DrummerNet icon indicating copy to clipboard operation
DrummerNet copied to clipboard

Published 20 hours ago • verified publisher icon keunwoochoi

Implementation details

Open clementabary opened this issue 4 years ago • 0 comments

Thanks a lot for the great work.

I still have a few questions on implementation details. First, what is the reason for partitioning the training procedure with powers of 2 ?

Second, I am confused with normalization. For the source dataset, you use the maximum absolute value normalization while for the sample dataset you use a scaling with lambda x: 10 * 1.0 / x.pow(2).sum().sqrt(). Can you give more insight on this choice ?

Third, why did you choose to pad your sequences with small noise rather than zeros ?

clementabary avatar Mar 09 '20 09:03 clementabary