Windows support, checkpoints, mix-to-vocals

[wuaalb]

These are several small changes that may be of general interest. I realize mixing issues in a single PR is not ideal, but didn't want to separate them in case you weren't interested altogether.

Changes

• Windows support
  • Wrapped code in if __name__ == '__main__' (needed for multiprocessing)
  • Removed lambdas (needed for pickling for multiprocessing)
• Fixed some inconsistencies in checkpoint loading/saving
  • When saving, save state dict of module wrapped by nn.DataParallel, not the wrapper itself
  • When loading, remove module. prefix from state dict keys if nn.DataParallel wrapper was saved (the provided pretrained weights for instance)
  • There was some confusion about storing step or state (training loop state) in the checkpoints. Changed to whole state.
• Allow separating just vocals from input mixture
  • Added --instruments command line argument, rather than hard coding the list.
  • Changed random_amplify so it doesn't assume instruments sum to mix.

[f90]

Thanks for your contribution! I just looked at the code and it seems to all work fine. Going to merge this pull request now.

May I ask what you are working on currently that you are using my model? :)