Xingjun Ma
Xingjun Ma
Hi Reuben, nice work here! My code for ICLR 2018 paper "Characterizing adversarial subspaces using local intrinsic dimensionality", has included the BU, KD measures along with the CW attack (and...
Hi bhadresh74, thanks for your interest. You can wrap up your new dataset in the datasets.py, load the data the same way as in train_models.py, you can try with a...
Hi Fanhan, Will have a look when I have time as I am currently busy with travelling. But from your results it seems CE is even better than any other...
Hi pokaxpoka, thank you for your report. I do find reproductivity issue when tested with a fresh run on new devices. I will try to fix it. Can you provide...
I have uploaded an old version of the code old_version/d2l_old.zip, can someone test if this version works?
Thank you all for your interest. And sorry that it took me so long to have time fix the issue. Sorry for the waiting. Good luck to you all with...
For CIFAR-10: 1) clean: train_model.py '-d', 'cifar-10', '-m', 'd2l', '-e', '120', '-b', '128', '-r', '0' 2) 20%: train_model.py '-d', 'cifar-10', '-m', 'd2l', '-e', '120', '-b', '128', '-r', '20' 3) 40%:...
Hi, Issues on CIFRA-10 has been fixed.
using the following instead: from keras_applications.imagenet_utils import _obtain_input_shape