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	1.857 ms	1 - 152 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® X2 Elite	2.419 ms	176 - 176 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® X Elite	4.152 ms	145 - 145 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.184 ms	3 - 175 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS8550 (Proxy)	4.043 ms	0 - 43 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.523 ms	0 - 150 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS9075	6.177 ms	5 - 50 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS8750	2.523 ms	0 - 150 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS7181	4.152 ms	145 - 145 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.392 ms	0 - 56 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X2 Elite	1.614 ms	179 - 179 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X Elite	3.859 ms	147 - 147 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.581 ms	0 - 91 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS6490	535.991 ms	213 - 219 MB	CPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	3.686 ms	0 - 46 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCM6690	261.116 ms	124 - 130 MB	CPU
Yolo-v3	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	232.703 ms	215 - 222 MB	CPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.878 ms	0 - 51 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS9075	3.982 ms	2 - 48 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS7790	232.703 ms	215 - 222 MB	CPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS8750	1.878 ms	0 - 51 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS7181	3.859 ms	147 - 147 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.663 ms	5 - 152 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X2 Elite	2.453 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X Elite	3.747 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.729 ms	5 - 166 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8275	20.102 ms	1 - 144 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.415 ms	5 - 18 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8775P	5.56 ms	1 - 147 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8650P	5.56 ms	1 - 147 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8255P	5.56 ms	1 - 147 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	10.003 ms	4 - 175 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA7255P	20.102 ms	1 - 144 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8295P	9.182 ms	0 - 151 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.156 ms	5 - 151 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS9075	5.8 ms	5 - 11 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8750	2.156 ms	5 - 151 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS7181	3.747 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	1.391 ms	2 - 54 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.763 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® X Elite	3.998 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.568 ms	2 - 75 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS6490	11.957 ms	4 - 8 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8275	9.204 ms	2 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	3.667 ms	2 - 4 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8775P	4.052 ms	1 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8650P	4.052 ms	1 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8255P	4.052 ms	1 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCM6690	38.503 ms	2 - 174 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA7255P	9.204 ms	2 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.636 ms	2 - 173 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8295P	5.474 ms	0 - 43 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.878 ms	2 - 49 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS9075	3.928 ms	1 - 5 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	4.458 ms	2 - 81 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS7790	4.636 ms	2 - 173 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8750	1.878 ms	2 - 49 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS7181	3.998 ms	2 - 2 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.532 ms	0 - 148 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.672 ms	0 - 187 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8275	19.948 ms	0 - 145 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.214 ms	0 - 2 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8775P	5.496 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8650P	5.496 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8255P	5.496 ms	0 - 150 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8450 (Proxy)	9.914 ms	0 - 196 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA7255P	19.948 ms	0 - 145 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8295P	9.092 ms	0 - 152 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.108 ms	0 - 143 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS9075	5.589 ms	0 - 30 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8750	2.108 ms	0 - 143 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.