Closed seekFire closed 3 years ago
I think you may aim to preserve the groundtruth coordinates available after carrying on one pixel shifting of flip testing. Is it right?
@seekFire You may need to ask the author of HRNet https://github.com/leoxiaobin/deep-high-resolution-net.pytorch/
In evaluate.py, function calc_dists, the Euclidean distance will be calculated under the condition:
if target[n, c, 0] > 1 and target[n, c, 1] > 1:
It seems that you exclude the case where the target coordinates are in [0, 1], so why do this?