Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Have you ever try to train the model from cratch without restore any weight? #2

Closed
Fighting-JJ opened this issue Jan 14, 2019 · 2 comments
Closed

Have you ever try to train the model from cratch without restore any weight? #2

Fighting-JJ opened this issue Jan 14, 2019 · 2 comments
Labels
wontfix This will not be worked on

Comments

@Fighting-JJ
Copy link

thank you a lot.
@viplix3
Copy link
Owner

viplix3 commented Jul 17, 2019 •
edited
Loading

Yes I did, but for a single class.
For muliple classes the classification loss is not coverging as expected, maybe it has something to do with the hyper parameters.
I am experimenting with focal loss and multi-resolution training.
Will push an update once I get better results.

@Fighting-JJ
Copy link
Author

Thanks for your reply.

@viplix3 viplix3 added the wontfix This will not be worked on label May 31, 2020
@viplix3 viplix3 pinned this issue May 31, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
wontfix This will not be worked on
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Fighting-JJ @viplix3