This is a pytorch implemention of the fast spectral norm regularization algorithm proposed in the paper Fast Approximate Spectral Norm Regularization for Enhancing Robustness of DNNs.
The 'GPU_version.py' will compare our fast spectral norm regularization algorithm with the newest algorithm. You can modify row 302 to switch loss among none regularizer (loss = loss
), our regularizer (loss = loss + loss_my_conv
) and newest regularizer (loss = loss + loss_old_conv
).
Please get the data from here.