NTL
NTL copied to clipboard
This is the code of ICLR 2022 Oral paper 'Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization'.
In L468 of **gan_aug_cifar_sm.py**, the model that should be frozen is **discriminator_aug**, while the one that is actually frozen is **discriminator**. Obviously, the **discriminator** does not appear below, while **discriminator_aug**...
Hi, Thanks for your great work! Could you please share the checkpoints of the generator models for gan_aug? And what's the value of `n_epochs` for training GAN for augmentation? Thanks!