Custom parser for YOLOv3 running on deepstream, in Jetson Nano

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Hi,
I am running Deepstream 7.1 on my Jetson Nano having Jetpack 6.1,
I have trained a YOLO v3 model on NVIDIA TAO.
After converting the onnx file to fp16 using TensorRT, I want to run the model on my Jetson.

Issue faced -
I can not find the objectDetector_Yolo folder in my current deepstream installation on Jetson, which contains the custom lib files for YOLO. I installed the deepstream via tar package.

Alternate method tried -
I tried setting up deepstream on a VM via docker, there i can successfully build my own custom parser (.so) file by which i can run my model.

Please suggest any solution for Jetson Nano.

5

sorry for the late reply! please refer to this faq for yolo samples.

6

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks