How to use TensorRT run SegNet(cpp version caffe)?


Sorry, I’m new to TensorRT, and the online tutorial can’t correspond to my TensorRT version.
If I have Caffe version SegNet model (prototxt, model, pascal.png).
How can I transfer Caffe model to ONNX format, and use this onnx build and save engine file?
By the way, how to use engine files to do inference then save semantic segmentation results?
I want to build an engine on ROS (robotic operation system).
Thank for your reading.

Yours faithfully,


TensorRT Version: 7.0.0
GPU Type: RTX2060 super
Nvidia Driver Version: 460.91.03
CUDA Version: 10
CUDNN Version: 7.6.3
Operating System + Version: Ubuntu 18.04
Python Version (if applicable): 3.6.9
TensorFlow Version (if applicable): –
PyTorch Version (if applicable): 1.9.1+cu102
Baremetal or Container (if container which image + tag): –


Hope following may be helpful to you.

Samples about how to use tensorrt.

Thank you.