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 1.25.0	Download
ONNX	w8a8	Universal	QAIRT 2.45, ONNX Runtime 1.25.0	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
RegNet	ONNX	float	Snapdragon® X2 Elite	0.915 ms	2 - 2 MB	NPU
RegNet	ONNX	float	Snapdragon® X Elite	1.768 ms	39 - 39 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.235 ms	0 - 126 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Gen 1 Mobile	2.726 ms	0 - 116 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.738 ms	0 - 68 MB	NPU
RegNet	ONNX	float	Qualcomm® QCS8450	2.726 ms	0 - 116 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	2.803 ms	0 - 4 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.835 ms	0 - 77 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Elite Mobile	0.996 ms	0 - 76 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.996 ms	0 - 76 MB	NPU
RegNet	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	1.768 ms	39 - 39 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® X2 Elite	0.473 ms	1 - 1 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® X Elite	0.931 ms	20 - 20 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.633 ms	0 - 134 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Gen 1 Mobile	1.3 ms	0 - 134 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ QCS6490	3.792 ms	0 - 3 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.904 ms	0 - 26 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCS8450	1.3 ms	0 - 134 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.547 ms	0 - 91 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	1.166 ms	0 - 87 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.508 ms	0 - 89 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.162 ms	0 - 3 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ Q-6690	7.239 ms	0 - 206 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ Q-7790	1.166 ms	0 - 87 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ Q-8750	0.547 ms	0 - 91 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-X7181	0.931 ms	20 - 20 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X2 Elite	1.211 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X Elite	2.254 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.406 ms	0 - 126 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	3.481 ms	0 - 115 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8275	9.847 ms	1 - 72 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.053 ms	1 - 33 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8775P	3.264 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8650P	3.264 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8255P	3.264 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8450	3.481 ms	0 - 115 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	3.041 ms	1 - 3 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.893 ms	1 - 76 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA7255P	9.847 ms	1 - 72 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.106 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8295P	3.464 ms	0 - 61 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.106 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	2.254 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.576 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X Elite	1.054 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.637 ms	0 - 111 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 1 Mobile	1.313 ms	0 - 112 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS6490	4.13 ms	0 - 2 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8275	2.312 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.884 ms	0 - 8 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8775P	1.301 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8650P	1.301 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8255P	1.301 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8450	1.313 ms	0 - 112 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.481 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.178 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.443 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.119 ms	0 - 2 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-6690	7.109 ms	0 - 199 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA7255P	2.312 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8295P	1.601 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-7790	1.178 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-8750	0.481 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-X7181	1.054 ms	0 - 0 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.397 ms	0 - 148 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	3.47 ms	0 - 137 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8275	9.882 ms	0 - 89 MB	NPU
RegNet	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.037 ms	0 - 7 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8775P	3.315 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8650P	3.315 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8255P	3.315 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8450	3.47 ms	0 - 137 MB	NPU
RegNet	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	3.036 ms	0 - 42 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.901 ms	0 - 86 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA7255P	9.882 ms	0 - 89 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite Mobile	1.105 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8295P	3.461 ms	0 - 72 MB	NPU
RegNet	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.105 ms	0 - 92 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.548 ms	0 - 118 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	1.111 ms	0 - 119 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS6490	3.918 ms	0 - 22 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8275	1.976 ms	0 - 75 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.708 ms	0 - 2 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8775P	1.119 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8650P	1.119 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8255P	1.119 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8450	1.111 ms	0 - 119 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.442 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.988 ms	0 - 73 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.394 ms	0 - 77 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.958 ms	0 - 22 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-6690	6.627 ms	0 - 193 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA7255P	1.976 ms	0 - 75 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8295P	1.418 ms	0 - 72 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-7790	0.988 ms	0 - 73 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	0.442 ms	0 - 79 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