yolov8's tensorRT int8 quantization

[mattherdelma]

How to implement yolov8's tensorRT int8 quantization?

[FeiYull]

@mattherdelma @lyb36524 He made a FP16 quantification of the ONNX model, through the following instructions: ./trtexec --onnx=yolov8n.onnx --saveEngine=yolov8n_fp16.trt --fp16 --buildOnly --minShapes=images:1x3x640x640 --optShapes=images:4x3x640x640 --maxShapes=images:8x3x640x640 Other instructions are the same as in the link： The figure below is the time overhead, the test device is Nvidia RTX4090, the BATCH_SIZE = 8：

FP32：

FP16：

More quantitative tutorials, we will update in the future