search

tml-epfl / understanding-fast-adv-training

Understanding and Improving Fast Adversarial Training [NeurIPS 2020]
https://arxiv.org/abs/2007.02617
94 stars 12 forks source link

Request for ImageNet pre-trained models. #4

Closed FeiiYin closed 3 years ago

FeiiYin commented 3 years ago

Hi, I'm really impressed with your excellent work. Can you provide the pre-trained model's checkpoint on Dataset ImageNet? Thanks!

max-andr commented 3 years ago

Hi,

Thanks for the interest in our work!

Unfortunately, I don't have the ImageNet models anymore. But you can train them from scratch using the code from "Fast is better than free" paper with the GradAlign regularizer.

I hope that helps.

Best, Maksym