Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / transformers /pr_33913 /ko /tasks /image_feature_extraction.html
rtrm's picture
rtrm
download
raw
29.1 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;이미지 특징 추출&quot;,&quot;local&quot;:&quot;image-feature-extraction&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;image-feature-extraction 파이프라인을 이용한 이미지 유사성&quot;,&quot;local&quot;:&quot;image-similarity-using-image-feature-extraction-pipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;AutoModel 을 사용하여 특징과 유사성 얻기&quot;,&quot;local&quot;:&quot;getting-features-and-similarities-using-automodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
 <link href="/docs/transformers/pr_33913/ko/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/entry/start.2d0ec41c.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/scheduler.bdbef820.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/singletons.665fa29a.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/index.8a885b74.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/paths.47fdf6cc.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/entry/app.e5c46936.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/index.33f81d56.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/nodes/0.7e28132d.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/nodes/134.ba0e0baa.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/CodeBlock.362b34a4.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/DocNotebookDropdown.d5db5928.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/globals.7f7f1b26.js">
 <link rel="modulepreload" href="/docs/transformers/pr_33913/ko/_app/immutable/chunks/EditOnGithub.a9246e21.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;이미지 특징 추출&quot;,&quot;local&quot;:&quot;image-feature-extraction&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;image-feature-extraction 파이프라인을 이용한 이미지 유사성&quot;,&quot;local&quot;:&quot;image-similarity-using-image-feature-extraction-pipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;AutoModel 을 사용하여 특징과 유사성 얻기&quot;,&quot;local&quot;:&quot;getting-features-and-similarities-using-automodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="image-feature-extraction" 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-feature-extraction"><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>이미지 특징 추출</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-1vt6q7k">이미지 특징 추출은 주어진 이미지에서 의미론적으로 의미 있는 특징을 추출하는 작업입니다. 이는 이미지 유사성 및 이미지 검색 등 다양한 사용 사례가 있습니다.
게다가 대부분의 컴퓨터 비전 모델은 이미지 특징 추출에 사용할 수 있으며, 여기서 작업 특화 헤드(이미지 분류, 물체 감지 등)를 제거하고 특징을 얻을 수 있습니다. 이러한 특징은 가장자리 감지, 모서리 감지 등 고차원 수준에서 매우 유용합니다.
또한 모델의 깊이에 따라 실제 세계에 대한 정보(예: 고양이가 어떻게 생겼는지)를 포함할 수도 있습니다. 따라서 이러한 출력은 특정 데이터 세트에 대한 새로운 분류기를 훈련하는 데 사용할 수 있습니다.</p> <p data-svelte-h="svelte-1726yuy">이 가이드에서는:</p> <ul data-svelte-h="svelte-1nqtv9s"><li><code>image-feature-extraction</code> 파이프라인을 활용하여 간단한 이미지 유사성 시스템을 구축하는 방법을 배웁니다.</li> <li>기본 모델 추론으로 동일한 작업을 수행합니다.</li></ul> <h2 class="relative group"><a id="image-similarity-using-image-feature-extraction-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="#image-similarity-using-image-feature-extraction-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>image-feature-extraction 파이프라인을 이용한 이미지 유사성</span></h2> <p data-svelte-h="svelte-1id1irs">물고기 그물 위에 앉아 있는 두 장의 고양이 사진이 있습니다. 이 중 하나는 생성된 이미지입니다.</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-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
<span class="hljs-keyword">import</span> requests
img_urls = [<span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png&quot;</span>, <span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.jpeg&quot;</span>]
image_real = Image.<span class="hljs-built_in">open</span>(requests.get(img_urls[<span class="hljs-number">0</span>], stream=<span class="hljs-literal">True</span>).raw).convert(<span class="hljs-string">&quot;RGB&quot;</span>)
image_gen = Image.<span class="hljs-built_in">open</span>(requests.get(img_urls[<span class="hljs-number">1</span>], stream=<span class="hljs-literal">True</span>).raw).convert(<span class="hljs-string">&quot;RGB&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ydo688">파이프라인을 실행해 봅시다. 먼저 파이프라인을 초기화하세요. 모델을 지정하지 않으면, 파이프라인은 자동으로 <a href="google/vit-base-patch16-224">google/vit-base-patch16-224</a> 모델로 초기화됩니다. 유사도를 계산하려면 <code>pool</code>을 True로 설정하세요.</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-keyword">import</span> torch
<span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline
DEVICE = torch.device(<span class="hljs-string">&#x27;cuda&#x27;</span> <span class="hljs-keyword">if</span> torch.cuda.is_available() <span class="hljs-keyword">else</span> <span class="hljs-string">&#x27;cpu&#x27;</span>)
