Open gyeongin opened 7 years ago
WaveNet autoencoder model is tailored for musical note data. We should fine tune the model to adapt for multi-note (music) data.
Instead of starting from scratch, we can use the pre-trained model from NSynth.
Modify the implementation to utilize multi GPUs
WaveNet autoencoder model is tailored for musical note data. We should fine tune the model to adapt for multi-note (music) data.