TensorRT INT8 calibration file C++ implementation

AI & Data Science Deep Learning (Training & Inference) TensorRT
, ,
1

Description

Hello, is there a implementation in C++ to create a calibration file calibration_data.cache, so that you can then use it to create TensorRT Engine with the trtexec command?

Environment

TensorRT Version: 8.6
Nvidia Driver Version: RTX3060
CUDA Version: 11.1
CUDNN Version: 8.0.6
Operating System + Version: Ubuntu 20.04

2

Response updated on Calibration INT8 with `trtexec` · Issue #4044 · NVIDIA/TensorRT · GitHub