foolwood / foolwood/DCFNet_pytorch
the DCFnet seems can't converge
Open
- Dominant language
- Python
- Stars
- 215
- Forks
- 60
- PR merge metrics
- No merged PRs in 30d
Description
Thank you for your excellent work and your share!
These days,I copy the code and retrain the DCFnet, to my surprise,I find that although the mean loss is decreasing, the loss seems fluctuating.Just like below. As I didn't change key parts of the DCFnet. It confused me.Do you ever met a similar phenomenon? And if it convenient to give me some advices? Sorry for my poor English and thank you again.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.