search

f90 / Wave-U-Net

Implementation of the Wave-U-Net for audio source separation
MIT License
845 stars 177 forks source link

Pretrained models NotFoundError #14

Closed beantowel closed 5 years ago

beantowel commented 5 years ago

run the command: python2 Predict.py with cfg.full_multi_instrument results in: NotFoundError: Key separator/conv1d_26/bias not found in checkpoint however, the command python2 Predict.py with cfg.full_44KHz will terminate with no errors.

f90 commented 5 years ago

As shown in the readme, by default the 44KHz singing voice separation model is loaded, so its okay to not put a model_path parameter. But in your case you have to put the path to the model checkpoint file. So it would be

python Predict.py with cfg.full_multi_instrument model_path="checkpoints/full_multi_instrument/full_multi_instrument-134067

Does that make sense/resolve your problem?

beantowel commented 5 years ago

thank you, it solves the problem, missed that part of readme 0v0