Closed HelloWorldLTY closed 3 months ago
I found a bug in the original implementation of universal attack, that is, a undefined variable was referred before.
Moreover, I also found that torch.autograd dropped the function of zero_gradients, so I also replace it with a new function.
Could you please review it and give some feedback? Thanks.
I see, thanks.
I found a bug in the original implementation of universal attack, that is, a undefined variable was referred before.
Moreover, I also found that torch.autograd dropped the function of zero_gradients, so I also replace it with a new function.
Could you please review it and give some feedback? Thanks.