How to accelerate attack speed?

[machanic]

I found it is too slow when I attack a large network in CIFAR-10 dataset. Because my experiments need attacking 1000 images. It will take 1 month!
I found the reason is that you feed only 1 image to network every time. (in def _eval_sample)
Can this code modify to batch image feed version to boost speed?
We first collect a batch of candidate, stats = candidate_future.result() into a block-queue, and then batch feed to network?
What about this proposal? What do you suggest?

[machanic]

Oh, no! I found the candidate and eval_sample returned value are depended on each other.