Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"키포인트 탐지","local":"keypoint-detection","sections":[],"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.5711aec5.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/scheduler.53228c21.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/singletons.e72f2fa0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.e93d0901.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/paths.6497411f.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/entry/app.fcc7a1b0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/preload-helper.cb103237.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/index.3db2ce32.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/nodes/0.af6df88e.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/162.390c02ed.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/CopyLLMTxtMenu.1327b590.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.49b88d99.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/CodeBlock.ada04ea6.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/ko/_app/immutable/chunks/DocNotebookDropdown.1834da50.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"키포인트 탐지","local":"keypoint-detection","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <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> </div> <div class="flex space-x-1 " style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"> <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> <h1 class="relative group"><a id="keypoint-detection" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#keypoint-detection"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>키포인트 탐지</span></h1> <p data-svelte-h="svelte-1h1cyjh">키포인트 감지(Keypoint detection)은 이미지 내의 특정 포인트를 식별하고 위치를 탐지합니다. 이러한 키포인트는 랜드마크라고도 불리며 얼굴 특징이나 물체의 일부와 같은 의미 있는 특징을 나타냅니다. | |
| 키포인트 감지 모델들은 이미지를 입력으로 받아 아래와 같은 출력을 반환합니다.</p> <ul data-svelte-h="svelte-163w3gg"><li><strong>키포인트들과 점수</strong>: 관심 포인트들과 해당 포인트에 대한 신뢰도 점수</li> <li><strong>디스크립터(Descriptors)</strong>: 각 키포인트를 둘러싼 이미지 영역의 표현으로 텍스처, 그라데이션, 방향 및 기타 속성을 캡처합니다.</li></ul> <p data-svelte-h="svelte-pstt3t">이번 가이드에서는 이미지에서 키포인트를 추출하는 방법을 다루어 보겠습니다.</p> <p data-svelte-h="svelte-hpzjsj">이번 튜토리얼에서는 키포인트 감지의 기본이 되는 모델인 <a href="./model_doc/superpoint">SuperPoint</a>를 사용해보겠습니다.</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="language-python "><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoImageProcessor, SuperPointForKeypointDetection | |
| processor = AutoImageProcessor.from_pretrained(<span class="hljs-string">"magic-leap-community/superpoint"</span>) | |
| model = SuperPointForKeypointDetection.from_pretrained(<span class="hljs-string">"magic-leap-community/superpoint"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1cpccm5">아래의 이미지로 모델을 테스트 해보겠습니다.</p> <div style="display: flex; align-items: center;" data-svelte-h="svelte-jde2l9"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg" alt="Bee" style="height: 200px; object-fit: contain; margin-right: 10px;"> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png" alt="Cats" style="height: 200px; object-fit: contain;"></div> <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="language-python "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image | |
| <span class="hljs-keyword">import</span> requests | |
| <span class="hljs-keyword">import</span> cv2 | |
| url_image_1 = <span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"</span> | |
| image_1 = Image.<span class="hljs-built_in">open</span>(requests.get(url_image_1, stream=<span class="hljs-literal">True</span>).raw) | |
| url_image_2 = <span class="hljs-string">"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png"</span> | |
| image_2 = Image.<span class="hljs-built_in">open</span>(requests.get(url_image_2, stream=<span class="hljs-literal">True</span>).raw) | |
| images = [image_1, image_2]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1cllq6p">이제 입력을 처리하고 추론을 할 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="language-python "><!-- HTML_TAG_START -->inputs = processor(images,return_tensors=<span class="hljs-string">"pt"</span>).to(model.device, model.dtype) | |
