Skip to content

kangmintong/FaShapley

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Pre-train, prune, and fine-tune on CIFAR-10 based on CROWN-IBP training:

sh cifar_crown-ibp.sh

Pre-train, prune, and fine-tune on CIFAR-10 based on MixTrain training:

sh cifar_mixtrain.sh

Pre-train, prune, and fine-tune on SVHN based on CROWN-IBP training:

sh svhn_crown-ibp.sh

Pre-train, prune, and fine-tune on SVHN based on MixTrain training:

sh svhn_mixtrain.sh

Prune on Tiny-ImageNet based on Auto-LiRPA training:

sh tinyimagenet_auto_lirpa.sh

For structured pruning, use shapley_init_structured.py instead of shapley_init.py.

About

Codes for FaShapley: Fast and Approximated Shapley Based Model Pruning Towards Certifiably Robust DNNs [SaTML 2023]

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published