Have someone reproduced the result of DenseNet 40 on CIFAR100 from the original paper?

vision
1

I have just got the acc of 70.86%, lower than the 75.58% in paper.
RandomCrop and RandomHorizontalFlip are used with SGD which the lr is set to 0.1 and get divided by 10 in epoch 150 and 225 of the all 300 epochs.

2

That’s quite a low result. I often get acc of 74.3% via PyTorch. With lua Torch it is very easy to reproduce the result. I don’t know why it is so hard to achieve the same acc with PyTorch…