| outputs = model(**inputs)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1nnd11r">모델 출력에는 배치 내의 각 항목에 대한 상대적인 키포인트, 디스크립터, 마스크와 점수가 있습니다. 마스크는 이미지에서 키포인트가 있는 영역을 강조하는 역할을 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="language-python "><!-- HTML_TAG_START -->SuperPointKeypointDescriptionOutput(loss=<span class="hljs-literal">None</span>, keypoints=tensor([[[<span class="hljs-number">0.0437</span>, <span class="hljs-number">0.0167</span>], | |
| [<span class="hljs-number">0.0688</span>, <span class="hljs-number">0.0167</span>], | |
| [<span class="hljs-number">0.0172</span>, <span class="hljs-number">0.0188</span>], | |
| ..., | |
| [<span class="hljs-number">0.5984</span>, <span class="hljs-number">0.9812</span>], | |
| [<span class="hljs-number">0.6953</span>, <span class="hljs-number">0.9812</span>]]]), | |
| scores=tensor([[<span class="hljs-number">0.0056</span>, <span class="hljs-number">0.0053</span>, <span class="hljs-number">0.0079</span>, ..., <span class="hljs-number">0.0125</span>, <span class="hljs-number">0.0539</span>, <span class="hljs-number">0.0377</span>], | |
| [<span class="hljs-number">0.0206</span>, <span class="hljs-number">0.0058</span>, <span class="hljs-number">0.0065</span>, ..., <span class="hljs-number">0.0000</span>, <span class="hljs-number">0.0000</span>, <span class="hljs-number">0.0000</span>]], | |
| grad_fn=<CopySlices>), descriptors=tensor([[[-<span class="hljs-number">0.0807</span>, <span class="hljs-number">0.0114</span>, -<span class="hljs-number">0.1210</span>, ..., -<span class="hljs-number">0.1122</span>, <span class="hljs-number">0.0899</span>, <span class="hljs-number">0.0357</span>], | |
| [-<span class="hljs-number">0.0807</span>, <span class="hljs-number">0.0114</span>, -<span class="hljs-number">0.1210</span>, ..., -<span class="hljs-number">0.1122</span>, <span class="hljs-number">0.0899</span>, <span class="hljs-number">0.0357</span>], | |
| [-<span class="hljs-number">0.0807</span>, <span class="hljs-number">0.0114</span>, -<span class="hljs-number">0.1210</span>, ..., -<span class="hljs-number">0.1122</span>, <span class="hljs-number">0.0899</span>, <span class="hljs-number">0.0357</span>], | |
| ...], | |
| grad_fn=<CopySlices>), mask=tensor([[<span class="hljs-number">1</span>, <span class="hljs-number">1</span>, <span class="hljs-number">1</span>, ..., <span class="hljs-number">1</span>, <span class="hljs-number">1</span>, <span class="hljs-number">1</span>], | |
| [<span class="hljs-number">1</span>, <span class="hljs-number">1</span>, <span class="hljs-number">1</span>, ..., <span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>]], dtype=torch.int32), hidden_states=<span class="hljs-literal">None</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-17xk3dd">이미지에 실제 키포인트를 표시하기 위해선 결과값을 후처리 해야합니다. 이를 위해 실제 이미지 크기를 결과값과 함께 <code>post_process_keypoint_detection</code>에 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="language-python "><!-- HTML_TAG_START -->image_sizes = [(image.size[<span class="hljs-number">1</span>], image.size[<span class="hljs-number">0</span>]) <span class="hljs-keyword">for</span> image <span class="hljs-keyword">in</span> images] | |
| outputs = processor.post_process_keypoint_detection(outputs, image_sizes)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1i38bsn">위 코드를 통해 결과값은 딕셔너리를 갖는 리스트가 되고, 각 딕셔너리들은 후처리된 키포인트, 점수 및 디스크립터로 이루어져있습니다.</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="language-python "><!-- HTML_TAG_START -->[{<span class="hljs-string">'keypoints'</span>: tensor([[ <span class="hljs-number">226</span>, <span class="hljs-number">57</span>], | |
| [ <span class="hljs-number">356</span>, <span class="hljs-number">57</span>], | |
| [ <span class="hljs-number">89</span>, <span class="hljs-number">64</span>], | |
| ..., | |
| [<span class="hljs-number">3604</span>, <span class="hljs-number">3391</span>]], dtype=torch.int32), | |
| <span class="hljs-string">'scores'</span>: tensor([<span class="hljs-number">0.0056</span>, <span class="hljs-number">0.0053</span>, ...], grad_fn=<IndexBackward0>), | |
| <span class="hljs-string">'descriptors'</span>: tensor([[-<span class="hljs-number">0.0807</span>, <span class="hljs-number">0.0114</span>, -<span class="hljs-number">0.1210</span>, ..., -<span class="hljs-number">0.1122</span>, <span class="hljs-number">0.0899</span>, <span class="hljs-number">0.0357</span>], | |
| [-<span class="hljs-number">0.0807</span>, <span class="hljs-number">0.0114</span>, -<span class="hljs-number">0.1210</span>, ..., -<span class="hljs-number">0.1122</span>, <span class="hljs-number">0.0899</span>, <span class="hljs-number">0.0357</span>]], | |
| grad_fn=<IndexBackward0>)}, | |
| {<span class="hljs-string">'keypoints'</span>: tensor([[ <span class="hljs-number">46</span>, <span class="hljs-number">6</span>], | |
| [ <span class="hljs-number">78</span>, <span class="hljs-number">6</span>], | |
| [<span class="hljs-number">422</span>, <span class="hljs-number">6</span>], | |
| [<span class="hljs-number">206</span>, <span class="hljs-number">404</span>]], dtype=torch.int32), | |
| <span class="hljs-string">'scores'</span>: tensor([<span class="hljs-number">0.0206</span>, <span class="hljs-number">0.0058</span>, <span class="hljs-number">0.0065</span>, <span class="hljs-number">0.0053</span>, <span class="hljs-number">0.0070</span>, ...,grad_fn=<IndexBackward0>), | |
| <span class="hljs-string">'descriptors'</span>: tensor([[-<span class="hljs-number">0.0525</span>, <span class="hljs-number">0.0726</span>, <span class="hljs-number">0.0270</span>, ..., <span class="hljs-number">0.0389</span>, -<span class="hljs-number">0.0189</span>, -<span class="hljs-number">0.0211</span>], | |
| [-<span class="hljs-number">0.0525</span>, <span class="hljs-number">0.0726</span>, <span class="hljs-number">0.0270</span>, ..., <span class="hljs-number">0.0389</span>, -<span class="hljs-number">0.0189</span>, -<span class="hljs-number">0.0211</span>]}]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-14nlu7l">이제 위 딕셔너리를 사용하여 키포인트를 표시할 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="language-python "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt | |
| <span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">for</span> i <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(<span class="hljs-built_in">len</span>(images)): | |
| keypoints = outputs[i][<span class="hljs-string">"keypoints"</span>] | |
| scores = outputs[i][<span class="hljs-string">"scores"</span>] | |
| descriptors = outputs[i][<span class="hljs-string">"descriptors"</span>] | |
| keypoints = outputs[i][<span class="hljs-string">"keypoints"</span>].detach().numpy() | |
| scores = outputs[i][<span class="hljs-string">"scores"</span>].detach().numpy() | |
| image = images[i] | |
| image_width, image_height = image.size | |
| plt.axis(<span class="hljs-string">'off'</span>) | |
| plt.imshow(image) | |
| plt.scatter( | |
| keypoints[:, <span class="hljs-number">0</span>], | |
| keypoints[:, <span class="hljs-number">1</span>], | |
| s=scores * <span class="hljs-number">100</span>, | |
| c=<span class="hljs-string">'cyan'</span>, | |
| alpha=<span class="hljs-number">0.4</span> | |
| ) | |
| plt.show()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-sfp95c">아래에서 결과를 확인할 수 있습니다.</p> <div style="display: flex; align-items: center;" data-svelte-h="svelte-5cde1n"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee_keypoint.png" alt="Bee" style="height: 200px; object-fit: contain; margin-right: 10px;"> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats_keypoint.png" alt="Cats" style="height: 200px; object-fit: contain;"></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/keypoint_detection.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 data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_gzo5de = { | |
| 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.5711aec5.js"), | |
| import("/docs/transformers/main/ko/_app/immutable/entry/app.fcc7a1b0.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 162], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 26.9 kB
- Xet hash:
- 923826b315cfef0ac5e29975c24da253e4a91bf2c85e637c1a9b49901f0eee40
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.