These are notebooks for reproducing our paper "Computer Vision with a Single (Robust) Classifier" (preprint, blog). Based on the robustness python library.

Steps to run the notebooks (for now, requires CUDA):

• Clone this repository
• Download our models from S3: CIFAR-10, Restricted ImageNet, ImageNet, Horse-to-Zebra, Summer-to-Winter, Apple-to-Orange
• Make a models folder in the main repository folder, and save the checkpoints there
• Install all the required packages with pip install -r requirements.txt
• Edit paths in user_constants.py to point to PyTorch-formatted versions of the CIFAR and ImageNet datasets
• Start a jupyter notebook server: jupyter notebook . --ip 0.0.0.0

@inproceedings{santurkar2019computer,
    title={Computer Vision with a Single (Robust) Classifier},
    author={Shibani Santurkar and Dimitris Tsipras and Brandon Tran and Andrew Ilyas and Logan Engstrom and Aleksander Madry},
    booktitle={ArXiv preprint arXiv:1906.09453},
    year={2019}
}