# vitpose-base-simple-torch Simplified ViTPose with 90M parameters removing complex decoder components. Maintains 75.1 AP through direct heatmap prediction from transformer features. Streamlined architecture for easier deployment while preserving accuracy on human pose tasks.. **Details** - Model name: `vitpose-base-simple-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: 327.75 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-simple-torch") dataset.apply_model(model, prompt_field="ground_truth", label_field="predictions") session = fo.launch_app(dataset) ```