I encountered a error after several runs, not the first run.
ERROR: …/nvdsinfer/nvdsinfer_func_utils.cpp:33 [TRT]: INVALID_CONFIG: The engine plan file is not compatible with this version of TensorRT, expecting library version 7.2.3 got 7.2.1, please rebuild.
It is a mystery.
My engine model is transformed by tlt tlt-converter. So, the version of TensorRT is automatically 7.2.1. How to generate a model with the version 7.2.3?
Make sure TensorRT used for building engine and TensorRT used when run deepstream app are the same.
besides, please provide below info:
Hardware Platform (Jetson / GPU)
DeepStream Version
JetPack Version (valid for Jetson only)
TensorRT Version
NVIDIA GPU Driver Version (valid for GPU only)