Image Feature Extraction
sapiens
English
Edit model card

Pretrain-Sapiens-2B

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-2B 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: original
  • File: sapiens_2b_epoch_660_clean.pth

Model Card

  • Image Size: 1024 x 1024
  • Num Parameters: 2.163 B
  • FLOPs: 8.709 TFLOPs
  • Patch Size: 16 x 16
  • Embedding Dimensions: 1920
  • Num Layers: 48
  • Num Heads: 32
  • Feedforward Channels: 7680

More Resources

Uses

Pretrained 2B model can be used for feature extraction, fine-tuning, or as a starting point for training new models.

Downloads last month
77
Inference API
Inference API (serverless) does not yet support sapiens models for this pipeline type.

Collection including facebook/sapiens-pretrain-2b