Can't reproduce MNIST results using current codes

[ain-soph]

I just cloned this repo and try to run codes with provided instructions. (the code is not modified.)
Environment: cuda 11.3, python 3.9.6, pytorch 1.9.0, torchvision 0.10.0, installed via miniconda.

I run python train_mnist.py --fname ./new_result.pth to get a model,
and then run python evaluate_mnist.py --fname ./new_result.pth to evaluate the robustness.
and run python evaluate_mnist.py --fname ./new_result.pth --attack none to evaluate the clean accuracy.

The result shows that robustness=0.00% and accuracy=97.71%, meaning the trained model is not robust at all.

However, using your pretrained model in models/fgsm.pth brings a robust model. (robustness=88.38% and accuracy=98.50%)

Could you provide any comment on how to reproduce your pretrained results?

[ain-soph]

Please ignore the UserWarning, which is caused by pytorch/vision#4184

[latorrefabian]

I am having the same issue, did you find a solution? @ain-soph