Running my custom trained yolo v8n model on ROS (on Jetson Orin nano)

Autonomous Machines Jetson & Embedded Systems Jetson Orin Nano
1

Hello,
I am using the following page(
GitHub - dusty-nv/ros_deep_learning: Deep learning inference nodes for ROS / ROS2 with support for NVIDIA Jetson and TensorRT
) to learn about running DNN models on ROS as a plugin. I want to run my custom trained YOLO v8 model on ROS. Please guide me how can I plugin or call the yolo object detection model on ROS.
Thank you in advance
Regards

3

Hi @anshbhatia07.nitt, you could look into these projects that support ROS and YOLO:

4

Thank you very much sir for your response. In the second link (https://github.com/indra4837/yolov4_trt_ros) , how can we use yolo v8 model instead of yolo v4 since v8 and v4 has a lot of difference.

In your github page, https://github.com/NVIDIA-AI-IOT/YOLOv5-with-Isaac-ROS/tree/main what are the files which I need to modify and plugin my Yolo v8 model python file to plugin my model in ROS. Kindly guide me sir. I would be grateful to you.
Thank you in advance.
Best Regards

5

@anshbhatia07.nitt I don’t have experience with those projects, you would need to dig into them for your personal uses. You could also just create a ROS node around the YOLOv8 inferencing code you already have. If you haven’t created a ROS node before, I would start there in the ROS documentation. There are also a number of other projects that implement ROS nodes for YOLO models:

http://wiki.ros.org/darknet_ros

7

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