I want to use onnx runtime for quantisation of yolo v11 model to reduce the weights and activations, maintain the accuracy from the original, decrese it from 32 bit float to 16bit int and 8 bit int. I want to see this from the scratch with the code and after performing quantization how did the code change and how did the results change.
provide me with the source codes, readme and everything required
This is a duplicate of Yolo11 quantization