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

A bug in `eval.py` #5

Closed cmhzc closed 3 years ago

cmhzc commented 3 years ago

In line 51 of eval.py, when calling get_model you passed 6 arguments but it only takes 5. The get_model isn't able to take args.n_hidden_fc as an argument.

max-andr commented 3 years ago

Hi,

Thanks a lot for letting us know! Indeed, I missed that while I was refactoring the code :) now it's fixed in this commit: https://github.com/tml-epfl/understanding-fast-adv-training/commit/96d1a62a3b2c4bb32bd2ff59c6a1cc6f045bb284

Best, Maksym