Skip to content

An official implementation of Improving Model Robustness via Automatically Incorporating Self-supervision Tasks

Notifications You must be signed in to change notification settings

storykim/robustness-self-supervision

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

robustness-self-supervision

An official implementation of Improving Model Robustness via Automatically Incorporating Self-supervision Tasks

Prerequisites

  • Python 3.7+
  • Pytorch 1.3.0+

Dataset

This code requires CIFAR-10-C dataset. You can download the dataset here.

Usage

Training:

python train.py -s {save_point} --rot --lambda_fix_epoch 5 --batch_size 64

Test with CIFAR-10-C:

python test_cifarc.py -l {save_point}

Use -h option to check more flags.

Acknowledgement

This code is based on Dan Hendrycks' code.

Author

Donghwa Kim (@storykim)

About

An official implementation of Improving Model Robustness via Automatically Incorporating Self-supervision Tasks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages