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 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	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	0.835 ms	1 - 87 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Elite Mobile	0.999 ms	0 - 85 MB	NPU
RegNet	ONNX	float	Snapdragon® X2 Elite	0.902 ms	39 - 39 MB	NPU
RegNet	ONNX	float	Snapdragon® X Elite	1.975 ms	39 - 39 MB	NPU
RegNet	ONNX	float	Snapdragon® X Elite	1.975 ms	39 - 39 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.248 ms	0 - 136 MB	NPU
RegNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.749 ms	0 - 56 MB	NPU
RegNet	ONNX	float	Qualcomm® QCS9075	2.848 ms	0 - 4 MB	NPU
RegNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.999 ms	0 - 85 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.511 ms	0 - 90 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.548 ms	0 - 92 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® X2 Elite	0.499 ms	20 - 20 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.657 ms	0 - 138 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCS6490	27.566 ms	8 - 22 MB	CPU
RegNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.894 ms	0 - 27 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCS9075	1.102 ms	0 - 3 MB	NPU
RegNet	ONNX	w8a8	Qualcomm® QCM6690	18.274 ms	9 - 18 MB	CPU
RegNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.548 ms	0 - 92 MB	NPU
RegNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	13.74 ms	8 - 18 MB	CPU
RegNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	13.74 ms	8 - 18 MB	CPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.894 ms	1 - 78 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.104 ms	0 - 74 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X2 Elite	1.212 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X Elite	2.28 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® X Elite	2.28 ms	1 - 1 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.402 ms	0 - 126 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	9.852 ms	1 - 72 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	2.082 ms	1 - 156 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8775P	3.27 ms	0 - 73 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8775P	3.27 ms	0 - 73 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8775P	3.27 ms	0 - 73 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS9075	3.055 ms	3 - 5 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	3.516 ms	0 - 114 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA7255P	9.852 ms	1 - 72 MB	NPU
RegNet	QNN_DLC	float	Qualcomm® SA8295P	3.468 ms	0 - 61 MB	NPU
RegNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.104 ms	0 - 74 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.433 ms	0 - 81 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.483 ms	0 - 77 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.566 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X Elite	1.058 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® X Elite	1.058 ms	0 - 0 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.634 ms	0 - 109 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS6490	2.631 ms	2 - 4 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	2.281 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.865 ms	0 - 2 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8775P	1.282 ms	0 - 81 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8775P	1.282 ms	0 - 81 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8775P	1.282 ms	0 - 81 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS9075	1.04 ms	2 - 4 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCM6690	7.099 ms	0 - 198 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.301 ms	0 - 111 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA7255P	2.281 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Qualcomm® SA8295P	1.628 ms	0 - 77 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.483 ms	0 - 77 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.176 ms	0 - 78 MB	NPU
RegNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.176 ms	0 - 78 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.897 ms	0 - 93 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite Mobile	1.104 ms	0 - 94 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.373 ms	0 - 153 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	9.865 ms	0 - 89 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	2.081 ms	0 - 3 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8775P	3.274 ms	0 - 91 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8775P	3.274 ms	0 - 91 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8775P	3.274 ms	0 - 91 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS9075	3.033 ms	0 - 42 MB	NPU
RegNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	3.468 ms	0 - 138 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA7255P	9.865 ms	0 - 89 MB	NPU
RegNet	TFLITE	float	Qualcomm® SA8295P	3.476 ms	0 - 72 MB	NPU
RegNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.104 ms	0 - 94 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.384 ms	0 - 79 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.434 ms	0 - 82 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.527 ms	0 - 121 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS6490	2.358 ms	0 - 22 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.994 ms	0 - 76 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.709 ms	0 - 3 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8775P	1.109 ms	0 - 78 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8775P	1.109 ms	0 - 78 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8775P	1.109 ms	0 - 78 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS9075	0.865 ms	0 - 22 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCM6690	6.627 ms	0 - 192 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.116 ms	0 - 110 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA7255P	1.994 ms	0 - 76 MB	NPU
RegNet	TFLITE	w8a8	Qualcomm® SA8295P	1.434 ms	0 - 72 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.434 ms	0 - 82 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.978 ms	0 - 73 MB	NPU
RegNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.978 ms	0 - 73 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.