Open Hyperparticle opened 6 years ago
Hi,I also download a sample subset of ImageNet files by the given file 'imagenet_urls.txt', but some problems to be found:
imagenet_urls.txt
is just a sample file with some example URLs and is by no means finished or ideal for testing.
keras.applications.MobileNet
) is not particularly accurate, so you may get inaccurate results on a small sample image set.It would also be nice if we had more URLs. This can be accomplished by downloading the URL files from the ImageNet database and sampling them randomly. Something under 5 MB of URLs could suffice. The labels for each of the images would also need to be stored somehow.
Thanks for checking it out. If you have any more questions I'd be happy to answer.
I am very glad to get your reply so soon! Coincidently,I have the same idea to refine the valid URLs by adding some logic and it works,but it comes out a new problem that some label(s)(e.g."n09337253") are not within the ImageNet1000.As the result,I finally just download very few images successfully.
Finding a good set of URLs with valid labels would be necessary. Unfortunately, I have not found any easy automated tools to do this, so it needs some manual work. Send a pull request if you are able.
Modify 2_one-pixel-attack-imagenet.ipynb to download a sample subset of ImageNet files with appropriate labels. The files should be preprocessed as to be ready for the attack.