TensorRT SDK on Jetson Device


I just installed DeepStream 6.2 on my Jetson Device (Orin NX) and it is working fine. I even tried to run Yolo models on it and the results are amazing. However, I would like to know how Do I use TensorRT SDK separately to try the same Yolo models? I wonder if there is any documentation about it?


1 Like

This link might help you.

1 Like

Thank you so much @rajupadhyay59 . However, is there any Documentation to using TensorRT and python? I mean, I would like to implement my projects using Python. And as a matter of fact, I have TensorRT installed already. Do I need to install the TensorRT SDK, something like: <nv-tensorrt-local-repo-ubuntu2004-8.5.2-cuda-11.8_1.0-1_arm64.deb>

No, TensorRT is already installed when you flash your Jetson with Jetpack, so you are good to go with your TensorRT

W.r.t python, I am unsure but maybe this could help?

There is an example with yolov3 so, use that as reference.
You can compare the c++ with python and make sense out of it.

Sorry for the late reply, Is this still an DeepStream issue to support? Thanks!

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.