Accelerate Onnx Model

Hello everyone,

I am trying to accelerate my onnx model. Now my speed is very slow. Is there anyone who faced this problem and solved this problem? If yes, can you explain the solution?

@umutt What model is your onnx, and how slow is it? What are your conversion parameters?

Hello Frank,

I am working on YOLOX + ByteTrack. On my computer, my solution works at about 15 fps. But when I worked on Edge-V Pro, codes work at about 1 fps. You can see the code that generates Onnx model from torch.

@umutt Edge don’t have NPU, you just run your model in CPU. Speed ​​is very slow

@Frank which board should be preferred for Yolo models in Khadas Products?

@umutt Just vim3 and vim3l support NPU

@Frank do you have any information about FPS? 15 fps is possible for Yolo- on vim3 or vim3l?

@umutt Both yolov2 and tiny series can reach 15FPS