Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"ViTPose","local":"vitpose","sections":[{"title":"Notes","local":"notes","sections":[],"depth":2},{"title":"Resources","local":"resources","sections":[],"depth":2},{"title":"VitPoseImageProcessor","local":"transformers.VitPoseImageProcessor","sections":[],"depth":2},{"title":"VitPoseConfig","local":"transformers.VitPoseConfig","sections":[],"depth":2},{"title":"VitPoseForPoseEstimation","local":"transformers.VitPoseForPoseEstimation","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/transformers/pr_33962/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/entry/start.1776ac26.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/scheduler.31fdf58d.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/singletons.73ad6261.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/index.252883d5.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/paths.7e4d6052.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/entry/app.d2b9a7d8.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/preload-helper.769e5991.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/index.2f76fdf0.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/nodes/0.29a76cb1.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/nodes/463.11baaeab.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/Tip.8d349121.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/CopyLLMTxtMenu.9922688f.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/globals.7f7f1b26.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/IconCopy.ac192424.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.4975a63c.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/Docstring.470b693c.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/CodeBlock.ab12f8e1.js"> | |
| <link rel="modulepreload" href="/docs/transformers/pr_33962/en/_app/immutable/chunks/ExampleCodeBlock.80dfa610.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"ViTPose","local":"vitpose","sections":[{"title":"Notes","local":"notes","sections":[],"depth":2},{"title":"Resources","local":"resources","sections":[],"depth":2},{"title":"VitPoseImageProcessor","local":"transformers.VitPoseImageProcessor","sections":[],"depth":2},{"title":"VitPoseConfig","local":"transformers.VitPoseConfig","sections":[],"depth":2},{"title":"VitPoseForPoseEstimation","local":"transformers.VitPoseForPoseEstimation","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <p data-svelte-h="svelte-1a7zm26"><em>This model was released on 2022-04-26 and added to Hugging Face Transformers on 2025-01-08.</em></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 style="float: right;" data-svelte-h="svelte-100e61"><div class="flex flex-wrap space-x-1"><img alt="PyTorch" src="https://img.shields.io/badge/PyTorch-DE3412?style=flat&logo=pytorch&logoColor=white"></div></div> <h1 class="relative group"><a id="vitpose" 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="#vitpose"><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>ViTPose</span></h1> <p data-svelte-h="svelte-1v22yin"><a href="https://huggingface.co/papers/2204.12484" rel="nofollow">ViTPose</a> is a vision transformer-based model for keypoint (pose) estimation. It uses a simple, non-hierarchical <a href="./vit">ViT</a> backbone and a lightweight decoder head. This architecture simplifies model design, takes advantage of transformer scalability, and can be adapted to different training strategies.</p> <p data-svelte-h="svelte-1w9zs1n"><a href="https://huggingface.co/papers/2212.04246" rel="nofollow">ViTPose++</a> improves on ViTPose by incorporating a mixture-of-experts (MoE) module in the backbone and using more diverse pretraining data.</p> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/vitpose-architecture.png" alt="drawing" width="600"> <p data-svelte-h="svelte-9e850o">You can find all ViTPose and ViTPose++ checkpoints under the <a href="https://huggingface.co/collections/usyd-community/vitpose-677fcfd0a0b2b5c8f79c4335" rel="nofollow">ViTPose collection</a>.</p> <p data-svelte-h="svelte-a1p9m2">The example below demonstrates pose estimation with the <a href="/docs/transformers/pr_33962/en/model_doc/vitpose#transformers.VitPoseForPoseEstimation">VitPoseForPoseEstimation</a> class.</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">import</span> requests | |
| <span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np | |
| <span class="hljs-keyword">import</span> supervision <span class="hljs-keyword">as</span> sv | |
| <span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image | |
| <span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor, RTDetrForObjectDetection, VitPoseForPoseEstimation | |
| <span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> Accelerator | |
| device = Accelerator().device | |
| url = <span class="hljs-string">"https://www.fcbarcelona.com/fcbarcelona/photo/2021/01/31/3c55a19f-dfc1-4451-885e-afd14e890a11/mini_2021-01-31-BARCELONA-ATHLETIC-BILBAOI-30.JPG"</span> | |
| image = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw) | |
| <span class="hljs-comment"># Detect humans in the image</span> | |
| person_image_processor = AutoProcessor.from_pretrained(<span class="hljs-string">"PekingU/rtdetr_r50vd_coco_o365"</span>) | |
| person_model = RTDetrForObjectDetection.from_pretrained(<span class="hljs-string">"PekingU/rtdetr_r50vd_coco_o365"</span>, device_map=device) | |
| inputs = person_image_processor(images=image, return_tensors=<span class="hljs-string">"pt"</span>).to(person_model.device) | |
| <span class="hljs-keyword">with</span> torch.no_grad(): | |
| outputs = person_model(**inputs) | |
| results = person_image_processor.post_process_object_detection( | |
| outputs, target_sizes=torch.tensor([(image.height, image.width)]), threshold=<span class="hljs-number">0.3</span> | |
| ) | |
| result = results[<span class="hljs-number">0</span>] | |
| <span class="hljs-comment"># Human label refers 0 index in COCO dataset</span> | |
| person_boxes = result[<span class="hljs-string">"boxes"</span>][result[<span class="hljs-string">"labels"</span>] == <span class="hljs-number">0</span>] | |
| person_boxes = person_boxes.cpu().numpy() | |
| <span class="hljs-comment"># Convert boxes from VOC (x1, y1, x2, y2) to COCO (x1, y1, w, h) format</span> | |
| person_boxes[:, <span class="hljs-number">2</span>] = person_boxes[:, <span class="hljs-number">2</span>] - person_boxes[:, <span class="hljs-number">0</span>] | |
| person_boxes[:, <span class="hljs-number">3</span>] = person_boxes[:, <span class="hljs-number">3</span>] - person_boxes[:, <span class="hljs-number">1</span>] | |
| <span class="hljs-comment"># Detect keypoints for each person found</span> | |
| image_processor = AutoProcessor.from_pretrained(<span class="hljs-string">"usyd-community/vitpose-base-simple"</span>) | |
| model = VitPoseForPoseEstimation.from_pretrained(<span class="hljs-string">"usyd-community/vitpose-base-simple"</span>, device_map=device) | |
| inputs = image_processor(image, boxes=[person_boxes], return_tensors=<span class="hljs-string">"pt"</span>).to(model.device) | |
| <span class="hljs-keyword">with</span> torch.no_grad(): | |
| outputs = model(**inputs) | |
| pose_results = image_processor.post_process_pose_estimation(outputs, boxes=[person_boxes]) | |
| image_pose_result = pose_results[<span class="hljs-number">0</span>] | |
| xy = torch.stack([pose_result[<span class="hljs-string">'keypoints'</span>] <span class="hljs-keyword">for</span> pose_result <span class="hljs-keyword">in</span> image_pose_result]).cpu().numpy() | |
| scores = torch.stack([pose_result[<span class="hljs-string">'scores'</span>] <span class="hljs-keyword">for</span> pose_result <span class="hljs-keyword">in</span> image_pose_result]).cpu().numpy() | |
| key_points = sv.KeyPoints( | |
| xy=xy, confidence=scores | |
| ) | |
| edge_annotator = sv.EdgeAnnotator( | |
| color=sv.Color.GREEN, | |
| thickness=<span class="hljs-number">1</span> | |
| ) | |
| vertex_annotator = sv.VertexAnnotator( | |
| color=sv.Color.RED, | |
| radius=<span class="hljs-number">2</span> | |
| ) | |
| annotated_frame = edge_annotator.annotate( | |
| scene=image.copy(), | |
| key_points=key_points | |
| ) | |
| annotated_frame = vertex_annotator.annotate( | |
| scene=annotated_frame, | |
| key_points=key_points | |
| ) | |
| annotated_frame<!-- HTML_TAG_END --></pre></div> <div class="flex justify-center" data-svelte-h="svelte-f93tab"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/vitpose.png"></div> <p data-svelte-h="svelte-nf5ooi">Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the <a href="../quantization/overview">Quantization</a> overview for more available quantization backends.</p> <p data-svelte-h="svelte-w36i1c">The example below uses <a href="../quantization/torchao">torchao</a> to only quantize the weights to int4.</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"># pip install torchao</span> | |
| <span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">import</span> requests | |
| <span class="hljs-keyword">import</span> numpy <span class="hljs-keyword">as</span> np | |
| <span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image | |
| <span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor, RTDetrForObjectDetection, VitPoseForPoseEstimation, TorchAoConfig | |
| url = <span class="hljs-string">"https://www.fcbarcelona.com/fcbarcelona/photo/2021/01/31/3c55a19f-dfc1-4451-885e-afd14e890a11/mini_2021-01-31-BARCELONA-ATHLETIC-BILBAOI-30.JPG"</span> | |
| image = Image.<span class="hljs-built_in">open</span>(requests.get(url, stream=<span class="hljs-literal">True</span>).raw) | |
| person_image_processor = AutoProcessor.from_pretrained(<span class="hljs-string">"PekingU/rtdetr_r50vd_coco_o365"</span>) | |
| person_model = RTDetrForObjectDetection.from_pretrained(<span class="hljs-string">"PekingU/rtdetr_r50vd_coco_o365"</span>, device_map=device) | |
| inputs = person_image_processor(images=image, return_tensors=<span class="hljs-string">"pt"</span>).to(device) | |
| <span class="hljs-keyword">with</span> torch.no_grad(): | |
| outputs = person_model(**inputs) | |
| results = person_image_processor.post_process_object_detection( | |
| outputs, target_sizes=torch.tensor([(image.height, image.width)]), threshold=<span class="hljs-number">0.3</span> | |
| ) | |
| result = results[<span class="hljs-number">0</span>] | |
| person_boxes = result[<span class="hljs-string">"boxes"</span>][result[<span class="hljs-string">"labels"</span>] == <span class="hljs-number">0</span>] | |
| person_boxes = person_boxes.cpu().numpy() | |
| person_boxes[:, <span class="hljs-number">2</span>] = person_boxes[:, <span class="hljs-number">2</span>] - person_boxes[:, <span class="hljs-number">0</span>] | |
| person_boxes[:, <span class="hljs-number">3</span>] = person_boxes[:, <span class="hljs-number">3</span>] - person_boxes[:, <span class="hljs-number">1</span>] | |
| quantization_config = TorchAoConfig(<span class="hljs-string">"int4_weight_only"</span>, group_size=<span class="hljs-number">128</span>) | |
| image_processor = AutoProcessor.from_pretrained(<span class="hljs-string">"usyd-community/vitpose-plus-huge"</span>) | |
| model = VitPoseForPoseEstimation.from_pretrained(<span class="hljs-string">"usyd-community/vitpose-plus-huge"</span>, device_map=device, quantization_config=quantization_config) | |
| inputs = image_processor(image, boxes=[person_boxes], return_tensors=<span class="hljs-string">"pt"</span>).to(device) | |
| <span class="hljs-keyword">with</span> torch.no_grad(): | |
| outputs = model(**inputs) | |
| pose_results = image_processor.post_process_pose_estimation(outputs, boxes=[person_boxes]) | |
| image_pose_result = pose_results[<span class="hljs-number">0</span>]<!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="notes" 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="#notes"><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>Notes</span></h2> <ul><li data-svelte-h="svelte-92f4sm"><p>Use <a href="/docs/transformers/pr_33962/en/model_doc/auto#transformers.AutoProcessor">AutoProcessor</a> to automatically prepare bounding box and image inputs.</p></li> <li data-svelte-h="svelte-8xam7b"><p>ViTPose is a top-down pose estimator. It uses a object detector to detect individuals first before keypoint prediction.</p></li> <li><p data-svelte-h="svelte-15141u4">ViTPose++ has 6 different MoE expert heads (COCO validation <code>0</code>, AiC <code>1</code>, MPII <code>2</code>, AP-10K <code>3</code>, APT-36K <code>4</code>, COCO-WholeBody <code>5</code>) which supports 6 different datasets. Pass a specific value corresponding to the dataset to the <code>dataset_index</code> to indicate which expert to use.</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> AutoProcessor, VitPoseForPoseEstimation | |
| <span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> Accelerator | |
| device = Accelerator().device | |
| image_processor = AutoProcessor.from_pretrained(<span class="hljs-string">"usyd-community/vitpose-plus-base"</span>) | |
| model = VitPoseForPoseEstimation.from_pretrained(<span class="hljs-string">"usyd-community/vitpose-plus-base"</span>, device=device) | |
| inputs = image_processor(image, boxes=[person_boxes], return_tensors=<span class="hljs-string">"pt"</span>).to(model.device) | |
| dataset_index = torch.tensor([<span class="hljs-number">0</span>], device=device) <span class="hljs-comment"># must be a tensor of shape (batch_size,)</span> | |
| <span class="hljs-keyword">with</span> torch.no_grad(): | |
| outputs = model(**inputs, dataset_index=dataset_index) | |
| ``` | |
| <!-- HTML_TAG_END --></pre></div></li> <li><p data-svelte-h="svelte-y4ytp0"><a href="https://opencv.org/" rel="nofollow">OpenCV</a> is an alternative option for visualizing the estimated pose.</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"># pip install opencv-python</span> | |
| <span class="hljs-keyword">import</span> math | |
| <span class="hljs-keyword">import</span> cv2 | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">draw_points</span>(<span class="hljs-params">image, keypoints, scores, pose_keypoint_color, keypoint_score_threshold, radius, show_keypoint_weight</span>): | |
| <span class="hljs-keyword">if</span> pose_keypoint_color <span class="hljs-keyword">is</span> <span class="hljs-keyword">not</span> <span class="hljs-literal">None</span>: | |
| <span class="hljs-keyword">assert</span> <span class="hljs-built_in">len</span>(pose_keypoint_color) == <span class="hljs-built_in">len</span>(keypoints) | |
| <span class="hljs-keyword">for</span> kid, (kpt, kpt_score) <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(<span class="hljs-built_in">zip</span>(keypoints, scores)): | |
| x_coord, y_coord = <span class="hljs-built_in">int</span>(kpt[<span class="hljs-number">0</span>]), <span class="hljs-built_in">int</span>(kpt[<span class="hljs-number">1</span>]) | |
| <span class="hljs-keyword">if</span> kpt_score > keypoint_score_threshold: | |
| color = <span class="hljs-built_in">tuple</span>(<span class="hljs-built_in">int</span>(c) <span class="hljs-keyword">for</span> c <span class="hljs-keyword">in</span> pose_keypoint_color[kid]) | |
| <span class="hljs-keyword">if</span> show_keypoint_weight: | |
| cv2.circle(image, (<span class="hljs-built_in">int</span>(x_coord), <span class="hljs-built_in">int</span>(y_coord)), radius, color, -<span class="hljs-number">1</span>) | |
| transparency = <span class="hljs-built_in">max</span>(<span class="hljs-number">0</span>, <span class="hljs-built_in">min</span>(<span class="hljs-number">1</span>, kpt_score)) | |
| cv2.addWeighted(image, transparency, image, <span class="hljs-number">1</span> - transparency, <span class="hljs-number">0</span>, dst=image) | |
| <span class="hljs-keyword">else</span>: | |
| cv2.circle(image, (<span class="hljs-built_in">int</span>(x_coord), <span class="hljs-built_in">int</span>(y_coord)), radius, color, -<span class="hljs-number">1</span>) | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">draw_links</span>(<span class="hljs-params">image, keypoints, scores, keypoint_edges, link_colors, keypoint_score_threshold, thickness, show_keypoint_weight, stick_width = <span class="hljs-number">2</span></span>): | |
| height, width, _ = image.shape | |
| <span class="hljs-keyword">if</span> keypoint_edges <span class="hljs-keyword">is</span> <span class="hljs-keyword">not</span> <span class="hljs-literal">None</span> <span class="hljs-keyword">and</span> link_colors <span class="hljs-keyword">is</span> <span class="hljs-keyword">not</span> <span class="hljs-literal">None</span>: | |
| <span class="hljs-keyword">assert</span> <span class="hljs-built_in">len</span>(link_colors) == <span class="hljs-built_in">len</span>(keypoint_edges) | |
| <span class="hljs-keyword">for</span> sk_id, sk <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(keypoint_edges): | |
| x1, y1, score1 = (<span class="hljs-built_in">int</span>(keypoints[sk[<span class="hljs-number">0</span>], <span class="hljs-number">0</span>]), <span class="hljs-built_in">int</span>(keypoints[sk[<span class="hljs-number">0</span>], <span class="hljs-number">1</span>]), scores[sk[<span class="hljs-number">0</span>]]) | |
| x2, y2, score2 = (<span class="hljs-built_in">int</span>(keypoints[sk[<span class="hljs-number">1</span>], <span class="hljs-number">0</span>]), <span class="hljs-built_in">int</span>(keypoints[sk[<span class="hljs-number">1</span>], <span class="hljs-number">1</span>]), scores[sk[<span class="hljs-number">1</span>]]) | |
| <span class="hljs-keyword">if</span> ( | |
| x1 > <span class="hljs-number">0</span> | |
| <span class="hljs-keyword">and</span> x1 < width | |
| <span class="hljs-keyword">and</span> y1 > <span class="hljs-number">0</span> | |
| <span class="hljs-keyword">and</span> y1 < height | |
| <span class="hljs-keyword">and</span> x2 > <span class="hljs-number">0</span> | |
| <span class="hljs-keyword">and</span> x2 < width | |
| <span class="hljs-keyword">and</span> y2 > <span class="hljs-number">0</span> | |
| <span class="hljs-keyword">and</span> y2 < height | |
| <span class="hljs-keyword">and</span> score1 > keypoint_score_threshold | |
| <span class="hljs-keyword">and</span> score2 > keypoint_score_threshold | |
| ): | |
| color = <span class="hljs-built_in">tuple</span>(<span class="hljs-built_in">int</span>(c) <span class="hljs-keyword">for</span> c <span class="hljs-keyword">in</span> link_colors[sk_id]) | |
| <span class="hljs-keyword">if</span> show_keypoint_weight: | |
| X = (x1, x2) | |
| Y = (y1, y2) | |
| mean_x = np.mean(X) | |
| mean_y = np.mean(Y) | |
| length = ((Y[<span class="hljs-number">0</span>] - Y[<span class="hljs-number">1</span>]) ** <span class="hljs-number">2</span> + (X[<span class="hljs-number">0</span>] - X[<span class="hljs-number">1</span>]) ** <span class="hljs-number">2</span>) ** <span class="hljs-number">0.5</span> | |
| angle = math.degrees(math.atan2(Y[<span class="hljs-number">0</span>] - Y[<span class="hljs-number">1</span>], X[<span class="hljs-number">0</span>] - X[<span class="hljs-number">1</span>])) | |
| polygon = cv2.ellipse2Poly( | |
| (<span class="hljs-built_in">int</span>(mean_x), <span class="hljs-built_in">int</span>(mean_y)), (<span class="hljs-built_in">int</span>(length / <span class="hljs-number">2</span>), <span class="hljs-built_in">int</span>(stick_width)), <span class="hljs-built_in">int</span>(angle), <span class="hljs-number">0</span>, <span class="hljs-number">360</span>, <span class="hljs-number">1</span> | |
| ) | |
| cv2.fillConvexPoly(image, polygon, color) | |
| transparency = <span class="hljs-built_in">max</span>(<span class="hljs-number">0</span>, <span class="hljs-built_in">min</span>(<span class="hljs-number">1</span>, <span class="hljs-number">0.5</span> * (keypoints[sk[<span class="hljs-number">0</span>], <span class="hljs-number">2</span>] + keypoints[sk[<span class="hljs-number">1</span>], <span class="hljs-number">2</span>]))) | |
| cv2.addWeighted(image, transparency, image, <span class="hljs-number">1</span> - transparency, <span class="hljs-number">0</span>, dst=image) | |
| <span class="hljs-keyword">else</span>: | |
| cv2.line(image, (x1, y1), (x2, y2), color, thickness=thickness) | |
| <span class="hljs-comment"># Note: keypoint_edges and color palette are dataset-specific</span> | |
| keypoint_edges = model.config.edges | |
| palette = np.array( | |
| [ | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">128</span>, <span class="hljs-number">0</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">153</span>, <span class="hljs-number">51</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">178</span>, <span class="hljs-number">102</span>], | |
| [<span class="hljs-number">230</span>, <span class="hljs-number">230</span>, <span class="hljs-number">0</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">153</span>, <span class="hljs-number">255</span>], | |
| [<span class="hljs-number">153</span>, <span class="hljs-number">204</span>, <span class="hljs-number">255</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">102</span>, <span class="hljs-number">255</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">51</span>, <span class="hljs-number">255</span>], | |
| [<span class="hljs-number">102</span>, <span class="hljs-number">178</span>, <span class="hljs-number">255</span>], | |
| [<span class="hljs-number">51</span>, <span class="hljs-number">153</span>, <span class="hljs-number">255</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">153</span>, <span class="hljs-number">153</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">102</span>, <span class="hljs-number">102</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">51</span>, <span class="hljs-number">51</span>], | |
| [<span class="hljs-number">153</span>, <span class="hljs-number">255</span>, <span class="hljs-number">153</span>], | |
| [<span class="hljs-number">102</span>, <span class="hljs-number">255</span>, <span class="hljs-number">102</span>], | |
| [<span class="hljs-number">51</span>, <span class="hljs-number">255</span>, <span class="hljs-number">51</span>], | |
| [<span class="hljs-number">0</span>, <span class="hljs-number">255</span>, <span class="hljs-number">0</span>], | |
| [<span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">255</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>], | |
| [<span class="hljs-number">255</span>, <span class="hljs-number">255</span>, <span class="hljs-number">255</span>], | |
| ] | |
| ) | |
| link_colors = palette[[<span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">7</span>, <span class="hljs-number">7</span>, <span class="hljs-number">7</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>]] | |
| keypoint_colors = palette[[<span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">16</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">9</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>, <span class="hljs-number">0</span>]] | |
| numpy_image = np.array(image) | |
| <span class="hljs-keyword">for</span> pose_result <span class="hljs-keyword">in</span> image_pose_result: | |
| scores = np.array(pose_result[<span class="hljs-string">"scores"</span>]) | |
| keypoints = np.array(pose_result[<span class="hljs-string">"keypoints"</span>]) | |
| <span class="hljs-comment"># draw each point on image</span> | |
| draw_points(numpy_image, keypoints, scores, keypoint_colors, keypoint_score_threshold=<span class="hljs-number">0.3</span>, radius=<span class="hljs-number">4</span>, show_keypoint_weight=<span class="hljs-literal">False</span>) | |
| <span class="hljs-comment"># draw links</span> | |
| draw_links(numpy_image, keypoints, scores, keypoint_edges, link_colors, keypoint_score_threshold=<span class="hljs-number">0.3</span>, thickness=<span class="hljs-number">1</span>, show_keypoint_weight=<span class="hljs-literal">False</span>) | |
| pose_image = Image.fromarray(numpy_image) | |
| pose_image<!-- HTML_TAG_END --></pre></div></li></ul> <h2 class="relative group"><a id="resources" 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="#resources"><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>Resources</span></h2> <p data-svelte-h="svelte-sux81q">Refer to resources below to learn more about using ViTPose.</p> <ul data-svelte-h="svelte-1lwv20u"><li>This <a href="https://github.com/NielsRogge/Transformers-Tutorials/blob/master/ViTPose/Inference_with_ViTPose_for_body_pose_estimation.ipynb" rel="nofollow">notebook</a> demonstrates inference and visualization.</li> <li>This <a href="https://huggingface.co/spaces/hysts/ViTPose-transformers" rel="nofollow">Space</a> demonstrates ViTPose on images and video.</li></ul> <h2 class="relative group"><a id="transformers.VitPoseImageProcessor" 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="#transformers.VitPoseImageProcessor"><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>VitPoseImageProcessor</span></h2> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"> <div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="transformers.VitPoseImageProcessor"><!-- HTML_TAG_START --><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">class</span> <span class="font-medium">transformers.</span><span class="font-semibold">VitPoseImageProcessor</span></span></h3><!