Skip to content

A pytorch re-implementation for paper "Towards Deep Learning Models Resistant to Adversarial Attacks"

Notifications You must be signed in to change notification settings

DengpanFu/RobustAdversarialNetwork

Repository files navigation

RobustAdversarialNetwork

A pytorch re-implementation for paper "Towards Deep Learning Models Resistant to Adversarial Attacks"

Requirements

  • pytorch>0.4
  • torchvision
  • tensorboardX

Parameters

All the parameters are defined in config.py

  • exp_name: experiment name, will be used for construct output directory
  • snap_dir: root directory to save snapshots, it works with exp_name to form a directory for a specific experiment

Usage

Training

python train.py

About

A pytorch re-implementation for paper "Towards Deep Learning Models Resistant to Adversarial Attacks"

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published