aaronsarna

Generally the way you would do something like this in Tensorflow is to have some dummy value for the ground truth when it's not available (like an all 0's tensor,...

Seems like this is an issue with TFDS, not TF-GAN. Consider reporting it at https://github.com/tensorflow/datasets/issues instead.

Hi Saurav, Thanks for contributing! Pretty much this whole library is designed around TF1 constructs and in order to get it working with Keras and proper TF2 it probably needs...

I think just showing a basic mnist or cifar10 GAN trained with TF2 and Keras is sufficient.

I don't think there's any need to stick with collections.namedtuple. To some extent the right answer will depend on the overall design. It may just be a class, or you...

Thanks, that was helpful. I've been working on reproducing your ViT results in JAX, and so far it seems that the most critical piece to getting this all to work...

As I recall, the thing that helped the most for SimMIM linear probe was to mask attention to the mask tokens in the ViT during pretraining. If you don't do...

I wasn't able to reproduce it without that change. Very possible I had some bug though.