More information about the updated checkpoint of pgd trained Madry's model on cifar-10 about pytorch-adversarial-training HOT 3 CLOSED

Sorry for the late reply.

Yes. I use the last saved checkpoints. According to the accuracy difference, there is a lot of randomness will effect the trained output, such as weight initialization, data order and the randomness in PGD attack (during training), so I guess the difference is come from some of these factors. To get a stable result, maybe you can train multiple models with different seeds and compute the average accuracy on them.

from pytorch-adversarial-training.

BTW, in Madry's implementation, they normalize the inputs with mean and std. This may also cause the difference.

from pytorch-adversarial-training.

Close because of inactivity.

from pytorch-adversarial-training.