Evaluate the errors in pitch class vector prediction

[bzamecnik]

• overall metrics for the full dataset splits
  • accuracy (on binary classes, full chords)
  • hamming distance (on binary classes, individual tones)
  • AUC (on probabilities, more informative)
• metrics on separate songs
  • how they differ?
• confusion matrix (matrices)
  • 12x 2x2 - for each pitch class separately
  • 1x 4096x4096 - for whole pitch class vectors
• plot a line of error per time frame
  • which places are more erroneous?
• How to take into consideration class imbalance?
  • imbalance in tones vs. silence (1 vs. 0)
  • imbalance across pitch classes