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

Results without pre-training

Open D-X-Y opened this issue 5 years ago • 0 comments

Hi, thanks for this awesome repo. I noticed that all models use imagenet pre-trained initialization. I am wondering, would you mind to provide results without imagenet pre-training.

D-X-Y avatar Dec 08 '19 03:12 D-X-Y