L2dist can‘t convergence

Question

L2dist can‘t convergence

Closed this issue 5 years ago · 2 comments

Hi,
I run your code on my dataset.
After finding the adversarial example, the L2 distance is larger as the number of iterations increases.
It looks like that the estimated gradient can't guide the direction of the drop in L2 distance.
Do you have any advice?
Thanks!

Answer 1 · 2019-03-15T20:05:17.000Z

Hi,

It seems like AutoZOOM cannot find a good estimation for the gradient vector. I would suggest to increase the number of random vector ( specified by the option num_rand_vec) to improve the estimation of the gradient vector.

Bests,
Chun-Chen

Answer 2 · 2019-03-16T06:09:53.000Z

Thanks for your reply!
I will try again according to your suggestion.