I think the reason is TensorRT 7.1.3 didn’t support ReverseSequence op but in the following topic it said TensorRT support
ReverseSequence?
If it didn’t support ReverseSequence how to add a customer layer for C++ API. Does it have any sample for adding plugin on ONNX to TensorRT with C++?
Or just following step
Environment
TensorRT Version : 7.1.3 GPU Type : Jetson TX2 iGPU Nvidia Driver Version : CUDA Version : 10.2 CUDNN Version : 8 Operating System + Version : Ubuntu 18.04