CornellDataScience / CornellDataScience/IntSys-Vocal-Isolation
SVSGan training loss not decreasing
Open
- Dominant language
- Python
- Stars
- 2
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Loss is bouncing around and not decreasing in general.
Notice that vocal/mixture can be as large as 67. Maybe using a probability mask is not proper?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.