search

magenta / magenta

Magenta: Music and Art Generation with Machine Intelligence
Apache License 2.0
19.03k stars 3.74k forks source link

Implement note-based (pitch + duration) encoder/decoder. #508

Open iansimon opened 7 years ago

iansimon commented 7 years ago

The current melody model uses time-based encoder/decoders; each RNN step is one 16th note by default. We should also try note-based encoder/decoders, where each RNN step is an event of the form "play note with pitch P for duration D".

veqtor commented 7 years ago

Perhaps it could be resolved using sigmoid output with every pitch/note encoded as multi-class labels. That way we could keep the 16th note resolution which helps inform the RNN of rhythmic patterns