timm / vit_base_patch16_224.dino
Vision86M368.6K6Updated Jan 21, 2025
Downloads
368.6K
Likes
6
Last updated
Jan 21, 2025
License
apache-2.0
A Vision Transformer (ViT) image feature model. Trained with Self-Supervised DINO method.
Tasks & library
- image feature extraction
- timm
Tags
- timm
- pytorch
- image-feature-extraction
- transformers
Technical specifications
Parameters86M
Librarytimm
LanguagesNot available
Licenseapache-2.0