Skip to content

Rotation is not accurate as R2CNN #46

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
Open
dexception opened this issue Nov 27, 2019 · 4 comments
Open

Rotation is not accurate as R2CNN #46

dexception opened this issue Nov 27, 2019 · 4 comments
Labels
good first issue Good for newcomers

Comments

@dexception
Copy link

I have trained a model but why is the output more than often making a plus sign. So the horizontal detection is coming along with another detection vertically making a plus sign. I don't know why is it happening ?
@yangxue0827
Copy link
Member

can you give me a example result and which cfgs file do you use?

@yangxue0827
Copy link
Member

The 180-degree range may have a plus sign. I'm not sure if it is a visualization problem, but I didn't check it out. This situation is reduced when using large models, and I suspect it is caused by angular periodicity.
@dexception

@yangxue0827 yangxue0827 added the good first issue Good for newcomers label Dec 19, 2019
@yangxue0827
Copy link
Member

yangxue0827 commented Dec 19, 2019 •
edited
Loading

image
Is it like the first line, the other box is suppressed by nms with low NMS_IOU_THRESHOLD = 0.1.

@dexception
Copy link
Author

Like the first picture but 2 detections for each object. One horizontal and one vertical thus making a plus sign. Out of 20 objects 12 are having this plus sign.

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

No branches or pull requests
2 participants
@yangxue0827 @dexception