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® X2 Elite	27.665 ms	5 - 5 MB	NPU
Yolo-R	ONNX	float	Snapdragon® X Elite	45.733 ms	72 - 72 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Gen 3 Mobile	35.31 ms	2 - 251 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Gen 1 Mobile	72.486 ms	6 - 319 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	53.852 ms	5 - 13 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	45.465 ms	0 - 98 MB	NPU
Yolo-R	ONNX	float	Qualcomm® QCS8450	72.486 ms	6 - 319 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	52.038 ms	5 - 12 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	45.733 ms	72 - 72 MB	NPU
Yolo-R	ONNX	float	Qualcomm® Dragonwing™ Q-8750	30.915 ms	3 - 197 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Elite Mobile	30.915 ms	3 - 197 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	27.852 ms	2 - 202 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® X2 Elite	15.428 ms	2 - 2 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® X Elite	23.694 ms	37 - 37 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	15.967 ms	2 - 398 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	31.953 ms	0 - 400 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	21.61 ms	1 - 7 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	22.431 ms	0 - 41 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® QCS8450	31.953 ms	0 - 400 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	25.428 ms	1 - 6 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	23.694 ms	37 - 37 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	47.717 ms	3 - 320 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	13.649 ms	1 - 333 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Elite Mobile	13.649 ms	1 - 333 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	14.577 ms	1 - 344 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	47.717 ms	3 - 320 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® X2 Elite	18.14 ms	5 - 5 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® X Elite	51.907 ms	5 - 5 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	40.884 ms	4 - 257 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	66.259 ms	5 - 312 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	57.99 ms	5 - 12 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	124.927 ms	1 - 198 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	55.571 ms	5 - 7 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA8775P	61.39 ms	1 - 198 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA8650P	61.39 ms	1 - 198 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA8255P	61.39 ms	1 - 198 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® QCS8450	66.259 ms	5 - 312 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	61.466 ms	5 - 11 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	51.907 ms	5 - 5 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	22.545 ms	0 - 194 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA7255P	124.927 ms	1 - 198 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Elite Mobile	22.545 ms	0 - 194 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	19.121 ms	5 - 209 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® X2 Elite	7.058 ms	2 - 2 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® X Elite	16.207 ms	2 - 2 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	10.005 ms	2 - 381 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	25.325 ms	2 - 382 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	64.881 ms	3 - 7 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	14.018 ms	2 - 7 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	32.603 ms	1 - 311 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	15.22 ms	2 - 6 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8775P	15.484 ms	0 - 310 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8650P	15.484 ms	0 - 310 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8255P	15.484 ms	0 - 310 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® QCS8450	25.325 ms	2 - 382 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	15.853 ms	2 - 7 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	16.207 ms	2 - 2 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	175.679 ms	2 - 342 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	21.501 ms	2 - 326 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	7.386 ms	2 - 321 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA7255P	32.603 ms	1 - 311 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8295P	20.832 ms	0 - 312 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	7.386 ms	2 - 321 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	5.859 ms	2 - 327 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	21.501 ms	2 - 326 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.