Skip to content

Release v0.9.8
Compare
Choose a tag to compare
@rwightman rwightman released this 21 Oct 20:52
· 346 commits to main since this release
v0.9.8
9afe0bb

Oct 20, 2023

  • SigLIP image tower weights supported in vision_transformer.py.
    • Great potential for fine-tune and downstream feature use.
  • Experimental 'register' support in vit models as per Vision Transformers Need Registers
  • Updated RepViT with new weight release. Thanks wangao
  • Add patch resizing support (on pretrained weight load) to Swin models
  • 0.9.8 release
Assets 2
Loading