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

about loss #61

Open
GanWang opened this issue Nov 2, 2020 · 2 comments
Open

about loss #61

GanWang opened this issue Nov 2, 2020 · 2 comments

Comments

@GanWang
Copy link

GanWang commented Nov 2, 2020

I train this model ，but there is a problem~total loss is not equal detect loss + recognize loss, i choose 2 to train ,i think that total loss should be equal to detect loss + recognize loss.
@GanWang
Copy link
Author

GanWang commented Nov 2, 2020

i have used lama=0.01.

@Pay20Y
Copy link
Owner

Pay20Y commented Nov 19, 2020

Hi, maybe it's because there is regularization in the loss.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Pay20Y @GanWang