-- HTML_TAG_END --> <a id="transformers.VitPoseImageProcessor" class="header-link invisible with-hover:group-hover:visible pr-2" href="#transformers.VitPoseImageProcessor"><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></a> <a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/transformers/blob/vr_33962/src/transformers/models/vitpose/image_processing_vitpose.py#L328" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span class="hidden md:block mx-0.5 hover:!underline" data-svelte-h="svelte-122apf4">source</span> <span data-svelte-h="svelte-x0xyl0">></span></a></span> <p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span data-svelte-h="svelte-8mvn6a">(</span> <span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">do_affine_transform<span class="opacity-60">: bool = True</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">size<span class="opacity-60">: typing.Optional[dict[str, int]] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">do_rescale<span class="opacity-60">: bool = True</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">rescale_factor<span class="opacity-60">: typing.Union[int, float] = 0.00392156862745098</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">do_normalize<span class="opacity-60">: bool = True</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">image_mean<span class="opacity-60">: typing.Union[float, list[float], NoneType] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">image_std<span class="opacity-60">: typing.Union[float, list[float], NoneType] = None</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">**kwargs<span class="opacity-60"></span></span> </span> <span data-svelte-h="svelte-1jq0pl7">)</span> </p> <div class="!mb-10 relative docstring-details "> <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800" data-svelte-h="svelte-lt6pb6">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p> <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.do_affine_transform" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.do_affine_transform"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>do_affine_transform</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) — | |
| Whether to apply an affine transformation to the input images.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.size" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.size"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>size</strong> (<code>dict[str, int]</code> <em>optional</em>, defaults to <code>{"height" -- 256, "width": 192}</code>): | |
| Resolution of the image after <code>affine_transform</code> is applied. Only has an effect if <code>do_affine_transform</code> is set to <code>True</code>. Can | |
| be overridden by <code>size</code> in the <code>preprocess</code> method.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.do_rescale" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.do_rescale"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>do_rescale</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) — | |
| Whether or not to apply the scaling factor (to make pixel values floats between 0. and 1.).<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.rescale_factor" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.rescale_factor"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>rescale_factor</strong> (<code>int</code> or <code>float</code>, <em>optional</em>, defaults to <code>1/255</code>) — | |
| Scale factor to use if rescaling the image. Can be overridden by <code>rescale_factor</code> in the <code>preprocess</code> | |
| method.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.do_normalize" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.do_normalize"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>do_normalize</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) — | |
| Whether or not to normalize the input with mean and standard deviation.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.image_mean" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.image_mean"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>image_mean</strong> (<code>list[int]</code>, defaults to <code>[0.485, 0.456, 0.406]</code>, <em>optional</em>) — | |
| The sequence of means for each channel, to be used when normalizing images.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.image_std" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.image_std"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>image_std</strong> (<code>list[int]</code>, defaults to <code>[0.229, 0.224, 0.225]</code>, <em>optional</em>) — | |
| The sequence of standard deviations for each channel, to be used when normalizing images.<!-- HTML_TAG_END --> </span></span> </li></ul> </div></div> <p data-svelte-h="svelte-1uf40pk">Constructs a VitPose image processor.</p> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"> <div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="transformers.VitPoseImageProcessor.preprocess"><!-- HTML_TAG_START --><h4 class="!m-0"><span class="flex-1 rounded-xl py-0.5 break-all bg-gradient-to-r from-blue-50/60 to-white dark:from-gray-900 dark:to-gray-950 text-blue-700 dark:text-blue-300 font-medium px-2"><svg width="1em" height="1em" viewBox="0 0 32 33" class="mr-1 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg"><path d="M5.80566 18.3545C4.90766 17.4565 4.90766 16.0005 5.80566 15.1025L14.3768 6.53142C15.2748 5.63342 16.7307 5.63342 17.6287 6.53142L26.1999 15.1025C27.0979 16.0005 27.0979 17.4565 26.1999 18.3545L17.6287 26.9256C16.7307 27.8236 15.2748 27.8236 14.3768 26.9256L5.80566 18.3545Z" fill="currentColor" fill-opacity="0.25"/><path fill-rule="evenodd" clip-rule="evenodd" d="M16.4801 13.9619C16.4801 12.9761 16.7467 12.5436 16.9443 12.3296C17.1764 12.078 17.5731 11.8517 18.2275 11.707C18.8821 11.5623 19.638 11.5342 20.4038 11.5582C20.7804 11.57 21.1341 11.5932 21.4719 11.6156L21.5263 11.6193C21.8195 11.6389 22.1626 11.6618 22.4429 11.6618V7.40825C22.3209 7.40825 22.1219 7.39596 21.7544 7.37149C21.4202 7.34925 20.9976 7.32115 20.5371 7.30672C19.6286 7.27824 18.4672 7.29779 17.3093 7.55377C16.1512 7.8098 14.8404 8.33724 13.8181 9.4452C12.7612 10.5907 12.2266 12.1236 12.2266 13.9619V15.0127H10.6836V19.2662H12.2266V26.6332H16.4801V19.2662H20.3394V15.0127H16.4801V13.9619Z" fill="currentColor"/></svg>preprocess</span></h4><!-- HTML_TAG_END --> <a id="transformers.VitPoseImageProcessor.preprocess" class="header-link invisible with-hover:group-hover:visible pr-2" href="#transformers.VitPoseImageProcessor.preprocess"><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></a> <a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/transformers/blob/vr_33962/src/transformers/models/vitpose/image_processing_vitpose.py#L423" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span class="hidden md:block mx-0.5 hover:!underline" data-svelte-h="svelte-122apf4">source</span> <span data-svelte-h="svelte-x0xyl0">></span></a></span> <p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span data-svelte-h="svelte-8mvn6a">(</span> <span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">images<span class="opacity-60">: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">boxes<span class="opacity-60">: typing.Union[list[list[float]], numpy.ndarray]</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">do_affine_transform<span class="opacity-60">: typing.Optional[bool] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">size<span class="opacity-60">: typing.Optional[dict[str, int]] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">do_rescale<span class="opacity-60">: typing.Optional[bool] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">rescale_factor<span class="opacity-60">: typing.Optional[float] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">do_normalize<span class="opacity-60">: typing.Optional[bool] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">image_mean<span class="opacity-60">: typing.Union[float, list[float], NoneType] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">image_std<span class="opacity-60">: typing.Union[float, list[float], NoneType] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">return_tensors<span class="opacity-60">: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">data_format<span class="opacity-60">: typing.Union[str, transformers.image_utils.ChannelDimension] = <ChannelDimension.FIRST: 'channels_first'></span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">input_data_format<span class="opacity-60">: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None</span></span> </span> <span data-svelte-h="svelte-1jq0pl7">)</span> <span class="font-bold" data-svelte-h="svelte-1j6k10o">→</span> <span class="rounded hover:bg-gray-400 cursor-pointer"><!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script><span><a | |
| href="/docs/transformers/pr_33962/en/main_classes/image_processor#transformers.BatchFeature" | |
| >BatchFeature</a></span><!-- HTML_TAG_END --></span></p> <div class="!mb-10 relative docstring-details "> <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800" data-svelte-h="svelte-lt6pb6">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p> <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.images" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.images"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>images</strong> (<code>ImageInput</code>) — | |
| Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If | |
