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	3.994 ms	5 - 172 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® 8 Elite Mobile	4.307 ms	0 - 170 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® X2 Elite	3.763 ms	14 - 14 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® X Elite	8.303 ms	14 - 14 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® X Elite	8.303 ms	14 - 14 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.491 ms	5 - 203 MB	NPU
Yolo-v6	ONNX	float	Qualcomm® QCS8550 (Proxy)	8.055 ms	0 - 36 MB	NPU
Yolo-v6	ONNX	float	Qualcomm® QCS9075	9.667 ms	5 - 8 MB	NPU
Yolo-v6	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.307 ms	0 - 170 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.838 ms	0 - 187 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® 8 Elite Mobile	2.083 ms	0 - 181 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® X2 Elite	2.0 ms	4 - 4 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® X Elite	4.473 ms	3 - 3 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® X Elite	4.473 ms	3 - 3 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.655 ms	0 - 225 MB	NPU
Yolo-v6	ONNX	w8a16	Qualcomm® QCS6490	285.768 ms	40 - 45 MB	CPU
Yolo-v6	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	4.088 ms	0 - 7 MB	NPU
Yolo-v6	ONNX	w8a16	Qualcomm® QCS9075	4.863 ms	2 - 5 MB	NPU
Yolo-v6	ONNX	w8a16	Qualcomm® QCM6690	148.18 ms	42 - 50 MB	CPU
Yolo-v6	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	2.083 ms	0 - 181 MB	NPU
Yolo-v6	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	129.709 ms	48 - 57 MB	CPU
Yolo-v6	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	129.709 ms	48 - 57 MB	CPU
Yolo-v6	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	3.387 ms	1 - 158 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® 8 Elite Mobile	3.761 ms	5 - 161 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® X2 Elite	3.474 ms	5 - 5 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® X Elite	6.537 ms	5 - 5 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® X Elite	6.537 ms	5 - 5 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	4.435 ms	0 - 180 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	16.25 ms	0 - 154 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	6.19 ms	5 - 6 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® SA8775P	7.7 ms	2 - 159 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® SA8775P	7.7 ms	2 - 159 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® SA8775P	7.7 ms	2 - 159 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® QCS9075	7.705 ms	5 - 11 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	9.137 ms	4 - 181 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® SA7255P	16.25 ms	0 - 154 MB	NPU
Yolo-v6	QNN_DLC	float	Qualcomm® SA8295P	9.026 ms	0 - 152 MB	NPU
Yolo-v6	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	3.761 ms	5 - 161 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.906 ms	1 - 43 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	1.11 ms	2 - 45 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.286 ms	2 - 2 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® X Elite	2.362 ms	2 - 2 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® X Elite	2.362 ms	2 - 2 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.431 ms	2 - 56 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS6490	6.63 ms	2 - 6 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	5.069 ms	1 - 39 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	2.102 ms	2 - 4 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® SA8775P	2.6 ms	1 - 41 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® SA8775P	2.6 ms	1 - 41 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® SA8775P	2.6 ms	1 - 41 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS9075	2.533 ms	2 - 6 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCM6690	17.391 ms	2 - 153 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	2.782 ms	2 - 58 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® SA7255P	5.069 ms	1 - 39 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Qualcomm® SA8295P	3.273 ms	0 - 36 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.11 ms	2 - 45 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	3.304 ms	2 - 153 MB	NPU
Yolo-v6	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	3.304 ms	2 - 153 MB	NPU
Yolo-v6	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.376 ms	0 - 165 MB	NPU
Yolo-v6	TFLITE	float	Snapdragon® 8 Elite Mobile	3.731 ms	0 - 162 MB	NPU
Yolo-v6	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	4.439 ms	0 - 188 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® QCS8275 (Proxy)	16.262 ms	0 - 162 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® QCS8550 (Proxy)	6.341 ms	0 - 64 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® SA8775P	7.697 ms	0 - 164 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® SA8775P	7.697 ms	0 - 164 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® SA8775P	7.697 ms	0 - 164 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® QCS9075	7.826 ms	0 - 18 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® QCS8450 (Proxy)	9.419 ms	0 - 185 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® SA7255P	16.262 ms	0 - 162 MB	NPU
Yolo-v6	TFLITE	float	Qualcomm® SA8295P	9.092 ms	0 - 161 MB	NPU
Yolo-v6	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	3.731 ms	0 - 162 MB	NPU

License

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

References

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.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/Yolo-v6

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

Paper • 2209.02976 • Published Sep 7, 2022