View Code? Open in Web Editor
NEW
A pytorch implementation of "Towards Evaluating the Robustness of Neural Networks"
License: MIT License
cw-pytorch's Introduction
- ๐ Postdoctoral Researcher at Seoul National University
- ๐ Machine Learning & Deep Learning
- ๐ฅ Adversarial Robustness & Generalization
cw-pytorch's People
Contributors
Watchers
cw-pytorch's Issues
error: indices should be either on cpu or on the same device as the indexed tensor (cpu)
one_hot_labels = torch.eye(len(outputs[0]))[labels].to(device))
I don't know, which item should set to cpu
I tried to perform targeted attack but failed. So how to set the parametres to perform the targeted attack?
Hey, even after adverserial attack, the panda image is being classified as panda. Can you help regarding this?
PS - I ran whole notebook as it is after uploading data