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	2.439 ms	5 - 5 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® X Elite	4.032 ms	20 - 20 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.11 ms	1 - 165 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Gen 1 Mobile	10.535 ms	5 - 196 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	6.815 ms	5 - 8 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.978 ms	0 - 21 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS8450	10.535 ms	5 - 196 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	5.878 ms	5 - 7 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	4.032 ms	20 - 20 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.541 ms	0 - 150 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Elite Mobile	2.541 ms	0 - 150 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.897 ms	2 - 150 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X2 Elite	1.608 ms	2 - 2 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X Elite	3.815 ms	10 - 10 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.527 ms	0 - 84 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	4.58 ms	2 - 89 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	14.985 ms	2 - 5 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.734 ms	0 - 4 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.658 ms	0 - 160 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS8450	4.58 ms	2 - 89 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	3.815 ms	10 - 10 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	39.275 ms	4 - 182 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	5.185 ms	2 - 179 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	1.883 ms	0 - 54 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite Mobile	1.883 ms	0 - 54 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.393 ms	1 - 58 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	5.185 ms	2 - 179 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X2 Elite	2.344 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X Elite	3.735 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.745 ms	0 - 161 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	10.039 ms	5 - 176 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	6.197 ms	5 - 12 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	20.099 ms	1 - 144 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.4 ms	3 - 27 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8775P	5.598 ms	1 - 147 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8650P	5.598 ms	1 - 147 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8255P	5.598 ms	1 - 147 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8450	10.039 ms	5 - 176 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	5.367 ms	5 - 11 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	3.735 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.182 ms	0 - 141 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA7255P	20.099 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	2.182 ms	0 - 141 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.716 ms	5 - 152 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.785 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® X Elite	3.996 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.566 ms	2 - 75 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	4.44 ms	2 - 80 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	13.987 ms	2 - 6 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.781 ms	1 - 6 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	9.185 ms	1 - 45 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.676 ms	2 - 4 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8775P	4.05 ms	1 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8650P	4.05 ms	1 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8255P	4.05 ms	1 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8450	4.44 ms	2 - 80 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.819 ms	2 - 6 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.996 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	36.382 ms	4 - 175 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	4.666 ms	2 - 172 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	1.885 ms	2 - 49 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA7255P	9.185 ms	1 - 45 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8295P	5.471 ms	0 - 43 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	1.885 ms	2 - 49 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.415 ms	2 - 51 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.666 ms	2 - 172 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.678 ms	0 - 187 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	9.951 ms	0 - 194 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	6.113 ms	0 - 31 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	19.948 ms	0 - 145 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.311 ms	0 - 151 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8775P	5.516 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8650P	5.516 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8255P	5.516 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8450	9.951 ms	0 - 194 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	5.276 ms	0 - 30 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.125 ms	0 - 146 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA7255P	19.948 ms	0 - 145 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8295P	9.072 ms	0 - 152 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite Mobile	2.125 ms	0 - 146 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.601 ms	0 - 148 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.