- Notifications
You must be signed in to change notification settings - Fork8
Public code for a paper "Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks."
License
NotificationsYou must be signed in to change notification settings
ytsmiling/lmt
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Public code for a paper"Lipschitz-Margin Training:Scalable Certification of Perturbation Invariancefor Deep Neural Networks."
How to train:
python3 train.py (configuration-file-name).pywhat is the configuration file?
example:
python3 train.py config/parseval_svhn/default.py --gpu 0How to evaluate with attacks:
python3 evaluate.py (result-dir-of-trained-network) (attack-configuration).pyThis script calculates each value in inequality (5) in Sec.6and create inequality-(attack_name).npy under a specified result directory.
example:
python3 evaluate.py result/config/parseval_svhn/default-00 config/attack/cw_100_1.pyY. Tsuzuku, I. Sato, M. Sugiyama:Lipschitz-Margin Training:Scalable Certification of Perturbation Invariance for Deep Neural Networks,(2018),url,bibtex