robintibor

Might tackle at some point or maybe @sylvchev wants to have a try? ;)

Hi, as the error indicates, your loss function needs to return a single value (hence the "scalar outputs" error). May be your loss function creates a value per example? then...

yap, good decision to close

What is status of this is it still planned? @sylvchev

@gemeinl we solved this right? or is this a different problem? @Div12345 do you use current master?

So it seems skorch returns version 'n/a' for some reason the way it was installed in your linked colab:  Seems this happens here: https://github.com/skorch-dev/skorch/blob/2d06cd70896d01c948eceec90dff84f2c9990a6a/skorch/__init__.py#L46-L49 Unclear to me why it...

well @Div12345 yes I think this can only happen with the master version of skorch, but maybe we still want to be compatible in any case?

I mean in this code, the dataset and window creation is done on module level, so when test_preprocess.py is imported it would be executed: https://github.com/braindecode/braindecode/blob/e7063545e7462fb50e216d7cd31020b36ae4d521/test/unit_tests/datautil/test_preprocess.py#L18-L26 Don't know if this really...

* multi-target * description part uses target column, a bit limiting * maybe keep target as a separated variable (like numpy array that can be returned) * might be possible...

Amazing stuff, great you mentioned to them!