Fabio Muratore

Same problem over here with Julia 1.7.2 VSCode 1.66.2 Julia Language Support 1.6.17 on Ubuntu 20.04

I just encountered the same problem with 2-dim input and 2-dim output for 5000 training points. I got the grid size from `gpytorch.utils.grid.choose_grid_size(inputs_trn, 1.0)` and created the `covar_module` like this...

I plan to have a look at it during the hackathon

I plan to have a look at it during the hackathon

Thanks, @omry for your quick reply. I am not familiar with that header mechanism you mentioned, thus don't immediately see how these are conflicting. Anyways, if you don't want this...

I understand, thanks for the explanation.

Hi @feracero, I am currently also thinking about using this repo for regression tasks. Did you have success? @ranganathkrishnan (and other contributors) would it be possible to add an example?...

@giulioturrisi I was putting it off due to other projects. It is still on my plate to try it within the next 1-2 months though. What is your experience?

Nice, thank you @ranganathkrishnan. Is there a specific reason why only LSTMs and not GRUs or RNNs are supported [here](https://github.com/IntelLabs/bayesian-torch/blob/main/bayesian_torch/models/dnn_to_bnn.py#L152)? Or in other words, why did you have to re-code...

I thought about pinning it, but within v0.3.X they should be backward compatible, and I think that >= logic does not increase the minor version if the version is less...