Erik Daxberger

@youkaichao Thanks for letting us know -- this exception comes from the BackPACK backend we're using to compute second-order information; not sure if the ASDL backend throws an exception when...

I was about to suggest this as well -- I have been using black in the past and liked it (although I agree that in some cases, it might produce...

Perhaps another thing to discuss: how should we make sure this style is used? I think there's several options: - just trusting contributors on running their code through black before...

Hi @georgezefko, Thanks a lot for your interest in our library and the subnetwork LA in particular, I really appreciate it — sorry also for the late response! Indeed, using...

Thanks for the great follow-up question! So the Last Layer approximation is a special case, as there the model can be interpreted as using a fixed feature extractor (i.e. comprising...

Thanks for the follow-up question! That's an interesting use case. I'm not too familiar with Spatial Transformer Networks, but what you're describing sounds somewhat reasonable. What is the reason for...

I see, the idea sounds sensible. In this case, I have another question: what exactly is the output of the localisation network? As I understand, the localisation network is mapping...

Ah I see, so it’s effectively a regression model — in that case it does make sense to me to use a Last Layer LA. Curious to see how well...

Thanks a lot for joining the discussion, @polaschwoebel, and sorry for the late response! What you describe sounds sensible to me as well. Perhaps @wiseodd or @AlexImmer, who are experts...

Thanks Agustinus for this PR, this is very useful! Just took a glance at the parts that I'm familiar with, which looks good to me. I'll defer to Alex and...