What is the intended learning rate schedule?

[ChanghwaPark]

imbalanced-semi-self/utils.py

Lines 28 to 39 in 16d8f02

	def adjust_learning_rate(optimizer, epoch, args):
	epoch = epoch + 1
	if epoch <= 5:
	lr = args.lr * epoch / 5
	elif epoch > 160:
	lr = args.lr * 0.01
	elif epoch > 180:
	lr = args.lr * 0.0001
	else:
	lr = args.lr
	for param_group in optimizer.param_groups:
	param_group['lr'] = lr

Hi, thanks for sharing your code!

I have a question about the referenced code above.
In the 'adjust_learning_rate' function, the lines 34 and 35 will never be passed.
Can I ask the learning rate schedule that you used for experiments in the paper?

According to the 'adjust_learning_rate' function, the learning rate may change as follows.

epoch lr
0: args.lr * 1 / 5
1: args.lr * 2 / 5
2: args.lr * 3 / 5
3: args.lr * 4 / 5
4: args.lr * 5 / 5
5 ~ 160: args.lr
161~: args.lr * 0.01

[YyzHarry]

Hi - thanks for your interests! This should be a typo when I cleaned up the code (have updated it). For experiments on CIFAR/SVHN, the lr decay is by 0.01 at both the 160th and the 180th epoch.