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

Compare results with original yolov4 (mAP) #7

Open
philipp-schmidt opened this issue Sep 22, 2020 · 3 comments
Open

Compare results with original yolov4 (mAP) #7

philipp-schmidt opened this issue Sep 22, 2020 · 3 comments
Labels
help wanted Extra attention is needed

Comments

@philipp-schmidt
Copy link
Contributor

I want to compare the results of our network with the original yolov4 to make sure we get the same accuracy and qualitative results. There could be mistakes or differences in the pre- and postprocessing that I want to rule out.

Optimally we would check its mAP like described in darknet and compare the results.

If anyone feels like implementing this into the existing python client I would gladly accept the PR and mention you in the README.

Also simply checking if we get the same resulting BoundingBoxes for a few images would be a nice start to check if there are differences.

@philipp-schmidt philipp-schmidt added the help wanted Extra attention is needed label Sep 22, 2020
@philipp-schmidt
Copy link
Contributor Author

Postprocessing has been fixed in v1.3.0. Initial results look very similar to default yolov4.
Further testing is needed though.

@ROBYER1
Copy link

ROBYER1 commented Jan 6, 2021

Postprocessing has been fixed in v1.3.0. Initial results look very similar to default yolov4.
Further testing is needed though.

Once confirmed, can the fix be shared with jkjung here and does the fix also benefit Yolo-v3-tiny? jkjung-avt/tensorrt_demos#237

@philipp-schmidt
Copy link
Contributor Author

Hi,
the fix I used for v1.3.0 is not necessary in jkjungs implementation as he confirmed: jkjung-avt/tensorrt_demos#315

I will have to implement mAP checks natively in C++ (directly with TensorRT exec) and Python client to compare with and without triton deployment and then crosscheck implementations with jkjung and wang-xinyu to compare with native darknet results.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
help wanted Extra attention is needed
Development

No branches or pull requests

2 participants