You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For resume training, you might add --continue_train --epoch_count N, where N is the current epoch of the pretrained model. continue_train will load your latest checkpoint from the checkpoint path.
So I guess you can try: python3 train.py --dataroot ./datasets/NIR2RGB --name NIR2RGB_DCL --continue_train --epoch_count N
Hello Junlin,
Thank you very much for your code!
I was just wondering, what is the command to resume training from a checkpoint?
I tried this one, but it didn't work out:
python3 train.py --dataroot ./datasets/NIR2RGB --name NIR2RGB_DCL --pretrained_name NIR2RGB_DCL
Thank you.
The text was updated successfully, but these errors were encountered: