Compare results with original yolov4 (mAP)

[philipp-schmidt]

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]

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

[ROBYER1]

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]

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.