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

YOLO detection false negative #114

Open
Bibiw1 opened this issue Aug 27, 2018 · 4 comments
Open

YOLO detection false negative #114

Bibiw1 opened this issue Aug 27, 2018 · 4 comments

Comments

@Bibiw1
Copy link

Bibiw1 commented Aug 27, 2018

Hello.
I launched yolo detection with video stream(IP-camera).
Picture:
image
There's two cars, but algorithm detected only one.
Can I tune program to fix it? Help me plz

@BlcaKHat
Copy link

if you want a perfect one, then you have to train one for yourself. read about threshold, and confidence. it can also help.
but at the end algorithm can't do everything, for practical scenario, you have to take care of image, size of object, exposure are and all that.

@Bibiw1
Copy link
Author

Bibiw1 commented Aug 31, 2018

okay, thank you.
I am asking about, maybe, settings of algorithm, like sensetivity. i want to decrease false negative by false positives. hope you can undestand me

@AvinoamK
Copy link

Try to change the values of some parameters in yolo3.cfg, for example
ignore_thresh, which is 0.7 by default.

@Bibiw1
Copy link
Author

Bibiw1 commented Aug 31, 2018

Thank you, I'll try it

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

3 participants