How to incorporate NvSORT with YoloV5 in deepstream

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) : Jetson AGX Orin 64GB
• DeepStream Version 6.3
• JetPack Version (valid for Jetson only) 5.1.2
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
How to add NvSORT tracker with YOLOv5 model in NvdsAnalytics of Deepstream 6.3. I tried manually changing the config file but it doesn’t seem to be working.

Can you share the config file? Suppose it should work fine with YOLOv5 model.

I had tried to do it on nvdsanalytics_pgie_config.txt as follows:

[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
onnx-file=best_ultra.onnx
model-engine-file=model_b1_gpu0_fp32.engine
#int8-calib-file=calib.table
labelfile-path=labels_test.txt
batch-size=1
network-mode=0
num-detected-classes=1
interval=0
gie-unique-id=1
process-mode=1
network-type=0
cluster-mode=2
maintain-aspect-ratio=1
symmetric-padding=1
#workspace-size=2000
parse-bbox-func-name=NvDsInferParseYolo
#parse-bbox-func-name=NvDsInferParseYoloCuda
custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so
engine-create-func-name=NvDsInferYoloCudaEngineGet

[class-attrs-all]
pre-cluster-threshold=0.25
eps=0.2
group-threshold=1

Am I doing something wrong here? I was able to run it fine using the default models in the config file but not for Yolov5 model.
PS: I am a newbie.

I also tried to add it to the config file of deepstream-app-config.txt of Deepstream-Yolo repo and then the video runs but I cannot see the ROIs which I had specified in the config file of nvdsanalytics .

Can you see the ROI when run default DeepSample: /opt/nvidia/deepstream/deepstream-6.3/sources/apps/sample_apps/deepstream-nvdsanalytics-test/config_nvdsanalytics.txt?

Yes. When I try in deepstream sample app it works. But not in my custom implementation.

Can you compare the nvdsanalytics.txt between the default and yours?