oneformer_cityscapes_swin_large
OneFormer model trained on the Cityscapes dataset (large-sized version, Swin backbone). It was introduced in the paper OneFormer: One Transformer to Rule Universal Image Segmentation by Jain et al. and first released in this repository.
Params
—
Context
—
Downloads 30d
184 K
Likes
2
Download history
tracking started — chart appears after 7 days of snapshots (1 recorded)184 K downloads in the last 30 days
Specifications
- Architecture
- OneFormerForUniversalSegmentation
- Layers / heads
- 10 / 8
- Licence
- mit
- First seen on the Hub
- 2022-11-15
- Training datasets
- huggan/cityscapes
- Added to our catalog
- 2026-10-24
Compare with any image-segmentation model