ByteDance-Seed / ByteDance-Seed/Depth-Anything-3
about get_intermediate_layers func
Open
- Dominant language
- Python
- Stars
- 6.3k
- Forks
- 702
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/ByteDance-Seed/Depth-Anything-3/blob/6b572120b32211a2596c99cab8a7b0996cc39dae/src/depth_anything_3/model/dinov2/vision_transformer.py#L388
I'd like to ask why only the latter half of the dimensions are normalized here?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.