| passing in images with pixel values between 0 and 1, set <code>do_rescale=False</code>.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.boxes" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.boxes"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>boxes</strong> (<code>list[list[list[float]]]</code> or <code>np.ndarray</code>) — | |
| List or array of bounding boxes for each image. Each box should be a list of 4 floats representing the bounding | |
| box coordinates in COCO format (top_left_x, top_left_y, width, height).<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.do_affine_transform" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.do_affine_transform"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>do_affine_transform</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>self.do_affine_transform</code>) — | |
| Whether to apply an affine transformation to the input images.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.size" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.size"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>size</strong> (<code>dict[str, int]</code> <em>optional</em>, defaults to <code>self.size</code>) — | |
| Dictionary in the format <code>{"height": h, "width": w}</code> specifying the size of the output image after | |
| resizing.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.do_rescale" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.do_rescale"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>do_rescale</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>self.do_rescale</code>) — | |
| Whether to rescale the image values between [0 - 1].<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.rescale_factor" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.rescale_factor"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>rescale_factor</strong> (<code>float</code>, <em>optional</em>, defaults to <code>self.rescale_factor</code>) — | |
| Rescale factor to rescale the image by if <code>do_rescale</code> is set to <code>True</code>.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.do_normalize" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.do_normalize"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>do_normalize</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>self.do_normalize</code>) — | |
| Whether to normalize the image.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.image_mean" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.image_mean"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>image_mean</strong> (<code>float</code> or <code>list[float]</code>, <em>optional</em>, defaults to <code>self.image_mean</code>) — | |
| Image mean to use if <code>do_normalize</code> is set to <code>True</code>.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.image_std" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.image_std"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>image_std</strong> (<code>float</code> or <code>list[float]</code>, <em>optional</em>, defaults to <code>self.image_std</code>) — | |
| Image standard deviation to use if <code>do_normalize</code> is set to <code>True</code>.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.preprocess.return_tensors" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.preprocess.return_tensors"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>return_tensors</strong> (<code>str</code> or <a href="/docs/transformers/pr_33962/en/internal/file_utils#transformers.TensorType">TensorType</a>, <em>optional</em>, defaults to <code>'np'</code>) — | |
| If set, will return tensors of a particular framework. Acceptable values are:</p> | |
| <ul> | |
| <li><code>'pt'</code>: Return PyTorch <code>torch.Tensor</code> objects.</li> | |
| <li><code>'np'</code>: Return NumPy <code>np.ndarray</code> objects.</li> | |
| </ul><!-- HTML_TAG_END --> </span></span> </li></ul> <div id="transformers.VitPoseImageProcessor.preprocess.returns" class="flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800 rounded "><p class="text-base">Returns</p> <!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script> | |
| <p><a | |
| href="/docs/transformers/pr_33962/en/main_classes/image_processor#transformers.BatchFeature" | |
| >BatchFeature</a></p> | |
| <!-- HTML_TAG_END --> <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700"></span></div> <p class="text-base"><!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script> | |
| <p>A <a | |
| href="/docs/transformers/pr_33962/en/main_classes/image_processor#transformers.BatchFeature" | |
| >BatchFeature</a> with the following fields:</p> | |
| <ul> | |
| <li><strong>pixel_values</strong> — Pixel values to be fed to a model, of shape (batch_size, num_channels, height, | |
| width).</li> | |
| </ul> | |
| <!-- HTML_TAG_END --></p> </div></div> <p data-svelte-h="svelte-1x3yxsa">Preprocess an image or batch of images.</p></div> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"> <div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="transformers.VitPoseImageProcessor.post_process_pose_estimation"><!-- HTML_TAG_START --><h4 class="!m-0"><span class="flex-1 rounded-xl py-0.5 break-all bg-gradient-to-r from-blue-50/60 to-white dark:from-gray-900 dark:to-gray-950 text-blue-700 dark:text-blue-300 font-medium px-2"><svg width="1em" height="1em" viewBox="0 0 32 33" class="mr-1 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg"><path d="M5.80566 18.3545C4.90766 17.4565 4.90766 16.0005 5.80566 15.1025L14.3768 6.53142C15.2748 5.63342 16.7307 5.63342 17.6287 6.53142L26.1999 15.1025C27.0979 16.0005 27.0979 17.4565 26.1999 18.3545L17.6287 26.9256C16.7307 27.8236 15.2748 27.8236 14.3768 26.9256L5.80566 18.3545Z" fill="currentColor" fill-opacity="0.25"/><path fill-rule="evenodd" clip-rule="evenodd" d="M16.4801 13.9619C16.4801 12.9761 16.7467 12.5436 16.9443 12.3296C17.1764 12.078 17.5731 11.8517 18.2275 11.707C18.8821 11.5623 19.638 11.5342 20.4038 11.5582C20.7804 11.57 21.1341 11.5932 21.4719 11.6156L21.5263 11.6193C21.8195 11.6389 22.1626 11.6618 22.4429 11.6618V7.40825C22.3209 7.40825 22.1219 7.39596 21.7544 7.37149C21.4202 7.34925 20.9976 7.32115 20.5371 7.30672C19.6286 7.27824 18.4672 7.29779 17.3093 7.55377C16.1512 7.8098 14.8404 8.33724 13.8181 9.4452C12.7612 10.5907 12.2266 12.1236 12.2266 13.9619V15.0127H10.6836V19.2662H12.2266V26.6332H16.4801V19.2662H20.3394V15.0127H16.4801V13.9619Z" fill="currentColor"/></svg>post_process_pose_estimation</span></h4><!-- HTML_TAG_END --> <a id="transformers.VitPoseImageProcessor.post_process_pose_estimation" class="header-link invisible with-hover:group-hover:visible pr-2" href="#transformers.VitPoseImageProcessor.post_process_pose_estimation"><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></a> <a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/transformers/blob/vr_33962/src/transformers/models/vitpose/image_processing_vitpose.py#L592" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span class="hidden md:block mx-0.5 hover:!underline" data-svelte-h="svelte-122apf4">source</span> <span data-svelte-h="svelte-x0xyl0">></span></a></span> <p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span data-svelte-h="svelte-8mvn6a">(</span> <span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">outputs<span class="opacity-60">: VitPoseEstimatorOutput</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">boxes<span class="opacity-60">: typing.Union[list[list[list[float]]], numpy.ndarray]</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">kernel_size<span class="opacity-60">: int = 11</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">threshold<span class="opacity-60">: typing.Optional[float] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">target_sizes<span class="opacity-60">: typing.Union[transformers.utils.generic.TensorType, list[tuple]] = None</span></span> </span> <span data-svelte-h="svelte-1jq0pl7">)</span> <span class="font-bold" data-svelte-h="svelte-1j6k10o">→</span> <span class="rounded hover:bg-gray-400 cursor-pointer"><!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script><span><code>list[list[Dict]]</code></span><!-- HTML_TAG_END --></span></p> <div class="!mb-10 relative docstring-details "> <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800" data-svelte-h="svelte-lt6pb6">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p> <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.post_process_pose_estimation.outputs" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.post_process_pose_estimation.outputs"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>outputs</strong> (<code>VitPoseEstimatorOutput</code>) — | |
