Deep isolation using DeepLabv3++ Segmentation Model

• "Looking to Listen" by Google : https://ai.googleblog.com/2018/04/looking-to-listen-audio-visual-speech.html
• "Phase aware speech enhancement with Deep U-Net" by Clova AI Research : https://openreview.net/forum?id=SkeRTsAcYm

• MusDB : https://sigsep.github.io/datasets/musdb.html
  This dataset enables you to split music to different sources including Vocals, Drums, Bass, other.

import DeepIsolation.API.Model as API

api = API(n_gpu=1)
model = api.getModel()

model = model.to(device)
...