TorchVision 0.28 is out with some small enhancement and bug-fixes:
Enhancements
- [transforms] Let wrap() preserve metadata for custom TVTensor subclasses (#9490)
- [transforms] Allow strings for interpolation param in resize transforms (#9461)
Bug fixes
- [transforms] Fix
F.resizeontv_tensors.Maskto honorNEAREST_EXACTinterpolation. Previously theinterpolationargument was ignored for mask inputs (resize_maskhardcodedNEAREST), soNEAREST_EXACTsilently produced plainNEARESToutput (#9497) - [io] Fix a GIF decoder bug on malformed GIFs that could write outside the allocated tensor's memory (#9520)
Contributors
🎉 We're grateful for our community, which helps us improve Torchvision by submitting issues and PRs, and providing feedback and suggestions. The following persons have contributed patches for this release:
Andrey Talman, Benson Ma, Jason Fried, Joanne Yun, Nicolas Hug