Brian Groenke

If you use my updated code, you should have the latest version of Keras available from pip installed.

One of the other changes I made early on was adding a command line interface. That earlier version requires you to supply the current iteration you want to start on...

I recommend that you review the total [diff](https://github.com/MattVitelli/GRUV/compare/master...bgroenks96:gruv-original) between that branch and the original GRUV code to get a better understanding of what changed and what you might want to...

I would recommend that you use the TensorFlow backend. I went down the rabbit hole of trying to get Theano to use my GPU, and it never worked. TensorFlow worked...

Hi all, I have been exploring the possibility of switching from Turing to Gen for some of my modeling tasks since it seems a lot more flexible. Unfortunately, I have...

@ChrisRackauckas (and anyone else), do you have any sugggestions as to how we could isolate this to be an `Optim` problem? (I have verified that this issue does not occur...

I am looking into this now. I think it works as is, but we would need to add some wrapper code for better integration with the `Strategy` APIs and `TF_CONFIG`.

I would prefer something like ```julia @lognamespace forces @log drag = p.c*x.vel^2 ``` or maybe `@loggroup` or something. Basically something which would set the context for all subsequent `@log` calls...

But I agree, this would be very useful for my use-case. At the moment, I'm going to try to use prefixes to accomplish this... but that's not ideal.

Looking at the code, it seems that we just need to add a version of `get_log` that allows for the global log to be already active. `activate!` and `deactivate!` should...