advboxes / AdvBox

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

MIFGSM

Shall-Ven opened this issue · comments

commented

使用MIFGSM时出现:
assert self.model.channel_axis() == adversary.original.ndim
AssertionError
问题在哪里?
其他的方法却没有问题