Express Computer
Home  »  Artificial Intelligence AI  »  Accelerating YOLOv8 Object Detection Model on AIxBoard with OpenVINO™

Accelerating YOLOv8 Object Detection Model on AIxBoard with OpenVINO™

0 33,127

01 Introduction

AIxBoard using OpenVINO™

Download the example code repository and set up the development environment for YOLOv8 with OpenVINO™ inference engine. Use the following command to clone the code repository:

git clone

02 Exporting YOLOv8 Object Detection OpenVINO™ IR Model

YOLOv8 has five different object detection models trained on the COCO dataset.

Start by exporting the YOLOv8n.onnx model using the command:

yolo export format=onnx


This will generate the yolov8n.onnx model.

mo -m yolov8n.onnx –compress_to_fp16

Next, optimize and export the OpenVINO™ IR format model with FP16 precision using the command:

03 Testing the Inference Performance of YOLOv8 Object Detection Model with benchmark_app

benchmark_app is a performance testing tool provided by the OpenVINO™ toolkit for evaluating the inference performance of AI models. It allows testing the pure AI model inference performance without pre- or post-processing in synchronous or asynchronous mode.

Use the command:

benchmark_app -m yolov8n.xml -d GPU

This will provide the asynchronous inference performance of the yolov8n.xml model on the integrated GPU of the AIxBoard.

04 Writing YOLOv8 Object Detection Model Inference Program with OpenVINO™ Python API

Open yolov8n.onnx using Netron, as shown in the figure below. The input shape of the model is [1,3,640,640], and the output shape is [1,84,8400]. The “84” represents the cx, cy, h, w, and scores for 80 classes. “8400” indicates the number of output cells for the three detection heads in YOLOv8 when the image size is 640 (80×80+40×40+20×20=8400).

Here’s an example program for YOLOv8 object detection model using the OpenVINO™ Python API:

The core source code is as follows:

The running result of `` is shown in the following image:

05 Conclusion

By leveraging the integrated GPU of the AIxBoard and utilizing OpenVINO™, impressive performance can be achieved with the YOLOv8 object detection model. Asynchronous processing and the use of AsyncInferQueue can further improve the utilization of the compute device and increase the throughput of AI inference programs.

Get real time updates directly on you device, subscribe now.

Leave A Reply

Your email address will not be published.

LIVE Webinar

Digitize your HR practice with extensions to success factors

Join us for a virtual meeting on how organizations can use these extensions to not just provide a better experience to its’ employees, but also to significantly improve the efficiency of the HR processes
India's Leading e-Governance Summit is here!!! Attend and Know more.
Register Now!
Attend Webinar & Enhance Your Organisation's Digital Experience.
Register Now
Enable A Truly Seamless & Secure Workplace.
Register Now
Attend Inida's Largest BFSI Technology Conclave!
Register Now
Know how to protect your company in digital era.
Register Now
Protect Your Critical Assets From Well-Organized Hackers
Register Now
Find Solutions to Maintain Productivity
Register Now
Live Webinar : Improve customer experience with Voice Bots
Register Now
Live Event: Technology Day- Kerala, E- Governance Champions Awards
Register Now
Virtual Conference : Learn to Automate complex Business Processes
Register Now