search

FacePerceiver / FaRL

FaRL for Facial Representation Learning [Official, CVPR 2022]
https://arxiv.org/abs/2112.03109
MIT License
375 stars 22 forks source link

Question about input size #7

Closed hedjazi closed 2 years ago

hedjazi commented 2 years ago

Hi, thank you very much for this great work. I see that the input to the CLIP model is of size 224x224, however the parsing and the alignment models' input is 448x448, would you please clarify this? thank you.

yinglinzheng commented 2 years ago

Please check our paper for more details, section 4.4. 图片

hedjazi commented 2 years ago

@yinglinzheng Thank you, I am sorry I should have read the paper first.