FR: Enable forward method of Bayesian Layers to return value only for smoother integration with PyTorch
piEsposito opened this issue · comments
It would be nice if we could store the KL divergence value as an attribute of the Bayesian Layers and return them on the forward method only if needed.
With that we can have less friction on integration with PyTorch. being able to "plug and play" with bayesian-torch
layers on deterministic models.
It would be something like that:
def forward(self, x, return_kl=False):
...
self.kl = kl
if return_kl:
return out, kl
return out
We then can get it from the bayesian layers when calculating the loss with no harm or hard changes to the code, which might encourage users to try the lib.
I can work on that also.
Thanks @piEsposito, this feature will be helpful for inference in particular as KL compute is not required.
@ranganathkrishnan you are welcome. Also, I've already linked a PR that introduces this feature.