hhhzzj

> > > I don't think that it looks that bad. Have a look at Fig. 2 in arXiv:1801.02612 (the original paper), the digits they have generated do not look...

Yes,i have the same model as model A.The dropout layers was added in the training procedure.When i calculate the ASR,i commented out them.Although the experiment is running,the result is bad.because...

Oh,i almost forgot.when i added softmax as an activation function in the FC layers (it is the same as the original paper's table 5),i absolutely not attacked any other images...

 Firstly thank you very much for your patience. 1. the accuracy is 98.6% on clean images.the accuracy in tabel 1 is 98.58%. 2. the library's version is 0.2 3....

nonononono,i am not solve this problem.the result's info are normal,but the ASR is only 1/3.It is too low.I really really hope get your help.

It is ok,thank you for your patience all the same.

Thank you so much!The way of calculating the ASR for me is the same as you(ruling out samples misclassified even with no perturbation).I decrease tau to 0.005,and model A's ASR...