li></ul> <p>시작하기 전에 필요한 라이브러리가 모두 설치되어 있는지 확인하세요:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-bash "><!---->pip install -q transformers<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="zeroshot-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="#zeroshot-image-classification-pipeline"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>제로샷(zero-shot) 이미지 분류 파이프라인</span></h2><!--]--><!----> <p><code>pipeline()</code>을 활용하면 가장 간단하게 제로샷 이미지 분류를 지원하는 모델로 추론해볼 수 있습니다. <a href="https://huggingface.co/models?pipeline_tag=zero-shot-image-classification&amp;sort=downloads" rel="nofollow">Hugging Face Hub에 업로드된 체크포인트</a>에서 파이프라인을 인스턴스화합니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>checkpoint = <span class="hljs-string">&quot;openai/clip-vit-large-patch14&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>detector = pipeline(model=checkpoint, task=<span class="hljs-string">&quot;zero-shot-image-classification&quot;</span>)<!----></pre></div><!----> <p>다음으로, 분류하고 싶은 이미지를 선택하세요.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> requests

<span class="hljs-meta">&gt;&gt;&gt; </span>url = <span class="hljs-string">&quot;https://unsplash.com/photos/g8oS8-82DxI/download?ixid=MnwxMjA3fDB8MXx0b3BpY3x8SnBnNktpZGwtSGt8fHx8fDJ8fDE2NzgxMDYwODc&amp;force=true&amp;w=640&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </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">&gt;&gt;&gt; </span>image<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/owl.jpg" alt="Photo of an owl"/></div> <p>이미지와 해당 이미지의 후보 레이블인 <code>candidate_labels</code>를 파이프라인으로 전달합니다.
여기서는 이미지를 직접 전달하지만, 컴퓨터에 저장된 이미지의 경로나 url로 전달할 수도 있습니다. <code>candidate_labels</code>는 이 예시처럼 간단한 단어일 수도 있고 좀 더 설명적인 단어일 수도 있습니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span>predictions = classifier(image, candidate_labels=[<span class="hljs-string">&quot;fox&quot;</span>, <span class="hljs-string">&quot;bear&quot;</span>, <span class="hljs-string">&quot;seagull&quot;</span>, <span class="hljs-string">&quot;owl&quot;</span>])
<span class="hljs-meta">&gt;&gt;&gt; </span>predictions
[{<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.9996670484542847</span>, <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;owl&#x27;</span>},
 {<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.000199399160919711</span>, <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;seagull&#x27;</span>},
 {<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">7.392891711788252e-05</span>, <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;fox&#x27;</span>},
 {<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">5.96074532950297e-05</span>, <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;bear&#x27;</span>}]<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="zeroshot-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="#zeroshot-image-classification-by-hand"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span>직접 제로샷(zero-shot) 이미지 분류하기</span></h2><!--]--><!----> <p>이제 제로샷 이미지 분류 파이프라인 사용 방법을 살펴보았으니, 실행하는 방법을 살펴보겠습니다.</p> <p><a href="https://huggingface.co/models?pipeline_tag=zero-shot-image-classification&amp;sort=downloads" rel="nofollow">Hugging Face Hub에 업로드된 체크포인트</a>에서 모델과 프로세서를 가져오는 것으로 시작합니다.
여기서는 이전과 동일한 체크포인트를 사용하겠습니다:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor, AutoModelForZeroShotImageClassification

<span class="hljs-meta">&gt;&gt;&gt; </span>model = AutoModelForZeroShotImageClassification.from_pretrained(checkpoint)
<span class="hljs-meta">&gt;&gt;&gt; </span>processor = AutoProcessor.from_pretrained(checkpoint)<!----></pre></div><!----> <p>다른 이미지를 사용해 보겠습니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> requests

<span class="hljs-meta">&gt;&gt;&gt; </span>url = <span class="hljs-string">&quot;https://unsplash.com/photos/xBRQfR2bqNI/download?ixid=MnwxMjA3fDB8MXxhbGx8fHx8fHx8fHwxNjc4Mzg4ODEx&amp;force=true&amp;w=640&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </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">&gt;&gt;&gt; </span>image<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg" alt="Photo of a car"/></div> <p>프로세서를 사용해 모델의 입력을 준비합니다.
프로세서는 모델의 입력으로 사용하기 위해 이미지 크기를 변환하고 정규화하는 이미지 프로세서와 텍스트 입력을 처리하는 토크나이저로 구성됩니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span>candidate_labels = [<span class="hljs-string">&quot;tree&quot;</span>, <span class="hljs-string">&quot;car&quot;</span>, <span class="hljs-string">&quot;bike&quot;</span>, <span class="hljs-string">&quot;cat&quot;</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>inputs = processor(images=image, text=candidate_labels, return_tensors=<span class="hljs-string">&quot;pt&quot;</span>, padding=<span class="hljs-literal">True</span>)<!----></pre></div><!----> <p>모델에 입력을 전달하고, 결과를 후처리합니다:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> Copied</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch

<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">with</span> torch.no_grad():
<span class="hljs-meta">... </span>    outputs = model(**inputs)

<span class="hljs-meta">&gt;&gt;&gt; </span>logits = outputs.logits_per_image[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>probs = logits.softmax(dim=-<span class="hljs-number">1</span>).numpy()
<span class="hljs-meta">&gt;&gt;&gt; </span>scores = probs.tolist()

<span class="hljs-meta">&gt;&gt;&gt; </span>result = [
<span class="hljs-meta">... </span>    {<span class="hljs-string">&quot;score&quot;</span>: score, <span class="hljs-string">&quot;label&quot;</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">&gt;&gt;&gt; </span>result
[{<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.998572</span>, <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;car&#x27;</span>},
 {<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.0010570387</span>, <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;bike&#x27;</span>},
 {<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">0.0003393686</span>, <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;tree&#x27;</span>},
 {<span class="hljs-string">&#x27;score&#x27;</span>: <span class="hljs-number">3.1572064e-05</span>, <span class="hljs-string">&#x27;label&#x27;</span>: <span class="hljs-string">&#x27;cat&#x27;</span>}]<!----></pre></div><!----> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/ko/tasks/zero_shot_image_classification.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
			
			<script>
				{
					__sveltekit_3y87jt = {
						base: "/docs/transformers/main/ko",
						assets: "/docs/transformers/main/ko"
					};
					const element = document.currentScript.parentElement;
					Promise.all([
						import("/docs/transformers/main/ko/_app/immutable/entry/start.yqDdfIah.js"),
						import("/docs/transformers/main/ko/_app/immutable/entry/app.Caw9CuWs.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 181],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>
		
Xet Storage Details

Size:: 29.7 kB
Xet hash:: 35f36478098c0418ccf915e0833dfaba9e444d6a0438f9fd6a127c00d4a4cb55
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.