Training option

[pokaxpoka]

Hi, thank you for sharing the code. Is it possible to clarify the all training options (e.g., python train_model.py -d mnist -m d2l -e 50 -b 128 -r 40 ) for the results on the paper? It'll be very useful in reproducing your results.

Thanks

[xingjunm]

For CIFAR-10:

1. clean: train_model.py '-d', 'cifar-10', '-m', 'd2l', '-e', '120', '-b', '128', '-r', '0'
2. 20%: train_model.py '-d', 'cifar-10', '-m', 'd2l', '-e', '120', '-b', '128', '-r', '20'
3. 40%: train_model.py '-d', 'cifar-10', '-m', 'd2l', '-e', '120', '-b', '128', '-r', '40'
4. 60%: train_model.py '-d', 'cifar-10', '-m', 'd2l', '-e', '120', '-b', '128', '-r', '60'