search

rahulvigneswaran / Lottery-Ticket-Hypothesis-in-Pytorch

This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks" by Jonathan Frankle and Michael Carbin that can be easily adapted to any model/dataset.
325 stars 91 forks source link

Transform only good for mnist #15

Closed bainro closed 2 years ago

bainro commented 2 years ago

https://github.com/rahulvigneswaran/Lottery-Ticket-Hypothesis-in-Pytorch/blob/master/main.py#L37

should be this for cifar10 & cifar100:

normalize = transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])

Not certain for fmnist though 🤔

bainro commented 2 years ago

dupe: https://github.com/rahulvigneswaran/Lottery-Ticket-Hypothesis-in-Pytorch/issues/9