facebookresearch / facebookresearch/AudioDec
Why do the feature matching loss and adversarial loss continue to increase during training?
Open
- Dominant language
- Python
- Stars
- 515
- Forks
- 33
- PR merge metrics
- No merged PRs in 30d
Description
Dear Author, I trained AudioDec_v2 without modifying any experimental settings, and the training loss changes are as follows. Why are the feature matching loss and adversarial loss continuously increasing? Is this behavior normal?
Contributor guide
Assessment
This issue has not been assessed yet.