search

bethgelab / foolbox

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
https://foolbox.jonasrauber.de
MIT License
2.77k stars 427 forks source link

Pytorch not work #146

Closed AmingWu closed 6 years ago

AmingWu commented 6 years ago

When I use FGSM with Pytorch, it does not classify wrong. fmodel = foolbox.models.PyTorchModel(inception, bounds=(0, 255), num_classes=1000) attack = foolbox.attacks.FGSM(fmodel) adversarial = attack(img, label=label)

jonasrauber commented 6 years ago

Can you give more details. Full code (minimal example) including expected and actual output.

jonasrauber commented 6 years ago

Assuming this has been solved.