How to write C++ code use UFF model with tensorrt on Xaiver

Autonomous Machines Jetson & Embedded Systems Jetson AGX Xavier
1

I was able to successfully convert lanenet (GitHub - MaybeShewill-CV/lanenet-lane-detection: Unofficial implemention of lanenet model for real time lane detection using deep neural network model https://maybeshewill-cv.github.io/lanenet-lane-detection/) model to uff. However, I do not how to use the uff model to run inference. I have been reading Jetson-Inference on github, but still do not know how to write the C++ code. What I want to process a live video feed and for each frame, output an instance image and a binary image.

2

Hi,

You can check the following folder for the C++ code of uff model:
/usr/src/tensorrt/samples/sampleUffMNIST

Thanks.

3

Yes, I found it. Thanks.

I also find a executable “trtexec” which can run uff mode directly. However, I am little confused how to use this exe on commandline. My network input is an image and the output is another image. How can I run trtexec?