Description
Hello, I have a YOLOv8 ONNX model with dynamic batch_size and an NMS module.
I want to use it to turn it into a TensorRT Engine with INT8. To do this, I need to create a calibration cache. How can I do this? Is there any guide or a python script that runs? Please help me.
Thank you in advance for your help.
Environment
TensorRT Version: 8.6.1
GPU Type: RTX3060
Nvidia Driver Version: nvidia-driver-555
CUDA Version: 11.1
CUDNN Version: 8.0.4
Operating System + Version: Ubuntu 20.04
Python Version (if applicable): 3.8.10
PyTorch Version (if applicable): 1.10.1+cu111
Relevant Files
YOLOv8_m_night.onnx
https://drive.google.com/drive/folders/1D19xWLW5mtTB6IRbmu8g87Y0vFQPZ3C6?usp=drive_link