Yolo-R: Optimized for Qualcomm Devices

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

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

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Input resolution: 640x640
• Model checkpoint: yolor_p6
• Model size (float): 17.9 MB
• Number of parameters: 4.68M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Yolo-R	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	25.765 ms	1 - 190 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	27.099 ms	3 - 188 MB	NPU
Yolo-R	ONNX	float	Snapdragon® X2 Elite	35.909 ms	5 - 5 MB	NPU
Yolo-R	ONNX	float	Snapdragon® X Elite	40.33 ms	72 - 72 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Gen 3 Mobile	32.364 ms	6 - 253 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Gen 1 Mobile	54.675 ms	1 - 305 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	49.729 ms	5 - 13 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	40.984 ms	0 - 77 MB	NPU
Yolo-R	ONNX	float	Qualcomm® QCS8450	54.675 ms	1 - 305 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	47.783 ms	5 - 13 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	40.33 ms	72 - 72 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ Q-8750	27.099 ms	3 - 188 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	14.486 ms	1 - 328 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	13.576 ms	1 - 320 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® X2 Elite	15.19 ms	2 - 2 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® X Elite	23.229 ms	37 - 37 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	15.874 ms	3 - 393 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	30.311 ms	0 - 389 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	21.484 ms	1 - 7 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	22.502 ms	0 - 40 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® QCS8450	30.311 ms	0 - 389 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	23.232 ms	1 - 6 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	23.229 ms	37 - 37 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	34.113 ms	3 - 307 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	13.576 ms	1 - 320 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	34.113 ms	3 - 307 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	24.446 ms	5 - 196 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	20.795 ms	0 - 186 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® X2 Elite	27.008 ms	5 - 5 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® X Elite	32.207 ms	5 - 5 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	25.728 ms	3 - 243 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	50.503 ms	5 - 304 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	40.83 ms	5 - 13 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	33.138 ms	5 - 7 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA8650P	61.374 ms	1 - 197 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA8255P	61.374 ms	1 - 197 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® QCS8450	50.503 ms	5 - 304 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	40.378 ms	5 - 12 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	32.207 ms	5 - 5 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	20.795 ms	0 - 186 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	5.742 ms	2 - 314 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	7.405 ms	2 - 307 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® X2 Elite	7.006 ms	2 - 2 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® X Elite	16.026 ms	2 - 2 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	9.927 ms	2 - 369 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	23.072 ms	2 - 370 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	56.763 ms	2 - 7 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	13.89 ms	2 - 8 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	15.086 ms	2 - 5 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8650P	15.488 ms	1 - 310 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8255P	15.488 ms	1 - 310 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® QCS8450	23.072 ms	2 - 370 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	15.503 ms	1 - 6 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	16.026 ms	2 - 2 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	153.244 ms	2 - 341 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	21.917 ms	2 - 318 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	7.405 ms	2 - 307 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8295P	19.92 ms	0 - 301 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	21.917 ms	2 - 318 MB	NPU

License

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

References

• You Only Learn One Representation: Unified Network for Multiple Tasks
• 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.