Testing sample_object_detector_tracker on 6.0.8 fails

[0xdeadbeef]

Please provide the following info (tick the boxes after creating this topic):
Software Version
DRIVE OS 6.0.8.1
DRIVE OS 6.0.6
DRIVE OS 6.0.5
DRIVE OS 6.0.4 (rev. 1)
DRIVE OS 6.0.4 SDK
other

Target Operating System
Linux
QNX
other

Hardware Platform
DRIVE AGX Orin Developer Kit (940-63710-0010-300)
DRIVE AGX Orin Developer Kit (940-63710-0010-200)
DRIVE AGX Orin Developer Kit (940-63710-0010-100)
DRIVE AGX Orin Developer Kit (940-63710-0010-D00)
DRIVE AGX Orin Developer Kit (940-63710-0010-C00)
DRIVE AGX Orin Developer Kit (not sure its number)
other

SDK Manager Version
1.9.3.10904
other

Host Machine Version
native Ubuntu Linux 20.04 Host installed with SDK Manager
native Ubuntu Linux 20.04 Host installed with DRIVE OS Docker Containers
native Ubuntu Linux 18.04 Host installed with DRIVE OS Docker Containers
other

Hi ,

I am using the sample example for dnn in 6.0.8 sample_object_detector_tracker. Can nvidia say what is the tensorrt model they used for testing this ? I see there is YoloV3 incorporated into, so the default tensorRT_model.bin is not working as expected. can Nvidia point me to the right model used to test yolo with this sample.

Regards,
Sistla.

[VickNV]

Thank you for reaching out. To better assist you, could you please provide more details about the issue you’re experiencing with the default ‘tensorRT_model.bin’ in the ‘sample_object_detector_tracker’ example? Specifically, if you could explain what isn’t working as expected and any error messages or observations you’ve encountered, it would help us pinpoint the issue more accurately.

[SivaRamaKrishnaNV]

Dear @0xdeadbeef ,
Could you check /usr/local/driveworks/data/samples/detector for model. May I know the error details? Are you running the sample on host or target?

[SivaRamaKrishnaNV]

Dear @0xdeadbeef,
I have verified the sample and notice no issue on target. I coped the input video file and model file to target from docker and ran using below command.

File paths on docker

input video: /usr/local/driveworks/data/samples/sfm/triangulation/video_0.h264 
Model : :/usr/local/driveworks/data/samples/detector/ampere-integrated/tensorRT_model.bin
Json file : /usr/local/driveworks/data/samples/detector/ampere-integrated/tensorRT_model.bin.json (It is used by sample internally)

Command

./sample_object_detector_tracker --video=/home/nvidia/video_0.h264 --tensorRT_model=/home/nvidia/tensorRT_model.bin