Cadene / Cadene/block.bootstrap.pytorch
The question about KLD loss
Open
- Dominant language
- Python
- Stars
- 354
- Forks
- 58
- PR merge metrics
- No merged PRs in 30d
Description
Excuse me again!
When I use the KLDivLoss as the criterion in ./block/models/criterions/kl_divergence.py rather than crossentropy, I get the loss is 0 and the acc is worse , as following picture shows:
But in paper MFH ,KLD loss is better than CrossEntropy, So, how could this be? Thanks!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.