Mask Alignment

[diamond0910]

Hi, I use the face parsing model (https://github.com/switchablenorms/CelebAMask-HQ/tree/master/face_parsing) to test the mask accuracy. I get the 512x512 mask result for the first 50 testing images and calculate the accuracy 0.46 for your pretrained model. Can you give me some advice？

[ziqihuangg]

Hi, could you provide more details regarding your implementation? For example, which network did you use for inference (mask-to-face? or collaborating text-to-face and mask to face?)