HRNet-Facial-Landmark-Detection icon indicating copy to clipboard operation
HRNet-Facial-Landmark-Detection copied to clipboard

Published 20 hours ago • verified publisher icon HRNet

Question about flipping data.

Open hao-qiang opened this issue 5 years ago • 2 comments

https://github.com/HRNet/HRNet-Facial-Landmark-Detection/blob/81ae5410222b870b466895de50b43b96c19efbcf/lib/utils/transforms.py#L40

For instance, when flipping (0, 0) point in 3x3 image, the result should be (3-1-0, 0). So I think x[:, 0] = width -1 - x[:, 0] maybe better. Is that right? Thx.

hao-qiang avatar Dec 02 '19 03:12 hao-qiang

rigth

738654805 avatar Jan 07 '20 11:01 738654805

I found I make a mistake, x[:, 0] = width - x[:, 0] is right.

hao-qiang avatar Jan 15 '20 01:01 hao-qiang