Megvii-BaseDetection / Megvii-BaseDetection/YOLOX
The formula of the annotations coordinates after the image is flipped seems to be problematic
Open
@FateScript is already working on this.
Since Jan 7, 2022.
check
- Dominant language
- Python
- Stars
- 10.6k
- Forks
- 2.5k
- PR merge metrics
- No merged PRs in 30d
Description
I found through experiments that the boxes calculated in this way cannot match the flipped image. I think the correct code should be:
if FLIP:
cp_bboxes_origin_np[:, 0] = (
origin_w - cp_bboxes_origin_np[:, 0] - cp_bboxes_origin_np[:, 2]
)
@FateScript
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.