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

How to use trianed model in facer? #5

Open Erfun76 opened 2 years ago

Erfun76 commented 2 years ago

hi, thanks for your work, We trained your model on our own dataset which contains lapa dataset and new images including wearing mask. after train we got checkpoints like these in blob/states/farl/face_parsing.train_lapa_farl-b-ep64_448_refinebb directory: 2.5G 10902_2.pth 2.5G 21804_4.pth 2.5G 32706_6.pth 2.5G 43608_8.pth 2.5G 54510_10.pth 2.5G 65412_12.pth 2.5G 76314_14.pth 2.5G 87216_16.pth 4.0K _records.pth which everyone contains model weights, optimizer and etc.

the problem is how to use these weight in facer project? i checked facer loading proccess and it use torchscript model.

Bai426 commented 1 year ago

Have you solved it and been able to use your own trained models?

YiangAhead commented 9 months ago

Hello, i met the same problem, have you guys solved it? I do not know how to use my trained model to infer new images.