| VitPoseForPoseEstimation model outputs.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.post_process_pose_estimation.boxes" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.post_process_pose_estimation.boxes"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>boxes</strong> (<code>list[list[list[float]]]</code> or <code>np.ndarray</code>) — | |
| List or array of bounding boxes for each image. Each box should be a list of 4 floats representing the bounding | |
| box coordinates in COCO format (top_left_x, top_left_y, width, height).<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.post_process_pose_estimation.kernel_size" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.post_process_pose_estimation.kernel_size"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>kernel_size</strong> (<code>int</code>, <em>optional</em>, defaults to 11) — | |
| Gaussian kernel size (K) for modulation.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.post_process_pose_estimation.threshold" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.post_process_pose_estimation.threshold"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>threshold</strong> (<code>float</code>, <em>optional</em>, defaults to None) — | |
| Score threshold to keep object detection predictions.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseImageProcessor.post_process_pose_estimation.target_sizes" class="header-link block pr-0.5 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="#transformers.VitPoseImageProcessor.post_process_pose_estimation.target_sizes"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>target_sizes</strong> (<code>torch.Tensor</code> or <code>list[tuple[int, int]]</code>, <em>optional</em>) — | |
| Tensor of shape <code>(batch_size, 2)</code> or list of tuples (<code>tuple[int, int]</code>) containing the target size | |
| <code>(height, width)</code> of each image in the batch. If unset, predictions will be resize with the default value.<!-- HTML_TAG_END --> </span></span> </li></ul> <div id="transformers.VitPoseImageProcessor.post_process_pose_estimation.returns" class="flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800 rounded "><p class="text-base">Returns</p> <!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script> | |
| <p><code>list[list[Dict]]</code></p> | |
| <!-- HTML_TAG_END --> <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700"></span></div> <p class="text-base"><!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script> | |
| <p>A list of dictionaries, each dictionary containing the keypoints and boxes for an image | |
| in the batch as predicted by the model.</p> | |
| <!-- HTML_TAG_END --></p> </div></div> <p data-svelte-h="svelte-1qvlu0g">Transform the heatmaps into keypoint predictions and transform them back to the image.</p></div></div> <h2 class="relative group"><a id="transformers.VitPoseConfig" 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="#transformers.VitPoseConfig"><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>VitPoseConfig</span></h2> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"> <div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="transformers.VitPoseConfig"><!-- HTML_TAG_START --><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">class</span> <span class="font-medium">transformers.</span><span class="font-semibold">VitPoseConfig</span></span></h3><!-- HTML_TAG_END --> <a id="transformers.VitPoseConfig" class="header-link invisible with-hover:group-hover:visible pr-2" href="#transformers.VitPoseConfig"><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></a> <a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/transformers/blob/vr_33962/src/transformers/models/vitpose/configuration_vitpose.py#L28" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span class="hidden md:block mx-0.5 hover:!underline" data-svelte-h="svelte-122apf4">source</span> <span data-svelte-h="svelte-x0xyl0">></span></a></span> <p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span data-svelte-h="svelte-8mvn6a">(</span> <span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">backbone_config<span class="opacity-60">: typing.Optional[transformers.configuration_utils.PreTrainedConfig] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">backbone<span class="opacity-60">: typing.Optional[str] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">use_pretrained_backbone<span class="opacity-60">: bool = False</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">use_timm_backbone<span class="opacity-60">: bool = False</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">backbone_kwargs<span class="opacity-60">: typing.Optional[dict] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">initializer_range<span class="opacity-60">: float = 0.02</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">scale_factor<span class="opacity-60">: int = 4</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">use_simple_decoder<span class="opacity-60">: bool = True</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">**kwargs<span class="opacity-60"></span></span> </span> <span data-svelte-h="svelte-1jq0pl7">)</span> </p> <div class="!mb-10 relative docstring-details "> <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800" data-svelte-h="svelte-lt6pb6">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p> <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseConfig.backbone_config" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.backbone_config"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>backbone_config</strong> (<code>PreTrainedConfig</code> or <code>dict</code>, <em>optional</em>, defaults to <code>VitPoseBackboneConfig()</code>) — | |
| The configuration of the backbone model. Currently, only <code>backbone_config</code> with <code>vitpose_backbone</code> as <code>model_type</code> is supported.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseConfig.backbone" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.backbone"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>backbone</strong> (<code>str</code>, <em>optional</em>) — | |
| Name of backbone to use when <code>backbone_config</code> is <code>None</code>. If <code>use_pretrained_backbone</code> is <code>True</code>, this | |
| will load the corresponding pretrained weights from the timm or transformers library. If <code>use_pretrained_backbone</code> | |
| is <code>False</code>, this loads the backbone’s config and uses that to initialize the backbone with random weights.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseConfig.use_pretrained_backbone" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.use_pretrained_backbone"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>use_pretrained_backbone</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) — | |
| Whether to use pretrained weights for the backbone.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseConfig.use_timm_backbone" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.use_timm_backbone"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>use_timm_backbone</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) — | |
| Whether to load <code>backbone</code> from the timm library. If <code>False</code>, the backbone is loaded from the transformers | |
| library.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseConfig.backbone_kwargs" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.backbone_kwargs"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>backbone_kwargs</strong> (<code>dict</code>, <em>optional</em>) — | |
| Keyword arguments to be passed to AutoBackbone when loading from a checkpoint | |
| e.g. <code>{'out_indices': (0, 1, 2, 3)}</code>. Cannot be specified if <code>backbone_config</code> is set.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseConfig.initializer_range" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.initializer_range"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>initializer_range</strong> (<code>float</code>, <em>optional</em>, defaults to 0.02) — | |
| The standard deviation of the truncated_normal_initializer for initializing all weight matrices.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseConfig.scale_factor" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.scale_factor"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>scale_factor</strong> (<code>int</code>, <em>optional</em>, defaults to 4) — | |
| Factor to upscale the feature maps coming from the ViT backbone.<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseConfig.use_simple_decoder" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.use_simple_decoder"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>use_simple_decoder</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) — | |
