Jaechang Kim

Difference output layer doesn't exist in pytorch version.

1

Doesn't difference output layer exist in pytorch version? In tensorflow version I could find 'output_type' parameter, but not in pytorch version. Is there any reason for not including that layer?

I'm trying SirenWrapper(mod-sine) with audio data. But having trouble with training modulator and latent vectors. Is there anyone who can share training code for SirenWrapper(mod-sine)?

Any plan for supporting windowing method?

1

Some previous libraries like museval (https://github.com/sigsep/sigsep-mus-eval/blob/master/museval/metrics.py) or mir-eval(https://github.com/craffel/mir_eval/blob/master/mir_eval/separation.py) have parameter named 'window'. It split large size data into multiple chunks and calculate metrics(like sdr) and aggregate them. I tried fast_bss_eval...

Having Trouble in training: utils.tensors_to_scalars

3

Hello, I'm trying to run your code. I just ran train.py with commands in readme, (with additional argument --hparams work_dir=ccc). But faced this error. > File "train.py", line 143, in...