Could you provide hyperparameter for MNIST?

[yyzharry]

Could you provide hyperparameter for MNIST?

[YyzHarry]

Hi, thanks for your interest in our work.

For training hyper-parameters on each dataset, you can actually find all relevant parameters in Appendix B, Table 8, in our paper. In short, for MNIST, we use SGD w/ momentum 0.9, LR=0.01, and LR decay on Epoch 100/150.

[Magallan1229]

Thank you for your reply , but the lenet model your provide need input with size of 33232 , which seems to be consistent with CIFAR10 not MNIST (12828). Do I need to resize the input or modify the model to match?

[YyzHarry]

Oh good question. I just checked the implementation on MNIST, and found that the LeNet model I used is actually the same as you used (I just made a quick check and seems this is the standard one used in literature). So no worries about my previous comment on architecture. :)

[Magallan1229]

And should I normalize images into [0,1] , or use mean and std to get transforms of inputs as (inputs-mean)/std ?

[Magallan1229]

In the paper you said"We then randomly flip the images horizontally and normalize them into [0, 1]", but code in train_pure.py has transforms composed of ToTensor() and Normalize() which results in a larger range of inputs than 0~1. Forgive my so many questions, I have to make things clear to avoid wasting days of time because my device always spend too much time to run cnn code. Thank you again for your reply.

[YyzHarry]

For the pure training of ME-Net, whether you do the normalization or not shouldn't affect the results much. So either way is fine.