Yolov3 on jetson nano 2gb, deepstream 5.0

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

• Hardware Platform (Jetson / GPU) = Jetson nano 2gb
• DeepStream Version = Deepstrea5.0
• JetPack Version (valid for Jetson only) =
• TensorRT Version = libnvinfer_plugin.so.7.1.3
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) Question

I have tested yolov3 (coco dataset) with deepstream 5.0 (C++ plugin), I am getting a 5-6 FPS, I want to trigger a GPIO when ever a dog or a person is detected.
Also can i improve the FPS without compensating with the accuracy.

3

you may could try TLT yolov3 - GitHub - NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream to improve the fps