search

jhb86253817 / PIPNet

Efficient facial landmark detector
MIT License
412 stars 82 forks source link

About test Image #9

Closed xuedue closed 3 years ago

xuedue commented 3 years ago

Hello, author, thanks for your sharing.

Can this network used to test CelebA-HQ-img? I want found a network to calculate landmark loss in CelebA-HQ-img, but after I seen your code, I don't konw how to test in CelebA-HQ-img.

jhb86253817 commented 3 years ago

Hi, can you run demo.py successfully? Please try modifying demo.py, which is used to predict landmarks for a given image. If the test image is already cropped, you can remove the codes related to face detection (line 80 to 101) and remove the for loop. Make sure the image is resized to 256.