About the variable 'input_audio_corrupt' in lines 240-241, isn't it target_audio_corrupt?

adobe-research / DeepAFx-ST

DeepAFx-ST - Style transfer of audio effects with differentiable signal processing. Please see https://csteinmetz1.github.io/DeepAFx-ST/

Other

369 stars 47 forks source link

About the variable 'input_audio_corrupt' in lines 240-241, isn't it target_audio_corrupt? #27

Open taehoGit opened 2 years ago

taehoGit commented 2 years ago

https://github.com/adobe-research/DeepAFx-ST/blob/49bd0c88f3a0ad8b9c45f88200b4caa74952c43d/deepafx_st/data/dataset.py#L229-L246

csteinmetz1 commented 2 years ago

Hi @taehoGit, this does look like a bug, however it likely has a minimal effect. There may be some different behavior between the dynamics of the input and the target, but style transfer training should still function. Thanks for pointing it out.