Closed jakesokol1 closed 4 years ago
I believe this yields expected behavior (if it is actually desired that only the first epoch have learning rate of .01).
for epoch in range(args.start_epoch, args.epochs):
if epoch == 1:
for param_group in optimizer.param_groups:
param_group['lr'] *= 10
`
I am trying to train resnet110. After the first epoch, the learning rate does not return to .1, and it stays at .01. I believe this is not intended.