Using examples/dsd100/separate_dsd.py

[SubhasreeSengupta]

Hello,

I am getting an error in running the above file. I used the fft_1024.pkl file and a mixture.wav file from the dsd100 dataset.

The error is : File "separate_dsd.py", line 336, in main(sys.argv[1:]) File "separate_dsd.py", line 333, in main train_auto(inputfile,outdir,model,0.3,30,25,32,513) File "separate_dsd.py", line 251, in train_auto lasagne.layers.set_all_param_values(network2,params) File "C:\Users\path\lasagne\layers\helper.py", line 516, in set_all_param_values (len(values), len(params))) ValueError: mismatch: got 13 values to set 15 parameters

[nkundiushuti]

Most likely due to loading a different model from the one declared in build_ca. The correct model for this script is:https://drive.google.com/file/d/0B-Th_dYuM4nOb281azdKc2tWbFk/view

[Riz0]

@nkundiushuti Thanks for linking that model, it resolved this exact issue I was having with separate_dsd.py. Sadly I am still experiencing issues with separate_ikala.py, do you also have the correct model for this filter? The error I am getting with separate_ikala.py while using the model you linked:

Traceback (most recent call last): File "separate_ikala.py", line 278, in main(sys.argv[1:]) File "separate_ikala.py", line 275, in main train_auto(inputfile,outdir,model,0.3,30,20,32,513) File "separate_ikala.py", line 205, in train_auto lasagne.layers.set_all_param_values(network2,params) File "C:\Users\Anon\Anaconda2\lib\site-packages\lasagne\layers\helper.py", line 516, in set_all_param_values (len(values), len(params))) ValueError: mismatch: got 15 values to set 13 parameters

I am hoping that separate_ikala.py will do a better job of isolating vocals as separate_dsd.py didn't work out as I hoped. A song with vocals laid over acoustic guitar is trickier then I imagined. Thanks in advance!