About low and high value of uniform distribution in PGD attack (CIFAR-10)
fugokidi opened this issue · 1 comments
fugokidi commented
Hi Eric,
Thank you for the code. It's awesome with all efficient training tricks.
I would like to ask your confirmation on the values of low and high value in CIFAR10/utils.py
line 61, the delta is initialized in uniform distribution on each normalized channel.
delta[:, i, :, :].uniform_(-epsilon[i][0][0].item(), epsilon[0][0][0].item())
The high value is epsilon[0][0][0]
, wouldn't it be epsilon[i][0][0]
?
I am new in this. Can you please confirm? If you specifically fix the high value, can you please explain me a little bit? Thank you for your valuable work again.
leslierice1 commented
Thanks for noticing this! It was a typo and has been fixed (though it shouldn't matter too much either way).