forked from Rowl1ng/implicit-hyper-opt
-
Notifications
You must be signed in to change notification settings - Fork 1
Open
Description
Run train_augment_experiment.py in resnet_cifar10_train branch. Then you might get Cuda out of memory error. You can change the setting by changing the config variable. And If you don't want to use wandb module, you can set 'use_wanb' as False. To use it, you have to make your ID on the wandb site.
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels