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:

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

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 Mobile	26.831 ms	6 - 317 MB	NPU
Yolo-R	ONNX	float	Snapdragon® X2 Elite	26.317 ms	75 - 75 MB	NPU
Yolo-R	ONNX	float	Snapdragon® X Elite	58.027 ms	74 - 74 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Gen 3 Mobile	42.086 ms	3 - 350 MB	NPU
Yolo-R	ONNX	float	Qualcomm® QCS8550 (Proxy)	55.271 ms	0 - 79 MB	NPU
Yolo-R	ONNX	float	Qualcomm® QCS9075	52.914 ms	5 - 12 MB	NPU
Yolo-R	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	37.053 ms	3 - 225 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	18.077 ms	3 - 437 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® X2 Elite	18.366 ms	41 - 41 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® X Elite	30.452 ms	40 - 40 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	21.1 ms	0 - 484 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® QCS6490	2312.799 ms	127 - 140 MB	CPU
Yolo-R	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	29.569 ms	0 - 50 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® QCS9075	29.381 ms	1 - 6 MB	NPU
Yolo-R	ONNX	w8a16	Qualcomm® QCM6690	1175.834 ms	131 - 148 MB	CPU
Yolo-R	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	17.133 ms	1 - 372 MB	NPU
Yolo-R	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	1121.546 ms	132 - 144 MB	CPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	14.056 ms	5 - 296 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® X2 Elite	15.16 ms	5 - 5 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® X Elite	29.373 ms	5 - 5 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	22.716 ms	5 - 324 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	100.159 ms	0 - 252 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	29.704 ms	5 - 7 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA8775P	36.154 ms	1 - 260 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® QCS9075	37.31 ms	5 - 11 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	49.96 ms	5 - 377 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA7255P	100.159 ms	0 - 252 MB	NPU
Yolo-R	QNN_DLC	float	Qualcomm® SA8295P	44.027 ms	0 - 306 MB	NPU
Yolo-R	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	18.433 ms	0 - 229 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	7.29 ms	2 - 303 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® X2 Elite	8.333 ms	2 - 2 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® X Elite	18.972 ms	2 - 2 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	12.307 ms	0 - 368 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® QCS6490	77.531 ms	1 - 5 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	18.378 ms	2 - 4 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8775P	18.336 ms	0 - 289 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® QCS9075	20.48 ms	0 - 5 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® QCM6690	234.681 ms	2 - 400 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	24.66 ms	2 - 369 MB	NPU
Yolo-R	QNN_DLC	w8a16	Qualcomm® SA8295P	23.548 ms	0 - 291 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	9.839 ms	2 - 301 MB	NPU
Yolo-R	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	26.209 ms	2 - 312 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.