Skip to content

avirmaux/lipEstimation

Repository files navigation

Lipschitz Estimation

Repository for the paper Lipschitz Regularity of deep neural networks: analysis and efficient estimation

Basic Python dependencies needed: PyTorch >= 0.3

Code organisation

  • lipschitz_approximations.py: many estimators
  • lipschitz_utils.py: toolbox for the different estimators
  • seqlip.py: SeqLip and GreedySeqLip
  • training.py: general scheme for train/test
  • utils.py: utility functions

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages