Sapiens Seg 0.6b Bfloat16

🚀 Seg-Sapiens-0.6B-Bfloat16

Seg-Sapiens-0.6B-Bfloat16 is a vision transformer model for human image segmentation, offering high - resolution inference and strong generalization ability.

🚀 Quick Start

This model is designed for human image segmentation tasks. With its pre - training on a large number of human images, it can effectively perform 28 - class body part segmentation on human images.

✨ Features

• High - Resolution Inference: Sapiens - 0.6B natively supports 1K high - resolution inference.
• Strong Generalization: The model shows remarkable generalization to in - the - wild data, even with scarce labeled data or entirely synthetic data.
• Human - Centric: Pretrained on 300 million human images at 1024 x 1024 image resolution, it is well - suited for human - centric vision tasks.

📚 Documentation

Model Details

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.

• Developed by: Meta
• Model type: Vision Transformer
• License: Creative Commons Attribution - NonCommercial 4.0
• Task: seg
• Format: bfloat16
• File: sapiens_0.6b_goliath_best_goliath_mIoU_7777_epoch_178_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-seg
• 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

💻 Usage Examples

Seg 0.6B model can be used to perform 28 class body part segmentation on human images.

📄 License

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