bevdet-tensorrt-cpp
bevdet-tensorrt-cpp copied to clipboard
How to do quantization to int8 model of img_stage_lt_d.onnx and bev_stage_lt_d.onnx?
Hey, How to do quantization to int8 model of img_stage_lt_d.onnx and bev_stage_lt_d.onnx? Thanks!
Later I will publish a unified engine model using explicit PTQ quantization, and I am cleaning up the code.
Is there a plan to release the code?
Thanks!