8*MLP was trained during finetune

HideUnderBush / UI2I_via_StyleGAN2

Unsupervised image-to-image translation method via pre-trained StyleGAN2 network

Other

222 stars 30 forks source link

8*MLP was trained during finetune #3

Open cnnlstm opened 3 years ago

cnnlstm commented 3 years ago

Thanks for your excellent work, but it seems that when finetuning the model on a new domain data, the mapping net(8mlp) was not frozen, which conflicts with your papers, though requires_grad==False was set in L422-425 of train.py. The gradient is activated in L229 again and the G_optimizer optimize all parameters of G. When I print the parameters of 8MLP on the original model and finetuned, they indeed different.

HideUnderBush commented 3 years ago

Thanks for pointing it out, there might be some missing lines when migrating the code from server to public repo. We'll look into it and update code soon.