← Lab
kpflip
confirmedupstream bugPython · torchvisionSystems & data structuresJuly 25, 2026
the question
Do torchvision transforms.v2 flip keypoints about the same frame as boxes, affine, and rotate?
what came out
torchvision's `transforms.v2` flips keypoints about `W-1`/`H-1` while boxes flip about `W`/`H` and affine/rotate reflect about the continuous centre. So a hflipped keypoint lands one pixel off its content and off its box corner, and `rotate(180)` != `hflip` then `vflip` for keypoints (holds for boxes). Fix: reflect about `W` and `H`.
method & receipts
- Result: confirmed
- Reproducible — one script re-runs the whole thing from scratch.
- Tested — a correctness/benchmark suite ships alongside the code.
→ read the code and re-run it
github.com/v-code01/kpflip