| Whether to use a <code>VitPoseSimpleDecoder</code> to decode the feature maps from the backbone into heatmaps. Otherwise it uses <code>VitPoseClassicDecoder</code>.<!-- HTML_TAG_END --> </span></span> </li></ul> </div></div> <p data-svelte-h="svelte-9zej8w">This is the configuration class to store the configuration of a <a href="/docs/transformers/pr_33962/en/model_doc/vitpose#transformers.VitPoseForPoseEstimation">VitPoseForPoseEstimation</a>. It is used to instantiate a | |
| VitPose model according to the specified arguments, defining the model architecture. Instantiating a configuration | |
| with the defaults will yield a similar configuration to that of the VitPose | |
| <a href="https://huggingface.co/usyd-community/vitpose-base-simple" rel="nofollow">usyd-community/vitpose-base-simple</a> architecture.</p> <p data-svelte-h="svelte-1ghu04j">Configuration objects inherit from <a href="/docs/transformers/pr_33962/en/main_classes/configuration#transformers.PreTrainedConfig">PreTrainedConfig</a> and can be used to control the model outputs. Read the | |
| documentation from <a href="/docs/transformers/pr_33962/en/main_classes/configuration#transformers.PreTrainedConfig">PreTrainedConfig</a> for more information.</p> <div class="relative group rounded-md"><a id="transformers.VitPoseConfig.example" class="header-link block pr-0.5 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="#transformers.VitPoseConfig.example"><span><svg class="text-smd" 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> <p data-svelte-h="svelte-11lpom8">Example:</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> VitPoseConfig, VitPoseForPoseEstimation | |
| <span class="hljs-meta">>>> </span><span class="hljs-comment"># Initializing a VitPose configuration</span> | |
| <span class="hljs-meta">>>> </span>configuration = VitPoseConfig() | |
| <span class="hljs-meta">>>> </span><span class="hljs-comment"># Initializing a model (with random weights) from the configuration</span> | |
| <span class="hljs-meta">>>> </span>model = VitPoseForPoseEstimation(configuration) | |
| <span class="hljs-meta">>>> </span><span class="hljs-comment"># Accessing the model configuration</span> | |
| <span class="hljs-meta">>>> </span>configuration = model.config<!-- HTML_TAG_END --></pre></div></div></div> <h2 class="relative group"><a id="transformers.VitPoseForPoseEstimation" 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="#transformers.VitPoseForPoseEstimation"><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>VitPoseForPoseEstimation</span></h2> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"> <div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="transformers.VitPoseForPoseEstimation"><!-- HTML_TAG_START --><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">class</span> <span class="font-medium">transformers.</span><span class="font-semibold">VitPoseForPoseEstimation</span></span></h3><!-- HTML_TAG_END --> <a id="transformers.VitPoseForPoseEstimation" class="header-link invisible with-hover:group-hover:visible pr-2" href="#transformers.VitPoseForPoseEstimation"><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></a> <a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/transformers/blob/vr_33962/src/transformers/models/vitpose/modeling_vitpose.py#L193" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span class="hidden md:block mx-0.5 hover:!underline" data-svelte-h="svelte-122apf4">source</span> <span data-svelte-h="svelte-x0xyl0">></span></a></span> <p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span data-svelte-h="svelte-8mvn6a">(</span> <span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">config<span class="opacity-60">: VitPoseConfig</span></span> </span> <span data-svelte-h="svelte-1jq0pl7">)</span> </p> <div class="!mb-10 relative docstring-details "> <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800" data-svelte-h="svelte-lt6pb6">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p> <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseForPoseEstimation.config" class="header-link block pr-0.5 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="#transformers.VitPoseForPoseEstimation.config"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>config</strong> (<a href="/docs/transformers/pr_33962/en/model_doc/vitpose#transformers.VitPoseConfig">VitPoseConfig</a>) — | |
| Model configuration class with all the parameters of the model. Initializing with a config file does not | |
| load the weights associated with the model, only the configuration. Check out the | |
| <a href="/docs/transformers/pr_33962/en/main_classes/model#transformers.PreTrainedModel.from_pretrained">from_pretrained()</a> method to load the model weights.<!-- HTML_TAG_END --> </span></span> </li></ul> </div></div> <p data-svelte-h="svelte-er1y03">The VitPose model with a pose estimation head on top.</p> <p data-svelte-h="svelte-1kqcut9">This model inherits from <a href="/docs/transformers/pr_33962/en/main_classes/model#transformers.PreTrainedModel">PreTrainedModel</a>. Check the superclass documentation for the generic methods the | |
| library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads | |
| etc.)</p> <p data-svelte-h="svelte-hswkmf">This model is also a PyTorch <a href="https://pytorch.org/docs/stable/nn.html#torch.nn.Module" rel="nofollow">torch.nn.Module</a> subclass. | |
| Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage | |
| and behavior.</p> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"> <div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="transformers.VitPoseForPoseEstimation.forward"><!-- HTML_TAG_START --><h4 class="!m-0"><span class="flex-1 rounded-xl py-0.5 break-all bg-gradient-to-r from-blue-50/60 to-white dark:from-gray-900 dark:to-gray-950 text-blue-700 dark:text-blue-300 font-medium px-2"><svg width="1em" height="1em" viewBox="0 0 32 33" class="mr-1 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg"><path d="M5.80566 18.3545C4.90766 17.4565 4.90766 16.0005 5.80566 15.1025L14.3768 6.53142C15.2748 5.63342 16.7307 5.63342 17.6287 6.53142L26.1999 15.1025C27.0979 16.0005 27.0979 17.4565 26.1999 18.3545L17.6287 26.9256C16.7307 27.8236 15.2748 27.8236 14.3768 26.9256L5.80566 18.3545Z" fill="currentColor" fill-opacity="0.25"/><path fill-rule="evenodd" clip-rule="evenodd" d="M16.4801 13.9619C16.4801 12.9761 16.7467 12.5436 16.9443 12.3296C17.1764 12.078 17.5731 11.8517 18.2275 11.707C18.8821 11.5623 19.638 11.5342 20.4038 11.5582C20.7804 11.57 21.1341 11.5932 21.4719 11.6156L21.5263 11.6193C21.8195 11.6389 22.1626 11.6618 22.4429 11.6618V7.40825C22.3209 7.40825 22.1219 7.39596 21.7544 7.37149C21.4202 7.34925 20.9976 7.32115 20.5371 7.30672C19.6286 7.27824 18.4672 7.29779 17.3093 7.55377C16.1512 7.8098 14.8404 8.33724 13.8181 9.4452C12.7612 10.5907 12.2266 12.1236 12.2266 13.9619V15.0127H10.6836V19.2662H12.2266V26.6332H16.4801V19.2662H20.3394V15.0127H16.4801V13.9619Z" fill="currentColor"/></svg>forward</span></h4><!-- HTML_TAG_END --> <a id="transformers.VitPoseForPoseEstimation.forward" class="header-link invisible with-hover:group-hover:visible pr-2" href="#transformers.VitPoseForPoseEstimation.forward"><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></a> <a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/transformers/blob/vr_33962/src/transformers/models/vitpose/modeling_vitpose.py#L212" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span class="hidden md:block mx-0.5 hover:!underline" data-svelte-h="svelte-122apf4">source</span> <span data-svelte-h="svelte-x0xyl0">></span></a></span> <p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span data-svelte-h="svelte-8mvn6a">(</span> <span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">pixel_values<span class="opacity-60">: Tensor</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">dataset_index<span class="opacity-60">: typing.Optional[torch.Tensor] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">flip_pairs<span class="opacity-60">: typing.Optional[torch.Tensor] = None</span></span> </span><span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">labels<span class="opacity-60">: typing.Optional[torch.Tensor] = None</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">**kwargs<span class="opacity-60">: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]</span></span> </span> <span data-svelte-h="svelte-1jq0pl7">)</span> <span class="font-bold" data-svelte-h="svelte-1j6k10o">→</span> <span class="rounded hover:bg-gray-400 cursor-pointer"><!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script><span><code>transformers.models.vitpose.modeling_vitpose.VitPoseEstimatorOutput</code> or <code>tuple(torch.FloatTensor)</code></span><!-- HTML_TAG_END --></span></p> <div class="!mb-10 relative docstring-details "> <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800" data-svelte-h="svelte-lt6pb6">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p> <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseForPoseEstimation.forward.pixel_values" class="header-link block pr-0.5 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="#transformers.VitPoseForPoseEstimation.forward.pixel_values"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>pixel_values</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, num_channels, image_size, image_size)</code>) — | |
