Skip to content

Repository for the Adversarial Attack on Generative Classifiers project for the Probabilistic Graphical Model course

Notifications You must be signed in to change notification settings

paulbarbier/adversarial-attacks-on-generative-classifiers

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

51 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Main repo for the Generative Classifiers PGM Project

Setup requirements

Please follow the following instructions to install the required packages:

cd code;
python -m venv venv
source venv/bin/activate
python3 -m pip install --upgrade pip
pip install -r requirements.txt

Or alternatively, run the setup.sh script.

Training instructions

you can train the model using the following command:

cd code; python -m train --config=configs/fashion-mnist-gfz.py --config.checkpoint_name="checkpoint-name" --config.num_epochs=1

the params checkpoints after each epoch will be stored under checkpoints. there is a load_checkpoint function to load them back.

Evaluation

To compute evaluation metrics on a given checkpoint, use the following command:

cd code; python -m evaluate --checkpoint=dfz-2-epochs-first-try-1

About

Repository for the Adversarial Attack on Generative Classifiers project for the Probabilistic Graphical Model course

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •