Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Keypoint Detection","local":"keypoint-detection","sections":[],"depth":1}"> | |
| <link href="/docs/transformers/pr_33892/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/entry/start.b2c4257a.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/scheduler.31fdf58d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/singletons.9860629f.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/index.252883d5.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/paths.e85c0ec8.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/entry/app.05ef1f97.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/preload-helper.40847a0e.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/index.2f76fdf0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/nodes/0.ca4aafa4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/nodes/559.3ad164ce.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/CopyLLMTxtMenu.ff482081.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.71f274cc.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/IconCopy.ac192424.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/CodeBlock.ab12f8e1.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33892/en/_app/immutable/chunks/DocNotebookDropdown.dd28433e.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Keypoint Detection","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 max-sm:gap-0.5 h-6 max-sm:h-5 px-2 max-sm:px-1.5 text-[11px] max-sm:text-[9px] 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"><svg class="w-3 h-3 max-sm:w-2.5 max-sm:h-2.5" 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-6 max-sm:h-5 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 w-3 h-3 max-sm:w-2.5 max-sm:h-2.5 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>Keypoint Detection</span></h1> <p data-svelte-h="svelte-aqx5b4">Keypoint detection identifies and locates specific points of interest within an image. These keypoints, also known as landmarks, represent meaningful features of objects, such as facial features or object parts. These models take an image input and return the following outputs:</p> <ul data-svelte-h="svelte-1thyc59"><li><strong>Keypoints and Scores</strong>: Points of interest and their confidence scores.</li> <li><strong>Descriptors</strong>: A representation of the image region surrounding each keypoint, capturing its texture, gradient, orientation and other properties.</li></ul> <p data-svelte-h="svelte-th3u1i">In this guide, we will show how to extract keypoints from images.</p> <p data-svelte-h="svelte-hz306d">For this tutorial, we will use <a href="./model_doc/superpoint">SuperPoint</a>, a foundation model for keypoint detection.</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, 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-tdrc12">Let’s test the model on the images below.</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=""><!-- 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-1uih3t1">We can now process our inputs and infer.</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 -->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-1c8r0oi">The model output has relative keypoints, descriptors, masks and scores for each item in the batch. The mask highlights areas of the image where keypoints are present.</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 -->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-ee9vxe">To plot actual keypoints in the image, we need to postprocess the output. To do so, we have to pass the actual image sizes to <code>post_process_keypoint_detection</code> along with outputs.</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 -->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-nmda5m">The outputs are now a list of dictionaries where each dictionary is a processed output of keypoints, scores and descriptors.</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-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-1tjla8l">We can use these to plot the keypoints.</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> 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-1dcx6hk">Below you can see the outputs.</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/en/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_16tnnm8 = { | |
| assets: "/docs/transformers/pr_33892/en", | |
| base: "/docs/transformers/pr_33892/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/pr_33892/en/_app/immutable/entry/start.b2c4257a.js"), | |
| import("/docs/transformers/pr_33892/en/_app/immutable/entry/app.05ef1f97.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 559], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 26.6 kB
- Xet hash:
- 78a8b0cbffbc14c8fc7f85b15476525311f80ed99514c43eea7e5872728c6d6b
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.