Tom Le Paine

@ibab the demo in `fast-wavenet` trains on a single sample using a scalar encoding. Maybe we could test the two methods using that simple setup? Train on a single sample...

Hi @ianni67, what are your goals exactly? This code is designed to demonstrate the fast wavenet generation algorithm. If you want to learn the structure of music and generate novel...

Do you still have this error with the newest updates? Also I haven't tested this with python 3. Can you try using it with python 2.7?

Hi @danieleghisi @ianni67 I have definitely run the demo with less memory. 6 GB I think. Did you have any luck?

@ianni67, I'm glad you resolved your issue. @danieleghisi do you think you have the same problem?

@danieleghisi why are you saving predictions[0]? What is the shape of predictions? Glad you are closer to getting the code working!

Does this demo occur when you run the demo notebook? Did you try restarting the notebook and running all cells in order? It sounds like for some reason the same...