Felix Bauer

> 1. Binning time windows needs 3 out of 4: bin size/time window/dt, number of bins, start time, end time. Question: what to do if the events do not all...

Yeah I see your pont. I just tried the function from torchvision and at least for the dataset I'm looking at it fails without any warning. Then maybe it's better...

The timeline is currently not clear. All I can say is that hopefully someone will work on it soon. As a support link, the official one is rockpool.ai . However,...

No. Looks like this one got overlooked. Would you like me to take care of it?

After discussion among sinabs developers: The current behavior is good as it is now. However, it should be described properly in the docstrings (and documentation).

@sheiksadique what's the current state of your graph extraction algorithm? Is it feasible to apply it to this issue?

I've been thinking a bit more about this. There are basically three input formats that we typically encounter: ### 1. Torch Tensors with binned (rasterized) events The standard in Sinabs...

That's a good point. So far I have considered consistency as the forward method always taking the same (data-)type as argument. But it's true that consistent (in particular consistent with...

If this refers to the default arguments of the `LIF` and `IAF` layers, I agree.

Implementation done, but still needs unit testing