RegNet: Optimized for Qualcomm Devices

RegNet is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of RegNet 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

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
ONNX	w8a8	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit RegNet on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

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

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for RegNet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

Input resolution: 224x224
Model checkpoint: Imagenet
Model size (float): 58.3 MB
Model size (w8a8): 15.4 MB
Number of parameters: 15.3M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
RegNet	ONNX	float	Snapdragon® X2 Elite	0.907 ms	2 - 2 MB	NPU
RegNet	ONNX	float	Snapdragon® X Elite	1.767 ms	39 - 39 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.238 ms	0 - 130 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Gen 1 Mobile	2.736 ms	0 - 116 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	3.031 ms	0 - 4 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.742 ms	0 - 43 MB	NPU
RegNet	ONNX	float	Qualcomm® QCS8450	2.736 ms	0 - 116 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	2.813 ms	0 - 4 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	1.767 ms	39 - 39 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.995 ms	0 - 76 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Elite Mobile	0.995 ms	0 - 76 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.834 ms	0 - 77 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® X2 Elite	0.471 ms	1 - 1 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® X Elite	0.927 ms	20 - 20 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.637 ms	0 - 136 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Gen 1 Mobile	1.298 ms	0 - 133 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ QCS6490	3.968 ms	0 - 3 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.024 ms	0 - 4 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.9 ms	0 - 157 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCS8450	1.298 ms	0 - 133 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.165 ms	0 - 3 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-X7181	0.927 ms	20 - 20 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ Q-6690	7.242 ms	0 - 206 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ Q-7790	1.154 ms	0 - 87 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ Q-8750	0.547 ms	0 - 88 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.547 ms	0 - 88 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.513 ms	0 - 88 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	1.154 ms	0 - 87 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X2 Elite	1.193 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X Elite	2.295 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.411 ms	0 - 126 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	3.499 ms	0 - 116 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	3.179 ms	1 - 4 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	9.848 ms	1 - 72 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.043 ms	1 - 153 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8775P	3.275 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8650P	3.275 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8255P	3.275 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8450	3.499 ms	0 - 116 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	3.049 ms	1 - 3 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	2.295 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.098 ms	0 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA7255P	9.848 ms	1 - 72 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8295P	3.452 ms	0 - 61 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.098 ms	0 - 74 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.907 ms	1 - 76 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.597 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X Elite	1.052 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.643 ms	0 - 110 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 1 Mobile	1.323 ms	0 - 110 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS6490	4.079 ms	0 - 2 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-8275	0.975 ms	0 - 3 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-8275	2.298 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.87 ms	0 - 27 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8775P	1.295 ms	0 - 81 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8650P	1.295 ms	0 - 81 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8255P	1.295 ms	0 - 81 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8450	1.323 ms	0 - 110 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.126 ms	0 - 2 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-X7181	1.052 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-6690	7.142 ms	0 - 199 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-7790	1.171 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-8750	0.486 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA7255P	2.298 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8295P	1.631 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.486 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.437 ms	0 - 83 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.171 ms	0 - 80 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.395 ms	0 - 152 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	3.475 ms	0 - 137 MB	NPU
RegNet	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	3.173 ms	0 - 42 MB	NPU
RegNet	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	9.88 ms	0 - 89 MB	NPU
RegNet	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.043 ms	0 - 2 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8775P	3.3 ms	0 - 90 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8650P	3.3 ms	0 - 90 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8255P	3.3 ms	0 - 90 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8450	3.475 ms	0 - 137 MB	NPU
RegNet	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	3.072 ms	0 - 42 MB	NPU
RegNet	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.103 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA7255P	9.88 ms	0 - 89 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8295P	3.464 ms	0 - 72 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite Mobile	1.103 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.902 ms	0 - 86 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.514 ms	0 - 118 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	1.11 ms	0 - 115 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS6490	3.84 ms	0 - 22 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	0.843 ms	0 - 23 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.971 ms	0 - 77 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.712 ms	0 - 3 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8775P	1.11 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8650P	1.11 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8255P	1.11 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8450	1.11 ms	0 - 115 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.937 ms	0 - 22 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-6690	6.646 ms	0 - 192 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-7790	1.023 ms	0 - 73 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	0.424 ms	0 - 71 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA7255P	1.971 ms	0 - 77 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8295P	1.43 ms	0 - 72 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.424 ms	0 - 71 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.388 ms	0 - 76 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.023 ms	0 - 73 MB	NPU

License

The license for the original implementation of RegNet can be found here.

References

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.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/RegNet

Designing Network Design Spaces

Paper • 2003.13678 • Published Mar 30, 2020 • 2