This is the code for the paper 'Music source separation using stacked hourglass networks', ISMIR 2018
Check out the qualitative results here
Required packages
tensorflow, pysoundfile, librosa, bss_eval (https://github.com/craffel/mir_eval)
MIR-1K dataset
DSD 100 dataset
Set the dataset and checkpoint paths at config.py and run
python train_mir_1k.py
for MIR-1K dataset, or
python train_dsd_100.py
for DSD 100 dataset.
Run
python eval_mir_1k.py
for MIR-1K dataset, or
python eval_dsd_100.py
for DSD 100 dataset.
These are the checkpoint files for each dataset to reproduce the results on the paper.