LTS4 / DeepFool

A simple and accurate method to fool deep neural networks
357 stars 130 forks source link

When running code on binary classification #4

Open Qian-Han opened 5 years ago

Qian-Han commented 5 years ago

When running code on binary classification, does it mean that we only need to modify the num_classes = 2 instead of 10 as default?

When I tried it, I found a lot of perturbed samples as NaN value. Have you ever found this before?