NPU Usage with OpenCV DNN

I am working in Khadas VIM3.
I ran the yolov5 model as per the instructions from here, but there is little difference in runtime in CPU and NPU. (0.02 - 0.03 seconds)
I don’t understand why like that.
How can I run faster on NPU using dnn, is that possible?
What is the reason for slow running on NPU? I used the yolov5n.onnx model directly without the .nb and .so conversions. Is it slow because I don’t quantify the Onnx model (i.e. model conversion)?

Hi @crackwitz

can you help me?