YOLOv8-Segmentation: Optimized for Mobile Deployment

Real-time object segmentation optimized for mobile and edge by Ultralytics

Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes, segmentation masks and classes of objects in an image.

This model is an implementation of YOLOv8-Segmentation found here.

More details on model performance across various devices, can be found here.

Model Details

• Model Type: Semantic segmentation
• Model Stats:
  • Model checkpoint: YOLOv8N-Seg
  • Input resolution: 640x640
  • Number of parameters: 3.43M
  • Model size: 13.2 MB
  • Number of output classes: 80

Model	Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
YOLOv8-Segmentation	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	4.951 ms	5 - 7 MB	FP16	NPU	--
YOLOv8-Segmentation	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	7.858 ms	14 - 39 MB	FP16	NPU	--
YOLOv8-Segmentation	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	3.571 ms	5 - 24 MB	FP16	NPU	--
YOLOv8-Segmentation	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	5.469 ms	7 - 68 MB	FP16	NPU	--
YOLOv8-Segmentation	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	4.159 ms	5 - 52 MB	FP16	NPU	--
YOLOv8-Segmentation	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	4.665 ms	15 - 64 MB	FP16	NPU	--
YOLOv8-Segmentation	SA7255P ADP	SA7255P	QNN	90.376 ms	1 - 10 MB	FP16	NPU	--
YOLOv8-Segmentation	SA8255 (Proxy)	SA8255P Proxy	QNN	4.999 ms	5 - 8 MB	FP16	NPU	--
YOLOv8-Segmentation	SA8295P ADP	SA8295P	QNN	9.161 ms	0 - 14 MB	FP16	NPU	--
YOLOv8-Segmentation	SA8650 (Proxy)	SA8650P Proxy	QNN	4.947 ms	5 - 7 MB	FP16	NPU	--
YOLOv8-Segmentation	SA8775P ADP	SA8775P	QNN	8.042 ms	0 - 10 MB	FP16	NPU	--
YOLOv8-Segmentation	QCS8275 (Proxy)	QCS8275 Proxy	QNN	90.376 ms	1 - 10 MB	FP16	NPU	--
YOLOv8-Segmentation	QCS8550 (Proxy)	QCS8550 Proxy	QNN	4.967 ms	5 - 7 MB	FP16	NPU	--
YOLOv8-Segmentation	QCS9075 (Proxy)	QCS9075 Proxy	QNN	8.042 ms	0 - 10 MB	FP16	NPU	--
YOLOv8-Segmentation	QCS8450 (Proxy)	QCS8450 Proxy	QNN	9.35 ms	5 - 38 MB	FP16	NPU	--
YOLOv8-Segmentation	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	5.405 ms	5 - 5 MB	FP16	NPU	--
YOLOv8-Segmentation	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	7.902 ms	17 - 17 MB	FP16	NPU	--

License

• The license for the original implementation of YOLOv8-Segmentation can be found here.
• The license for the compiled assets for on-device deployment can be found here

References

• Ultralytics YOLOv8 Docs: Instance Segmentation
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.

Usage and Limitations

Model may not be used for or in connection with any of the following applications:

• Accessing essential private and public services and benefits;
• Administration of justice and democratic processes;
• Assessing or recognizing the emotional state of a person;
• Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
• Education and vocational training;
• Employment and workers management;
• Exploitation of the vulnerabilities of persons resulting in harmful behavior;
• General purpose social scoring;
• Law enforcement;
• Management and operation of critical infrastructure;
• Migration, asylum and border control management;
• Predictive policing;
• Real-time remote biometric identification in public spaces;
• Recommender systems of social media platforms;
• Scraping of facial images (from the internet or otherwise); and/or
• Subliminal manipulation