README.md

---
language: en
license: cc-by-nc-4.0
pipeline_tag: image-feature-extraction
tags:
- sapiens
---

# Pretrain-Sapiens-0.3B-Torchscript

### 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.
Sapiens-0.3B 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.

- **Developed by:** Meta
- **Model type:** Vision Transformer
- **License:** Creative Commons Attribution-NonCommercial 4.0
- **Task:** pretrain
- **Format:** torchscript
- **File:** sapiens_0.3b_epoch_1600_torchscript.pt2

### Model Card
- **Image Size:** 1024 x 1024
- **Num Parameters:** 0.336 B
- **FLOPs:** 1.242 TFLOPs
- **Patch Size:** 16 x 16
- **Embedding Dimensions:** 1024
- **Num Layers:** 24
- **Num Heads:** 16
- **Feedforward Channels:** 4096

### More Resources
- **Repository:** [https://github.com/facebookresearch/sapiens](https://github.com/facebookresearch/sapiens)
- **Paper:** [https://arxiv.org/abs/2408.12569](https://arxiv.org/abs/2408.12569)
- **Demos:** [Sapiens Gradio Spaces](https://huggingface.co/collections/facebook/sapiens-66d22047daa6402d565cb2fc)
- **Project Page:** [https://about.meta.com/realitylabs/codecavatars/sapiens](https://about.meta.com/realitylabs/codecavatars/sapiens/)
- **Additional Results:** [https://rawalkhirodkar.github.io/sapiens](https://rawalkhirodkar.github.io/sapiens/)
- **HuggingFace Collection:** [https://huggingface.co/collections/facebook/sapiens-66d22047daa6402d565cb2fc](https://huggingface.co/collections/facebook/sapiens-66d22047daa6402d565cb2fc)

## Uses
Pretrained 0.3B model can be used for feature extraction, fine-tuning, or as a starting point for training new models.