Dawn90 issues

Repositories
Issues
Comments

Results 2 issues of


                                            Dawn90

Why the rec_loss returned from function train_main_network() is divided by args.batch_size in main.py?

1. Why the rec_loss returned from function train_main_network() is divided by args.batch_size in main.py? As we know, nn.MSELoss() already returns the mean loss by default. `line 183: return sim_loss.data/args.batch_size, rec_loss.data/args.batch_size`...

Why use class AdamW instead of "torch.optim.adamw "

Hi, Thanks a lot for sharing the pytorch version of GAIN!! I'm trying to run the code and make some changes based on GAIN. I was wondering why you define...