Closed inkawhich closed 4 years ago
If it is the former, do you incur a ~4x increase in training time because the effective batch size is 4x bigger?
The training time is around the same because 4x the number examples per batch on CIFAR usually fits within memory.
I just added the adversarial files (though I have not tested the code in a while).
Dan,
I think I know the answer to this question but I will ask it anyway. Do you compute the adversarial examples on the batch that contains all of the rotated versions of the data OR do you compute the adversarial examples on the 0deg rotation batch then compute the rotated versions? If it is the former, do you incur a ~4x increase in training time because the effective batch size is 4x bigger?
Thanks in advance, Nate