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.

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

Question about angle? #3

Open
ilwoonam75 opened this issue Dec 20, 2021 · 4 comments
Open

Question about angle? #3

ilwoonam75 opened this issue Dec 20, 2021 · 4 comments

Comments

@ilwoonam75
Copy link

ilwoonam75 commented Dec 20, 2021

Sorry to bother you again.

I succeeded training with cube dataset with your help.

And I am trying to train my own dataset.
I want to detect the rotated vehicle.

This time I am little confused with the angle.

I think you use 0 to 90 angle because the cube is square. right?

But because vehicle is rectangle, I think I cannot express the angle between 0 and 90.

So I changed the angle between 0 and 180, and correct the source code to train 0 and 180 angle.

But the mAP doesn't increase at all.

Can you advice me how to train?

@thohemp
Copy link
Owner

thohemp commented Dec 20, 2021

I also trained with 180 degrees before I reduced them to 90 for your already mentioned reason.

Did you take a look at this commit?
cc9a40b

This was the change from 180 to 90 degrees.

@ilwoonam75
Copy link
Author

Do you mean that you changed the max angle from 180 to 90 because you got the good result?

@thohemp
Copy link
Owner

thohemp commented Dec 20, 2021

As far as I remember 180 worked out for me, too, but I expected to archieve more stable results with 90 degrees.

@ilwoonam75
Copy link
Author

Okay. I will try again. Thank you

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants