universal_pytorch icon indicating copy to clipboard operation
universal_pytorch copied to clipboard

Pytorch implementation of Universal Adverserial Perturbation and Fast Feature Fool

Results 3 universal_pytorch issues
Sort by recently updated
recently updated
newest added

Hi, Thanks for your contribution. For line 335 in utils.py, https://github.com/BardOfCodes/universal_pytorch/blob/6ae4dbb9795026a895b187063a9d6bd1e2842dd7/utils.py#L335 I believe the code should be `params.requires_grad = False` btw, I am wondering why there is no clipping implementation...

I use pytorch 0.4.0 to run, but it reports error after many iterations. see below ``` Traceback (most recent call last): File "find_uap.py", line 76, in max_iter_df=max_iter_df,init_batch_size=batch_size) File "/home1/machen/universal_pytorch/utils.py", line...

In ImageNet dataset, there are 1000 classes in total, but when I set num_classes in Universal, the algorithm runs too slow, because it will iterate over 1000 times in deepfool.py