Lottery-Ticket-Hypothesis-in-Pytorch icon indicating copy to clipboard operation
Lottery-Ticket-Hypothesis-in-Pytorch copied to clipboard

Published 20 hours ago • verified publisher icon rahulvigneswaran

Every dataset is normalized with MNIST's mean and std dev

Open npnbpb opened this issue 4 years ago • 1 comments
trafficstars

The transform used while loading every dataset (line 37, main.py) uses MNIST's mean and standard deviation. The correct values for normalizing CIFAR 10, etc are different.

npnbpb avatar Dec 01 '20 20:12 npnbpb

For cifar10 & cifar100: normalize = transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])

bainro avatar Dec 25 '21 09:12 bainro