Oh no! Where's the JavaScript?
Your Web browser does not have JavaScript enabled or does not support JavaScript. Please enable JavaScript on your Web browser to properly view this Web site, or upgrade to a Web browser that does support JavaScript.
Navigation
Member Polls
whats your favorite language
  1. Home
  2. Discussion Forum
  3. ML and AI
  4. Best AI models for object detection on edge devices?

Best AI models for object detection on edge devices?

Last updated on 2 hours ago
ai programs
ML and AI
Track threadPrint
K
KevinSenior Member
Posted 2 hours ago
#1
Username: EdgeComputing101
Posted: 1 week ago
I'm working on a project that needs real-time object detection on a jetson nano. Currently using yolov5 but wondering if there are better options now in 2024? Need something that can handle at least 15fps with decent accuracy. Power consumption is also a concern since this will run 24/7. What are you guys using for similar projects?
K
KevinSenior Member
Posted 2 hours ago
#2
Reply by: MLEnthusiast
Have you looked at YOLOv8? It's way more efficient than v5 and the accuracy is better too. I'm getting around 20fps on my jetson nano with the small model. Also check out the tensorrt optimization, it made a huge difference for me - almost doubled my framerate. There's also some newer models like YOLO-NAS that are supposed to be even better but i havent tested them personally.
You can view all discussion threads in this forum.
You cannot start a new discussion thread in this forum.
You cannot reply in this discussion thread.
You cannot start on a poll in this forum.
You cannot upload attachments in this forum.
You cannot download attachments in this forum.
Sign In
Not a member yet? Click here to register.
Forgot Password?
Users Online Now
Guests Online 6
Members Online 0
Total Members: 19
Newest Member: bokovac