Closed dwy6626 closed 3 years ago
As title, I am looking at your code and find the centor of an image is shifted by 0.12 times of the face width:
centor
# api.py center = torch.FloatTensor( [d[2] - (d[2] - d[0]) / 2.0, d[3] - (d[3] - d[1]) / 2.0]) center[1] = center[1] - (d[3] - d[1]) * 0.12
Could someone tell me what does this means, thanks.
Apologies for the delay. If its still relevant, that was simply used due to a shift present in the original data vs the detected bounding box.
As title, I am looking at your code and find the
centor
of an image is shifted by 0.12 times of the face width:Could someone tell me what does this means, thanks.