Johnathan

Github:

• https://github.com/JChin88/RNN-Nottingham

9/20:

• Research RNNs
• Review PyTorch

10/4:

• Read Articles:
  • https://towardsdatascience.com/recurrent-neural-networks-and-lstm-4b601dd822a5
  • http://colah.github.io/posts/2015-08-Understanding-LSTMs/
• Set up PyTorch

• To do for next week:
  • Set up RNN
    • parse through Nottingham Dataset
    • set up RNN model

10/11:

• Imported Nottingham Dataset and parse through MIDI Files
  • using mido library
• Set up Github repo

• To do for nest week:
  • Figure out how to represent MIDI file as integer in order to best feed into an RNN
  • Create RNN model

10/18:

• 2 approaches of parsing MIDI files:
  • sequence of events
    • possible pros:
      • more free-form
      • can generate own rhythm
    • possible cons:
      • lack of structured rhythm, e.g. 4/4, 3/4
      • note-on/note-off pairs
        • can be resolved by passing in notes as events rather than MIDI messages
  • sequence of beats
    • possible pros:
      • structured rhythm
    • possible cons:
      • may miss off-beat notes, e.g. read quarter beats, miss some eighth notes

• To do for next week:
  • build and train RNN model
  • implement beat sequencer

10/25:

• implemented parse by beats
  • RNN doesn't work with parsing by notes, elapsed time and note length too large compared to other values
  • represented as binary value with 14 bits
    • first 7 bits represent the tone
    • last 7 bits represent the velocity
• implemented reconstruction
• created RNN model
  • one LSTM cell
• trained RNN model
  • only train 10 epoch on one file
  • files don't contain enough notes

• To do for next week:
  • try a fixed velocity?
  • ignore rests?
  • train on more files and for more epochs

11/1:

• Changed representation of notes
  • [note name, octave, length(if parsing by notes)]
  • fixed velocity to 90
• Train RNN model
  • train by beat
    • often get silent MIDI file
  • train by notes
    • often get a single note that sustains
• Problems:
  • RNN doesn't like to change values
    • issue with training, works fine when untrained
• Possible fixes:
  • backprop is probably sinking the params, choose a different loss function?
  • use an optimizer?

• To do for next week:
  • fix bugs in training
    • different loss function?
    • use an optimizer?
  • if bugs are fixed, train on a more diverse set of files

Final:

• Somewhat fixed repetitiveness issue:
  • still repetitive, but now selects from 3-4 notes instead of one
  • with the exception of very low and very high notes, range of notes typically sound good together(not off-key)
• Possible future fixes:
  • More complex LSTM
  • restrict range of notes: keep around the middle