Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"제로샷(zero-shot) 이미지 분류","local":"zeroshot-image-classification","sections":[{"title":"제로샷(zero-shot) 이미지 분류 파이프라인","local":"zeroshot-image-classification-pipeline","sections":[],"depth":2},{"title":"직접 제로샷(zero-shot) 이미지 분류하기","local":"zeroshot-image-classification-by-hand","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/transformers/main/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/start.9aa88961.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/scheduler.9bc65507.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/singletons.9eec45c3.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.3b203c72.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/paths.566078f7.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/app.84fb67c3.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.707bf1b6.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/0.1c99376b.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/85.9a37710e.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/CodeBlock.54a9f38d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/DocNotebookDropdown.41f65cb5.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/EditOnGithub.922df6ba.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"제로샷(zero-shot) 이미지 분류","local":"zeroshot-image-classification","sections":[{"title":"제로샷(zero-shot) 이미지 분류 파이프라인","local":"zeroshot-image-classification-pipeline","sections":[],"depth":2},{"title":"직접 제로샷(zero-shot) 이미지 분류하기","local":"zeroshot-image-classification-by-hand","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <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 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>제로샷(zero-shot) 이미지 분류</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-1ohgv1c">제로샷(zero-shot) 이미지 분류는 특정 카테고리의 예시가 포함된 데이터를 학습되지 않은 모델을 사용해 이미지 분류를 수행하는 작업입니다.</p> <p data-svelte-h="svelte-w8qz18">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 data-svelte-h="svelte-o87ayh">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 data-svelte-h="svelte-ryenqj">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 data-svelte-h="svelte-pdyjx9">이번 가이드에서 배울 내용은 다음과 같습니다:</p> <ul data-svelte-h="svelte-1nsu74x"><li>제로샷 이미지 분류 파이프라인 만들기</li> <li>직접 제로샷 이미지 분류 모델 추론 실행하기</li></ul> <p data-svelte-h="svelte-1k0z9pm">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 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="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 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>제로샷(zero-shot) 이미지 분류 파이프라인</span></h2> <p data-svelte-h="svelte-jljpqr"><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&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 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-tza26b">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 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-1vlt2d5">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 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 = classifier(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="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 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>직접 제로샷(zero-shot) 이미지 분류하기</span></h2> <p data-svelte-h="svelte-chmorg">이제 제로샷 이미지 분류 파이프라인 사용 방법을 살펴보았으니, 실행하는 방법을 살펴보겠습니다.</p> <p data-svelte-h="svelte-1to009q"><a href="https://huggingface.co/models?pipeline_tag=zero-shot-image-classification&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 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-qe32ys">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 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-sjszr1">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 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-11wh2d9">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 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/ko/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_1hrx8 = { | |
| assets: "/docs/transformers/main/ko", | |
| base: "/docs/transformers/main/ko", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/main/ko/_app/immutable/entry/start.9aa88961.js"), | |
| import("/docs/transformers/main/ko/_app/immutable/entry/app.84fb67c3.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 85], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 27.8 kB
- Xet hash:
- 7b36dfebedcb37893497a385252ef02c2ab09aaaf92f37bf404df81860009216
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.