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 2.42, ONNX Runtime 1.25.0	Download
ONNX	w8a8	Universal	QAIRT 2.42, 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® 8 Elite Gen 5 Mobile	0.831 ms	1 - 82 MB	NPU
RegNet	ONNX	float	Snapdragon® X2 Elite	0.905 ms	212 - 212 MB	NPU
RegNet	ONNX	float	Snapdragon® X Elite	1.778 ms	181 - 181 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.231 ms	0 - 131 MB	NPU
RegNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.748 ms	0 - 54 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.006 ms	0 - 78 MB	NPU
RegNet	ONNX	float	Qualcomm® QCS9075	2.881 ms	1 - 46 MB	NPU
RegNet	ONNX	float	Qualcomm® QCS8750	1.006 ms	0 - 78 MB	NPU
RegNet	ONNX	float	Qualcomm® QCS7181	1.778 ms	181 - 181 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.499 ms	0 - 90 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® X2 Elite	0.482 ms	212 - 212 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® X Elite	0.933 ms	149 - 149 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.638 ms	0 - 138 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCS6490	27.759 ms	7 - 18 MB	CPU
RegNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.894 ms	0 - 48 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	13.704 ms	8 - 18 MB	CPU
RegNet	ONNX	w8a8	Qualcomm® QCM6690	17.837 ms	7 - 16 MB	CPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.543 ms	0 - 89 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCS9075	1.084 ms	0 - 45 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCS7790	13.704 ms	8 - 18 MB	CPU
RegNet	ONNX	w8a8	Qualcomm® QCS8750	0.543 ms	0 - 89 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCS7181	0.933 ms	149 - 149 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.891 ms	1 - 77 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X2 Elite	1.199 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X Elite	2.259 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.406 ms	0 - 125 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8275	9.839 ms	1 - 72 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.086 ms	1 - 127 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8775P	3.274 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8650P	3.274 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8255P	3.274 ms	1 - 74 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	3.512 ms	0 - 116 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8295P	3.478 ms	0 - 61 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.104 ms	0 - 73 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA7255P	9.839 ms	1 - 72 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS9075	3.037 ms	3 - 5 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8750	1.104 ms	0 - 73 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS7181	2.259 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.44 ms	0 - 83 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.565 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X Elite	1.049 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.619 ms	0 - 111 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS6490	2.607 ms	0 - 2 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8275	2.298 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.911 ms	0 - 37 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8775P	1.284 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8650P	1.284 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8255P	1.284 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA7255P	2.298 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.173 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8295P	1.61 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCM6690	7.133 ms	0 - 199 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.491 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS9075	1.051 ms	2 - 4 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.304 ms	0 - 113 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS7790	1.173 ms	0 - 80 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8750	0.491 ms	0 - 82 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS7181	1.049 ms	0 - 0 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.889 ms	0 - 93 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.409 ms	0 - 152 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8275	9.867 ms	0 - 89 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.065 ms	0 - 8 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8775P	3.288 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8650P	3.288 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8255P	3.288 ms	0 - 92 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	3.474 ms	0 - 137 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8295P	3.462 ms	0 - 72 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.103 ms	0 - 93 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA7255P	9.867 ms	0 - 89 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS9075	3.051 ms	0 - 42 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8750	1.103 ms	0 - 93 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.393 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.532 ms	1 - 121 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS6490	2.359 ms	0 - 22 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8275	2.061 ms	0 - 76 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.711 ms	0 - 7 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8775P	1.108 ms	0 - 78 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8650P	1.108 ms	0 - 78 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8255P	1.108 ms	0 - 78 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA7255P	2.061 ms	0 - 76 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.976 ms	0 - 73 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8295P	1.406 ms	0 - 72 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCM6690	6.636 ms	0 - 192 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.42 ms	0 - 71 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS9075	0.865 ms	0 - 22 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.12 ms	0 - 109 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS7790	0.976 ms	0 - 73 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8750	0.42 ms	0 - 71 MB	NPU

License

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

References

• Designing Network Design Spaces
• 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.