search

JDAI-CV / FaceX-Zoo

A PyTorch Toolbox for Face Recognition
https://arxiv.org/pdf/2101.04407.pdf
Other
1.89k stars 433 forks source link

What is pretrained-model? #11

Open buimanhlinh96 opened 3 years ago

buimanhlinh96 commented 3 years ago

Hi @wang21jun , Thanks for your contributor! In your submit at https://github.com/JDAI-CV/FaceX-Zoo/tree/main/training_mode, i see you had two kind models: SOTA backbones model and SOTA heads model. What is the difference between them? Thank you!!

wang21jun commented 3 years ago

SOTA backbones model : models which are trained by the SOTA backbones with the same head, i.e. MV-Softmax. SOTA heads model : models which are trained by the SOTA heads with the same backbone, i.e. MobileFaceNet.

buimanhlinh96 commented 3 years ago

@wang21jun I got it! Thank you for your clear answer.

buimanhlinh96 commented 3 years ago

If I just want to train head, not re-train the backbone in my custom dataset. How can i solve it?

vietth-bka commented 3 years ago

If I just want to train head, not re-train the backbone in my custom dataset. How can i solve it?

You can search keyword freezing backbone pytorch. Specifically, you can set requires_grad = False for the whole learnable parameters of the backbone. But the easiest way is just putting the parameters of head into the optimizer but not the params of backbone.

buimanhlinh96 commented 3 years ago

@vietth-bka thank you!