Train Error
Closed this issue · 4 comments
LuluW8071 commented
LuluW8071 commented
Optimizer param error
LuluW8071 commented
GPU warn is solved
LuluW8071 commented
LuluW8071 commented
If Train Epoch exits due to less GPU memory
decrease batch_size to 32
parser.add_argument('--batch_size', default=64, type=int, help='size of batch')
Also, if train.json and test.json are too less
REPLACE
val_check_interval=args.valid_every
WITH
val_check_interval=10