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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Yolo-v3	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.813 ms	0 - 150 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® X2 Elite	2.418 ms	20 - 20 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® X Elite	4.232 ms	19 - 19 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.245 ms	2 - 175 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS8550 (Proxy)	3.994 ms	0 - 21 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS9075	6.223 ms	5 - 7 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.533 ms	0 - 146 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.391 ms	0 - 54 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X2 Elite	1.615 ms	10 - 10 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X Elite	3.996 ms	10 - 10 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.52 ms	0 - 93 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS6490	526.758 ms	211 - 217 MB	CPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	3.692 ms	0 - 12 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS9075	4.01 ms	2 - 5 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCM6690	260.573 ms	215 - 221 MB	CPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.884 ms	0 - 54 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	237.021 ms	214 - 221 MB	CPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.733 ms	4 - 151 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X2 Elite	2.45 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X Elite	3.697 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.74 ms	0 - 159 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	20.094 ms	0 - 143 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.405 ms	3 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS9075	5.764 ms	5 - 11 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	10.055 ms	4 - 173 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.162 ms	5 - 151 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.375 ms	2 - 53 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	4.068 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.564 ms	36 - 111 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS6490	11.473 ms	1 - 5 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	9.22 ms	0 - 45 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	3.708 ms	2 - 4 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS9075	3.932 ms	1 - 5 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCM6690	36.646 ms	2 - 174 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	4.347 ms	2 - 79 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.904 ms	2 - 51 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.742 ms	2 - 174 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.518 ms	0 - 148 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.685 ms	0 - 187 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8275 (Proxy)	19.981 ms	0 - 146 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.213 ms	0 - 2 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS9075	5.666 ms	0 - 30 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8450 (Proxy)	9.907 ms	0 - 192 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.127 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.