pipe = pipeline(task=<span class="hljs-string">&quot;image-feature-extraction&quot;</span>, model_name=<span class="hljs-string">&quot;google/vit-base-patch16-384&quot;</span>, device=DEVICE, pool=<span class="hljs-literal">True</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-123f7i0"><code>pipe</code>를 사용하여 추론하려면 두 이미지를 모두 전달하세요.</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 -->outputs = pipe([image_real, image_gen])<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-11yg842">출력에는 두 이미지의 풀링된(pooled) 임베딩이 포함되어 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-comment"># 단일 출력의 길이 구하기</span>
<span class="hljs-built_in">print</span>(<span class="hljs-built_in">len</span>(outputs[<span class="hljs-number">0</span>][<span class="hljs-number">0</span>]))
<span class="hljs-comment"># 출력 결과 표시하기</span>
<span class="hljs-built_in">print</span>(outputs)
<span class="hljs-comment"># 768</span>
<span class="hljs-comment"># [[[-0.03909236937761307, 0.43381670117378235, -0.06913255900144577,</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-g3oteq">유사도 점수를 얻으려면, 이들을 유사도 함수에 전달해야 합니다.</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-keyword">from</span> torch.nn.functional <span class="hljs-keyword">import</span> cosine_similarity
similarity_score = cosine_similarity(torch.Tensor(outputs[<span class="hljs-number">0</span>]),
 torch.Tensor(outputs[<span class="hljs-number">1</span>]), dim=<span class="hljs-number">1</span>)
<span class="hljs-built_in">print</span>(similarity_score)
<span class="hljs-comment"># tensor([0.6043])</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1t773by">풀링 이전의 마지막 은닉 상태를 얻고 싶다면, <code>pool</code> 매개변수에 아무 값도 전달하지 마세요. 또한, 기본값은 <code>False</code>로 설정되어 있습니다. 이 은닉 상태는 모델의 특징을 기반으로 새로운 분류기나 모델을 훈련시키는 데 유용합니다.</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 -->pipe = pipeline(task=<span class="hljs-string">&quot;image-feature-extraction&quot;</span>, model_name=<span class="hljs-string">&quot;google/vit-base-patch16-224&quot;</span>, device=DEVICE)
output = pipe(image_real)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1gqm4lc">아직 출력이 풀링되지 않았기 때문에, 첫 번째 차원은 배치 크기이고 마지막 두 차원은 임베딩 형태인 마지막 은닉 상태를 얻을 수 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-keyword">import</span> numpy <span class="hljs-keyword">as</span> np
<span class="hljs-built_in">print</span>(np.array(outputs).shape)
<span class="hljs-comment"># (1, 197, 768)</span><!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="getting-features-and-similarities-using-automodel" 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="#getting-features-and-similarities-using-automodel"><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>AutoModel 을 사용하여 특징과 유사성 얻기</span></h2> <p data-svelte-h="svelte-nu0ph0">transformers의 <code>AutoModel</code> 클래스를 사용하여 특징을 얻을 수도 있습니다. <code>AutoModel</code>은 작업 특화 헤드 없이 모든 transformers 모델을 로드할 수 있으며, 이를 통해 특징을 추출할 수 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-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoImageProcessor, AutoModel
processor = AutoImageProcessor.from_pretrained(<span class="hljs-string">&quot;google/vit-base-patch16-224&quot;</span>)
model = AutoModel.from_pretrained(<span class="hljs-string">&quot;google/vit-base-patch16-224&quot;</span>).to(DEVICE)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1fnffdx">추론을 위한 간단한 함수를 작성해 보겠습니다. 먼저 입력값을 <code>processor</code>에 전달한 다음, 그 출력값을 <code>model</code>에 전달할 것입니다.</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-keyword">def</span> <span class="hljs-title function_">infer</span>(<span class="hljs-params">image</span>):
 inputs = processor(image, return_tensors=<span class="hljs-string">&quot;pt&quot;</span>).to(DEVICE)
 outputs = model(**inputs)
 <span class="hljs-keyword">return</span> outputs.pooler_output<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1630srz">이 함수에 이미지를 직접 전달하여 임베딩을 얻을 수 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 -->embed_real = infer(image_real)
embed_gen = infer(image_gen)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-s0jrer">그리고 이 임베딩을 사용하여 다시 유사도를 계산할 수 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-keyword">from</span> torch.nn.functional <span class="hljs-keyword">import</span> cosine_similarity
similarity_score = cosine_similarity(embed_real, embed_gen, dim=<span class="hljs-number">1</span>)
<span class="hljs-built_in">print</span>(similarity_score)
<span class="hljs-comment"># tensor([0.6061], device=&#x27;cuda:0&#x27;, grad_fn=&lt;SumBackward1&gt;)</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/image_feature_extraction.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_1wfirp1 = {
 assets: "/docs/transformers/pr_33913/ko",
 base: "/docs/transformers/pr_33913/ko",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/transformers/pr_33913/ko/_app/immutable/entry/start.2d0ec41c.js"),
 import("/docs/transformers/pr_33913/ko/_app/immutable/entry/app.e5c46936.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 134],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
29.1 kB
·
Xet hash:
304ad7e3f60b1f4521bc0c6924d0069fb191249b458a7974f33f615685f5167b

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