search

ashafahi / free_adv_train

Official TensorFlow Implementation of Adversarial Training for Free! which trains robust models at no extra cost compared to natural training.
https://arxiv.org/abs/1904.12843
173 stars 30 forks source link

The question about delta. #9

Open ghost opened 4 years ago

ghost commented 4 years ago

Thanks for your work, it helps me a lot. I notice the delta in your algorithm is gradually accumulate. but that in 《Towards Deep Learning Models Resistant to Adversarial》 is randomly reset. Is there any difference between these two methods ?