Sapiens Pose 1b Bfloat16

🚀 Pose-Sapiens-1B-Bfloat16

Sapiens is a family of vision transformers, and this model can estimate 308 keypoints on a single image.

✨ Features

Sapiens is a family of vision transformers pretrained on 300 million human images at 1024 x 1024 image resolution. The pretrained models, when finetuned for human-centric vision tasks, generalize to in-the-wild conditions. Sapiens-1B natively support 1K high-resolution inference. The resulting models exhibit remarkable generalization to in-the-wild data, even when labeled data is scarce or entirely synthetic.

📚 Documentation

Model Details

• Developed by: Meta
• Model type: Vision Transformer
• License: Creative Commons Attribution-NonCommercial 4.0
• Task: pose
• Format: bfloat16
• File: sapiens_1b_goliath_best_goliath_AP_639_bfloat16.pt2

Model Card

More Resources

• Repository: https://github.com/facebookresearch/sapiens
• Paper: https://arxiv.org/abs/2408.12569
• Demo: https://huggingface.co/spaces/facebook/sapiens-pose
• Project Page: https://about.meta.com/realitylabs/codecavatars/sapiens
• Additional Results: https://rawalkhirodkar.github.io/sapiens
• HuggingFace Collection: https://huggingface.co/collections/facebook/sapiens-66d22047daa6402d565cb2fc

📄 License

This model is licensed under the Creative Commons Attribution-NonCommercial 4.0 license.

💻 Usage Examples

Basic Usage

The Pose 1B model can be used for estimate 308 keypoints (body + face + hands + feet) on a single image.

# Note: No specific code example was provided in the original README.
# You may need to add actual code here according to the real usage.