Yolov5 on Xavier NX

[emurtha]

Hello All!

First I’ll admit I’m a bit of a newb when it comes to building binaries and the like. I’ve used unix in a past life and I’m now working on getting Yolov5 (I’d even setting for Yolo3 at this point).

I was looking for general guidance on how to approach this. I did try a few times and typically run into problems with OpenCV (compiling for arm64).

Has anyone had success here that can share some experience and / or workflow?

Many thanks,

[AastaLLL]

Hi,

Sorry that we don’t have an official sample for the YOLOv5 on the Jetson device.
But some of our user have successfully deployed it on the Xavier NX through docker.

Please check this topic for the details:

YOLOv5 Repo on Xavier?

Hello, I have been using darknet YOLOv3 to perform object detection from an RTSP source on my Xavier. YOLOv5 is supposed to be much faster but not supported by darknet. I followed the detect.py example for YOLOv5 on https://github.com/ultralytics/yolov5 but cannot get past some python dependancies espcially nump/scipy incompatibility. Has anyone gotten these repo instructions to work on Xavier/Nano? TIA pip3 install --user --upgrade scipy ERROR: Command errored out with exit status 1: /usr/bi…

Thanks.