# vitpose-base-torch Vision Transformer for pose estimation with 90M parameters using standard ViT backbone. Detects 17 human keypoints through heatmap regression achieving 75.8 AP on COCO. Processes 256x192 images with hierarchical features for accurate joint localization.. **Details** - Model name: `vitpose-base-torch` - Model source: [https://github.com/ViTAE-Transformer/ViTPose](https://github.com/ViTAE-Transformer/ViTPose) - Model author: Yufei Xu, et al. - Model license: Apache 2.0 - Model size: 343.33 MB - Exposes embeddings? no - Tags: `keypoints, coco, torch, transformers, pose-estimation, official` **Requirements** - Packages: `torch, torchvision, transformers` - CPU support - yes - GPU support - yes **Example usage** ```python import fiftyone as fo import fiftyone.zoo as foz dataset = foz.load_zoo_dataset( "coco-2017", split="validation", dataset_name=fo.get_default_dataset_name(), max_samples=50, shuffle=True, ) model = foz.load_zoo_model("vitpose-base-torch") dataset.apply_model(model, prompt_field="ground_truth", label_field="predictions") session = fo.launch_app(dataset) ```