Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

yangjiange
/

STP

Feature Extraction

robot-manipulation

self-supervised

masked-autoencoder

egocentric-video

visual-representation

Model card Files Files and versions

STP / util

17 kB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

yangjiange's picture

Sync util/

9bbc822 verified 2 days ago

__init__.py

0 Bytes
Add STP ViT-B/16 pre-trained weights (slim: model only + decoder-free encoder) 2 days ago
ckpt_io.py

2.13 kB
Add STP ViT-B/16 pre-trained weights (slim: model only + decoder-free encoder) 2 days ago
lr_sched.py

921 Bytes
Add STP ViT-B/16 pre-trained weights (slim: model only + decoder-free encoder) 2 days ago
misc.py

11.2 kB
Sync util/ 2 days ago
pos_embed.py

1.91 kB
Add STP ViT-B/16 pre-trained weights (slim: model only + decoder-free encoder) 2 days ago
torch_six_compat.py

835 Bytes
Add STP ViT-B/16 pre-trained weights (slim: model only + decoder-free encoder) 2 days ago