metadata

language: en
license: cc-by-nc-4.0

Pretrain-Sapiens-0.6B-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-0.6B 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_0.6b_epoch_1600_torchscript.pt2

Model Card

Embedding Dimensions: 1280
Num Layers: 32
Num Heads: 16
Feedforward Channels: 5120
Num Parameters: 0.6B
Input Image Size: 1024 x 1024
Patch Size: 16 x 16

Model Sources

Repository: https://github.com/facebookresearch/sapiens
Paper: https://arxiv.org/abs/2408.12569

Uses

Pretrained 0.6B model can be used for feature extraction, fine-tuning, or as a starting point for training new models.