ly-zhu/leveraging-category-information-for-single-frame-visual-sound-source-separation

PyTorch implementation of "Leveraging Category Information for Single-Frame Visual Sound Source Separation"

leveraging-category-information-for-single-frame-visual-sound-source-separation's Issues

Dataset path

Hello, I'm running your code and building my own dataset, but in music Py has a problem. I don't know how to pass the real data path

My data set path is like this：

I want to ask how I should modify it, thank you for your answer.

separate sound type

Hi, could you please tell me that if the model could separate the sound of musical instrument and singing by person?
Thank you!