YOLOv3 implementation on Drive AGX xavier

Please provide the following info (check/uncheck the boxes after creating this topic):
Software Version
DRIVE OS Linux 5.2.6
[+] DRIVE OS Linux 5.2.6 and DriveWorks 4.0
DRIVE OS Linux 5.2.0
DRIVE OS Linux 5.2.0 and DriveWorks 3.5
NVIDIA DRIVE™ Software 10.0 (Linux)
NVIDIA DRIVE™ Software 9.0 (Linux)
other DRIVE OS version

Target Operating System
[+] Linux

Hardware Platform
[+] NVIDIA DRIVE™ AGX Xavier DevKit (E3550)
NVIDIA DRIVE™ AGX Pegasus DevKit (E3550)

SDK Manager Version

Host Machine Version
[+] native Ubuntu 18.04

Hi Team,
I am trying to implement custom DNN models with Drive OS 5.2.6 + driveworks 4.0.

I went through the sample provided ‘object detection and tracking’. But in the provided sample the DNN gives bboxes and coverage as outputs and then ‘Interpret outputs’ function filters the bboxes.

I tried to follow the yolov3 (tensorrt sample provided). Converted the model in onnx format and later to .bin file uisng tensorrt optimization tool.
The object detection and tracking sample is able to read the yolov3 DNN.

Am confused on how to proceed further. As Yolov3 gives three detection heads which gives output in NCHW format. Each having bboxes and confidence values etc. Do we have to implement all the object thresholding and non max suppression etc by our own?

Thank you,

Dear @nithin.m1,
Yes. You have to implement post processing functions.