Yolo-v6: Optimized for Qualcomm Devices

YoloV6 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This is based on the implementation of Yolo-v6 found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

See our repository for Yolo-v6 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Model checkpoint: YoloV6-N
• Input resolution: 640x640
• Number of parameters: 4.68M
• Model size (float): 17.9 MB
• Model size (w8a8): 4.68 MB
• Model size (w8a16): 5.03 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Yolo-v6	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.997 ms	5 - 172 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® X2 Elite	3.72 ms	14 - 14 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® X Elite	8.29 ms	14 - 14 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.534 ms	5 - 206 MB	NPU
Yolo-v6	ONNX	float	Qualcomm® QCS8550 (Proxy)	8.312 ms	0 - 17 MB	NPU
Yolo-v6	ONNX	float	Qualcomm® QCS9075	9.68 ms	5 - 7 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.314 ms	3 - 171 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.838 ms	0 - 188 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® X2 Elite	2.006 ms	4 - 4 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® X Elite	4.481 ms	3 - 3 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.657 ms	0 - 225 MB	NPU
Yolo-v6	ONNX	w8a16	Qualcomm® QCS6490	285.924 ms	41 - 46 MB	CPU
Yolo-v6	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	4.136 ms	2 - 5 MB	NPU
Yolo-v6	ONNX	w8a16	Qualcomm® QCS9075	4.853 ms	2 - 5 MB	NPU
Yolo-v6	ONNX	w8a16	Qualcomm® QCM6690	149.651 ms	41 - 50 MB	CPU
Yolo-v6	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	2.077 ms	2 - 185 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	128.473 ms	45 - 53 MB	CPU
Yolo-v6	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	3.038 ms	1 - 159 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® X2 Elite	3.052 ms	5 - 5 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® X Elite	6.2 ms	5 - 5 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	4.528 ms	0 - 180 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	15.902 ms	0 - 153 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	6.06 ms	5 - 6 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® SA8775P	7.631 ms	1 - 157 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® QCS9075	7.794 ms	5 - 11 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	8.86 ms	4 - 183 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® SA7255P	15.902 ms	0 - 153 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® SA8295P	9.103 ms	0 - 153 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	3.204 ms	0 - 156 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.928 ms	2 - 43 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.358 ms	2 - 2 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® X Elite	2.459 ms	2 - 2 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.521 ms	2 - 56 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS6490	6.665 ms	1 - 5 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	5.343 ms	0 - 37 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	2.205 ms	2 - 4 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® SA8775P	2.724 ms	0 - 40 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS9075	2.545 ms	2 - 6 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCM6690	17.992 ms	2 - 153 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	2.829 ms	2 - 58 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® SA7255P	5.343 ms	0 - 37 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® SA8295P	3.382 ms	0 - 36 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.138 ms	2 - 44 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	2.758 ms	2 - 153 MB	NPU
Yolo-v6	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.368 ms	0 - 166 MB	NPU
Yolo-v6	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	4.419 ms	0 - 191 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® QCS8275 (Proxy)	16.281 ms	0 - 163 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® QCS8550 (Proxy)	6.298 ms	0 - 11 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® SA8775P	7.686 ms	0 - 164 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® QCS9075	7.821 ms	0 - 18 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® QCS8450 (Proxy)	9.382 ms	0 - 192 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® SA7255P	16.281 ms	0 - 163 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® SA8295P	9.132 ms	0 - 161 MB	NPU
Yolo-v6	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	3.744 ms	0 - 163 MB	NPU

License

• The license for the original implementation of Yolo-v6 can be found here.

References

• YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
• 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.