| The tensors corresponding to the input images. Pixel values can be obtained using | |
| <code>image_processor_class</code>. See <code>image_processor_class.__call__</code> for details (<code>processor_class</code> uses | |
| <code>image_processor_class</code> for processing images).<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseForPoseEstimation.forward.dataset_index" class="header-link block pr-0.5 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="#transformers.VitPoseForPoseEstimation.forward.dataset_index"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>dataset_index</strong> (<code>torch.Tensor</code> of shape <code>(batch_size,)</code>) — | |
| Index to use in the Mixture-of-Experts (MoE) blocks of the backbone.</p> | |
| <p>This corresponds to the dataset index used during training, e.g. For the single dataset index 0 refers to the corresponding dataset. For the multiple datasets index 0 refers to dataset A (e.g. MPII) and index 1 refers to dataset B (e.g. CrowdPose).<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseForPoseEstimation.forward.flip_pairs" class="header-link block pr-0.5 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="#transformers.VitPoseForPoseEstimation.forward.flip_pairs"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>flip_pairs</strong> (<code>torch.tensor</code>, <em>optional</em>) — | |
| Whether to mirror pairs of keypoints (for example, left ear — right ear).<!-- HTML_TAG_END --> </span></span> </li><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="transformers.VitPoseForPoseEstimation.forward.labels" class="header-link block pr-0.5 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="#transformers.VitPoseForPoseEstimation.forward.labels"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>labels</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, sequence_length)</code>, <em>optional</em>) — | |
| Labels for computing the masked language modeling loss. Indices should either be in <code>[0, ..., config.vocab_size]</code> or -100 (see <code>input_ids</code> docstring). Tokens with indices set to <code>-100</code> are ignored | |
| (masked), the loss is only computed for the tokens with labels in <code>[0, ..., config.vocab_size]</code>.<!-- HTML_TAG_END --> </span></span> </li></ul> <div id="transformers.VitPoseForPoseEstimation.forward.returns" class="flex items-center font-semibold space-x-3 text-base !mt-0 !mb-0 text-gray-800 rounded "><p class="text-base">Returns</p> <!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script> | |
| <p><code>transformers.models.vitpose.modeling_vitpose.VitPoseEstimatorOutput</code> or <code>tuple(torch.FloatTensor)</code></p> | |
| <!-- HTML_TAG_END --> <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700"></span></div> <p class="text-base"><!-- HTML_TAG_START --><script context="module">export const metadata = 'undefined';</script> | |
| <p>A <code>transformers.models.vitpose.modeling_vitpose.VitPoseEstimatorOutput</code> or a tuple of | |
| <code>torch.FloatTensor</code> (if <code>return_dict=False</code> is passed or when <code>config.return_dict=False</code>) comprising various | |
| elements depending on the configuration (<a | |
| href="/docs/transformers/pr_33962/en/model_doc/vitpose#transformers.VitPoseConfig" | |
| >VitPoseConfig</a>) and inputs.</p> | |
| <ul> | |
| <li> | |
| <p><strong>loss</strong> (<code>torch.FloatTensor</code> of shape <code>(1,)</code>, <em>optional</em>, returned when <code>labels</code> is provided) — Loss is not supported at this moment. See <a | |
| href="https://github.com/ViTAE-Transformer/ViTPose/tree/main/mmpose/models/losses" | |
| rel="nofollow" | |
| >https://github.com/ViTAE-Transformer/ViTPose/tree/main/mmpose/models/losses</a> for further detail.</p> | |
| </li> | |
| <li> | |
| <p><strong>heatmaps</strong> (<code>torch.FloatTensor</code> of shape <code>(batch_size, num_keypoints, height, width)</code>) — Heatmaps as predicted by the model.</p> | |
| </li> | |
| <li> | |
| <p><strong>hidden_states</strong> (<code>tuple(torch.FloatTensor)</code>, <em>optional</em>, returned when <code>output_hidden_states=True</code> is passed or when <code>config.output_hidden_states=True</code>) — Tuple of <code>torch.FloatTensor</code> (one for the output of the embeddings, if the model has an embedding layer, + | |
| one for the output of each stage) of shape <code>(batch_size, sequence_length, hidden_size)</code>. Hidden-states | |
| (also called feature maps) of the model at the output of each stage.</p> | |
| </li> | |
| <li> | |
| <p><strong>attentions</strong> (<code>tuple[torch.FloatTensor, ...]</code>, <em>optional</em>, returned when <code>output_attentions=True</code> is passed or when <code>config.output_attentions=True</code>) — Tuple of <code>torch.FloatTensor</code> (one for each layer) of shape <code>(batch_size, num_heads, sequence_length, sequence_length)</code>.</p> | |
| <p>Attentions weights after the attention softmax, used to compute the weighted average in the self-attention | |
| heads.</p> | |
| </li> | |
| </ul> | |
| <!-- HTML_TAG_END --></p> </div></div> <p data-svelte-h="svelte-e57umw">The <a href="/docs/transformers/pr_33962/en/model_doc/vitpose#transformers.VitPoseForPoseEstimation">VitPoseForPoseEstimation</a> forward method, overrides the <code>__call__</code> special method.</p> <blockquote class="tip"><p data-svelte-h="svelte-fincs2">Although the recipe for forward pass needs to be defined within this function, one should call the <code>Module</code> | |
| instance afterwards instead of this since the former takes care of running the pre and post processing steps while | |
| the latter silently ignores them.</p></blockquote> <div class="relative group rounded-md"><a id="transformers.VitPoseForPoseEstimation.forward.example" class="header-link block pr-0.5 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="#transformers.VitPoseForPoseEstimation.forward.example"><span><svg class="text-smd" 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> <p data-svelte-h="svelte-kvfsh7">Examples:</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> AutoImageProcessor, VitPoseForPoseEstimation | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch | |
| <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>processor = AutoImageProcessor.from_pretrained(<span class="hljs-string">"usyd-community/vitpose-base-simple"</span>) | |
| <span class="hljs-meta">>>> </span>model = VitPoseForPoseEstimation.from_pretrained(<span class="hljs-string">"usyd-community/vitpose-base-simple"</span>) | |
| <span class="hljs-meta">>>> </span>url = <span class="hljs-string">"http://images.cocodataset.org/val2017/000000039769.jpg"</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>boxes = [[[<span class="hljs-number">412.8</span>, <span class="hljs-number">157.61</span>, <span class="hljs-number">53.05</span>, <span class="hljs-number">138.01</span>], [<span class="hljs-number">384.43</span>, <span class="hljs-number">172.21</span>, <span class="hljs-number">15.12</span>, <span class="hljs-number">35.74</span>]]] | |
| <span class="hljs-meta">>>> </span>inputs = processor(image, boxes=boxes, return_tensors=<span class="hljs-string">"pt"</span>) | |
| <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>heatmaps = outputs.heatmaps<!-- HTML_TAG_END --></pre></div></div></div></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/model_doc/vitpose.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_1yuubte = { | |
| assets: "/docs/transformers/pr_33962/en", | |
| base: "/docs/transformers/pr_33962/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/pr_33962/en/_app/immutable/entry/start.1776ac26.js"), | |
| import("/docs/transformers/pr_33962/en/_app/immutable/entry/app.d2b9a7d8.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 463], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 140 kB
- Xet hash:
- d8d3e73d9812da04cf5d43dd5acdcb37dc224e49af65a540cab07d1f986984ad
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.