FPS is low in Jetson nano while using yolo4 person detection

YOLO4 based Real time person detection is slow in Windows 10 CPU. I can get approximately 4 FPS. So I used Jetson nano to improve FPS. I have installed opencv 4.4.0 and it is compiled with CUDA. Still FPS is low (0.3 FPS). I suspect jetson is not using its GPU. How to overcome this issue?

First, the Jetson Nano is a low-end device, don’t expect it to perform miracles.

Anyway, did you check if Yolo is running on the CPU or the GPU? (use nvidia-smi to check the GPU useage)

I suggest to use the original framework instead of OpenCV. Darknet has OpenCV bindings, so you can pass cv::Mat images for processing (just make sure to enable OpenCV when compiling). And it is well optimized for CUDA.

I am getting below error when nvidia-smi is given in terminal. How to rectify it?

bash: nvidia-smi: command not found