search

carlini / nn_robust_attacks

Robust evasion attacks against neural network to find adversarial examples
BSD 2-Clause "Simplified" License
778 stars 229 forks source link

Made the print compatible with Python 2. #13

Closed mzweilin closed 6 years ago

mzweilin commented 6 years ago

Python 2.7 would run this line into problem without the future print fuction:

print(step,*sess.run((loss1,loss2),feed_dict=feed_dict))