Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • Users
  • Groups
Collapse
Brand Logo

ModalAI Forum

  1. ModalAI Support Forum
  2. Ask your questions right here!
  3. YOLOv8 with NPU (VOXL2 Mini)

YOLOv8 with NPU (VOXL2 Mini)

Scheduled Pinned Locked Moved Ask your questions right here!
2 Posts 2 Posters 236 Views
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • Y Offline
    Y Offline
    yashpyrrhus
    wrote on last edited by
    #1

    Dear Dev Team,

    My goal is to run the yolov8s-oiv model on the NPU. I've quantized the model to INT8 following this method:

    from ultralytics import YOLO
    model = YOLO('yolov8s-oiv7.pt')
    model.export(format='tflite', int8=True, data='dataset.yaml', imgsz=640, nms=False, single_cls=False)
    

    where dataset.yaml provides details to the calibration dataset.

    When I run the quantized model on the VOXL2 Mini (SDK 1.6.3), it silently falls back to the CPU. I have edited the voxl-tflite-server.conf file to set delegate to nnapi.

    I'd really appreciate any inputs on the best practices for quantizing YOLOv8 for the NPU, and references to relevant documentation. I also wished to run a sanity check to ensure the NPU works, can you please provide some quantized models that I can use to verify a functional NPU?

    Thanks,
    Yash

    F 1 Reply Last reply
    0
    • Y yashpyrrhus

      Dear Dev Team,

      My goal is to run the yolov8s-oiv model on the NPU. I've quantized the model to INT8 following this method:

      from ultralytics import YOLO
      model = YOLO('yolov8s-oiv7.pt')
      model.export(format='tflite', int8=True, data='dataset.yaml', imgsz=640, nms=False, single_cls=False)
      

      where dataset.yaml provides details to the calibration dataset.

      When I run the quantized model on the VOXL2 Mini (SDK 1.6.3), it silently falls back to the CPU. I have edited the voxl-tflite-server.conf file to set delegate to nnapi.

      I'd really appreciate any inputs on the best practices for quantizing YOLOv8 for the NPU, and references to relevant documentation. I also wished to run a sanity check to ensure the NPU works, can you please provide some quantized models that I can use to verify a functional NPU?

      Thanks,
      Yash

      F Offline
      F Offline
      fhaltmayer
      wrote on last edited by
      #2

      Adding onto this, is there a way to get the server to log out which operations/how many operations were delegated to the CPU? I believe its something that the tflite interpreter can spit out and would be super useful when trying to figure out why a model isnt loading correctly.

      1 Reply Last reply
      0

      Hello! It looks like you're interested in this conversation, but you don't have an account yet.

      Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.

      With your input, this post could be even better 💗

      Register Login
      Reply
      • Reply as topic
      Log in to reply
      • Oldest to Newest
      • Newest to Oldest
      • Most Votes


      ModalAI
      Categories Recent Tags ModalAI.com Docs
      © 2026 ModalAI® · Accelerating autonomy for smaller, smarter, safer drones · Powered by NodeBB
      • Login

      • Don't have an account? Register

      • Login or register to search.
      • First post
        Last post
      0
      • Categories
      • Recent
      • Tags
      • Popular
      • Users
      • Groups