Tiny Yolo v3 Frame Rate

Hi, I’m running Tiny Yolo v3 using: GitHub - pjreddie/darknet: Convolutional Neural Networks , but I’m only getting 3-5 FPS.

According to this document: https://developer.nvidia.com/embedded/jetson-benchmarks , I should be seeing a much higher FPS.

I am running in max power mode.

I would appreciate it if anyone has any thoughts as to why my FPS is so low. Thanks


You will need to inference it with TensorRT for optimized performance.
Here are two approaches to do this:

1. Use darknet YOLOv3 with Deepstream

2. Use ONNX YOLOv3 with TensorRT API