jvmncs

hi @skeydan, sorry that we overlooked your question before :( I've written an update about tf 2.x support in [this comment](https://github.com/tf-encrypted/tf-encrypted/issues/799#issuecomment-636127262). thanks for your interest, we enjoyed your blog post!

Yes, it's on our roadmap, although we've prioritized a few other items (in particular, more robust support for Keras layers and models). @yanndupis and I have some other things on...

This would be great to work on after the keras work is done. The forward pass is easy, but the backward pass can be quite tricky.

We've had plans to do so, but it's been a bit neglected -- would you find it useful to have it? If you'd like to add it, we'd be more...

Ah, the problem here is that we've only tested converting Sequential models via clone_model, and using the InputLayer isn't necessary in those cases. We should be able to implement that...

ping @mortendahl

This definitely looks like a bug, we'd want a way to sample batches and it looks like that's not happening here. I'd recommend that we patch it by following tf.keras's...

This looks similar to #787, does the solution there fix your issue?

Hi, we don't have a release planned yet, but our next release will include ABY3 in the pip package! You can find more info about our upcoming plans [here](https://github.com/tf-encrypted/tf-encrypted/issues/799#issuecomment-636127262).

>Can I essentially use the Conv2dTranspose class from keras as reference, and just replace the necessary methods and variables with the tfe equivalent? (Want to make sure that I am...