search

rakutentech / stAdv

Spatially Transformed Adversarial Examples with TensorFlow
MIT License
72 stars 18 forks source link

A new bug #5

Closed hhhzzj closed 5 years ago

hhhzzj commented 5 years ago

When i ran the program to calculate the ASR,i had a new problem. 3 There are 9913 clean images predicted successfully by model A.And i planned to attack these images to calculate the ASR.But when it was attacking the 2039th clean images,it stopped.And it looked like the memory leak. So i want to finalize the graph to check the program. 4 And above picture shows that every iteration tf.gradients() can build a new node,and eventually there are too much node to run. What do you think about it?

berangerd commented 5 years ago

Good catch! Indeed, given that I am using using an external optimizer (SpiPy's) for L-BFGS, so far I have been calling tf.gradients every time stadv.optimization.lbfgs is called. But what I missed is that it makes the graph grow every time the routine is called. I have pushed modifications for that (see https://github.com/rakutentech/stAdv/commit/26286a8e84b61d474a958735dcff8f70d31deccc) and made it a version 0.2.1. You can upgrade with pip install -U stadv. Providing grad_op as input (as done in the updated demo notebook) should solve the problem. Please let me know if it works with you.

berangerd commented 5 years ago

Let me close this issue. If the fix in v0.2.1 doesn't solve your problem, feel free to reopen.

hhhzzj commented 5 years ago

It solved my problem,thank you so much.