Yolo-v3: Optimized for Qualcomm Devices

YoloV3 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This is based on the implementation of Yolo-v3 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-v3 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Input resolution: 416p (416x416)
• Model checkpoint: YoloV3 Tiny
• Model size (float): 43.9 MB
• Model size (w8a16): 16.9 MB
• Number of parameters: 11.5M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Yolo-v3	ONNX	float	Snapdragon® X2 Elite	2.443 ms	5 - 5 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® X Elite	4.025 ms	20 - 20 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.108 ms	0 - 167 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Gen 1 Mobile	10.477 ms	5 - 195 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	6.807 ms	5 - 8 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.98 ms	0 - 21 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS8450	10.477 ms	5 - 195 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	5.917 ms	5 - 7 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	4.025 ms	20 - 20 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.535 ms	3 - 153 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Elite Mobile	2.535 ms	3 - 153 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.897 ms	1 - 148 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X2 Elite	1.611 ms	2 - 2 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X Elite	3.838 ms	10 - 10 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.523 ms	0 - 88 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	4.559 ms	2 - 88 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	15.125 ms	2 - 5 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.746 ms	0 - 4 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.667 ms	0 - 12 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS8450	4.559 ms	2 - 88 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.859 ms	2 - 5 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.838 ms	10 - 10 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	36.609 ms	2 - 181 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	5.258 ms	2 - 179 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	1.878 ms	1 - 55 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite Mobile	1.878 ms	1 - 55 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.393 ms	0 - 57 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	5.258 ms	2 - 179 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X2 Elite	2.361 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X Elite	3.721 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.731 ms	0 - 162 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	10.021 ms	5 - 174 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	6.201 ms	5 - 12 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	20.102 ms	1 - 144 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.401 ms	5 - 13 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8775P	5.562 ms	2 - 149 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8650P	5.562 ms	2 - 149 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8255P	5.562 ms	2 - 149 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8450	10.021 ms	5 - 174 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	5.356 ms	5 - 11 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	3.721 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.155 ms	0 - 145 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA7255P	20.102 ms	1 - 144 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8295P	9.17 ms	0 - 150 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.155 ms	0 - 145 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.716 ms	5 - 155 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.775 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® X Elite	4.024 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.576 ms	0 - 76 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	4.42 ms	2 - 80 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	14.09 ms	4 - 8 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.78 ms	2 - 7 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	9.193 ms	1 - 46 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.67 ms	2 - 4 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8775P	4.04 ms	0 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8650P	4.04 ms	0 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8255P	4.04 ms	0 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8450	4.42 ms	2 - 80 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	4.532 ms	0 - 4 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	4.024 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	38.483 ms	2 - 173 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	4.653 ms	2 - 172 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	1.877 ms	2 - 53 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA7255P	9.193 ms	1 - 46 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8295P	5.491 ms	0 - 43 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	1.877 ms	2 - 53 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.416 ms	2 - 52 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.653 ms	2 - 172 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.669 ms	0 - 186 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	9.928 ms	0 - 194 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	6.105 ms	0 - 31 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	19.947 ms	0 - 145 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.289 ms	0 - 2 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8775P	5.495 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8650P	5.495 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8255P	5.495 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8450	9.928 ms	0 - 194 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	5.29 ms	0 - 30 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.114 ms	0 - 147 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA7255P	19.947 ms	0 - 145 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8295P	9.057 ms	0 - 152 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite Mobile	2.114 ms	0 - 147 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.537 ms	0 - 149 MB	NPU

License

• The license for the original implementation of Yolo-v3 can be found here.

References

• YOLOv3: An Incremental Improvement
• 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.