FastDeploy/examples/vision/detection/yolov8

English | 简体中文

YOLOv8 Ready-to-deploy Model

• The deployment of the YOLOv8 model is based on YOLOv8 and Pre-trained Model Based on COCO
  • （1）The *.onnx provided by Official Repository can be deployed directly；
  • （2）The YOLOv8 model trained by personal data should employ export.py in YOLOv8 to export the ONNX files for deployment.

Download Pre-trained ONNX Model

For developers' testing, models exported by YOLOv8 are provided below. Developers can download them directly. (The accuracy in the following table is derived from the source official repository)

Model	Size	Accuracy	Note
YOLOv8n	12.1MB	37.3%	This model file is sourced from YOLOv8，GPL-3.0 License
YOLOv8s	42.6MB	44.9%	This model file is sourced from YOLOv8，GPL-3.0 License
YOLOv8m	98.8MB	50.2%	This model file is sourced from YOLOv8，GPL-3.0 License
YOLOv8l	166.7MB	52.9%	This model file is sourced from YOLOv8，GPL-3.0 License
YOLOv8x	260.3MB	53.9%	This model file is sourced from YOLOv8，GPL-3.0 License

Detailed Deployment Documents

• Python Deployment
• C++ Deployment

Release Note

• Document and code are based on YOLOv8