Jens Egholm Pedersen

Thanks for the input and kind words :-) Happy to hear it's useful! Your work sounds interesting. I would be curious to hear more about your neuron simulator. Are you...

Happy to hear that! Does this link work? https://discord.gg/7fGN359

Thanks for the issue! Unfortunately, I'm a little time-restricted currently. If I recall correctly, the original implementor was @cpehle. Do you have a minute to check this out?

Could the batch dimension be related to the batch dimension in the sample data? On line 40 it's `torch.rand((1, 2, 34, 34))`.

Is that true? This code works well for me: ``` import torch torch.nn.Linear(1, 2)(torch.zeros(1)) ```

Happy to put that in the spec. Ideally, the graphs should be independent of batches, IMO. Shouldn't batches be independent of the computation? We're not doing any batch norming in...

Thank you so much for the insight @chanokin. You're indeed right that we should be returning a Numpy number. And there was an additional bug in that it assumed numpy...

There's a type in the "Import a NIR graph to s**n**Torch". Otherwise, LGTM!

I would agree. But do you know the rough timeline for this? I'm in the middle of fixing a bug in the Norse code (:grimacing:), so if you're ok with...

I'm grateful for your quick reaction @biphasic, but I wonder whether this could also be fixed on the Norse side. As it appears to me, the problem is that the...