WideResNet50: Optimized for Qualcomm Devices

WideResNet50 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 WideResNet50 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 WideResNet50 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 WideResNet50 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: 68.9M
• Model size (float): 263 MB
• Model size (w8a8): 66.6 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
WideResNet50	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.64 ms	1 - 189 MB	NPU
WideResNet50	ONNX	float	Snapdragon® X2 Elite	2.187 ms	132 - 132 MB	NPU
WideResNet50	ONNX	float	Snapdragon® X Elite	4.439 ms	132 - 132 MB	NPU
WideResNet50	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.468 ms	0 - 226 MB	NPU
WideResNet50	ONNX	float	Qualcomm® QCS8550 (Proxy)	4.568 ms	1 - 366 MB	NPU
WideResNet50	ONNX	float	Qualcomm® QCS9075	6.776 ms	1 - 4 MB	NPU
WideResNet50	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.81 ms	0 - 179 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.149 ms	0 - 53 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® X2 Elite	0.819 ms	66 - 66 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® X Elite	1.788 ms	66 - 66 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	1.413 ms	0 - 131 MB	NPU
WideResNet50	ONNX	w8a8	Qualcomm® QCS6490	77.076 ms	10 - 111 MB	CPU
WideResNet50	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.857 ms	0 - 99 MB	NPU
WideResNet50	ONNX	w8a8	Qualcomm® QCS9075	1.929 ms	0 - 3 MB	NPU
WideResNet50	ONNX	w8a8	Qualcomm® QCM6690	61.735 ms	0 - 9 MB	CPU
WideResNet50	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.222 ms	0 - 54 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	57.377 ms	8 - 16 MB	CPU
WideResNet50	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.557 ms	0 - 171 MB	NPU
WideResNet50	QNN_DLC	float	Snapdragon® X2 Elite	2.567 ms	1 - 1 MB	NPU
WideResNet50	QNN_DLC	float	Snapdragon® X Elite	4.666 ms	1 - 1 MB	NPU
WideResNet50	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.656 ms	0 - 223 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	24.488 ms	1 - 173 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	4.843 ms	1 - 297 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® SA8775P	7.156 ms	1 - 169 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® QCS9075	7.098 ms	1 - 3 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	9.219 ms	0 - 198 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® SA7255P	24.488 ms	1 - 173 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® SA8295P	7.831 ms	1 - 152 MB	NPU
WideResNet50	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.96 ms	0 - 174 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.09 ms	0 - 56 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.902 ms	0 - 0 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® X Elite	1.809 ms	0 - 0 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	1.415 ms	0 - 127 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS6490	7.95 ms	2 - 4 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	3.995 ms	0 - 52 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.866 ms	0 - 2 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® SA8775P	2.016 ms	0 - 55 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS9075	1.901 ms	2 - 4 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCM6690	17.229 ms	0 - 214 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	2.515 ms	0 - 127 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® SA7255P	3.995 ms	0 - 52 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® SA8295P	2.766 ms	0 - 51 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.164 ms	0 - 53 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	2.863 ms	0 - 210 MB	NPU
WideResNet50	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.513 ms	0 - 102 MB	NPU
WideResNet50	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.55 ms	0 - 215 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® QCS8275 (Proxy)	23.784 ms	0 - 100 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® QCS8550 (Proxy)	4.75 ms	0 - 2 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® SA8775P	7.04 ms	0 - 101 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® QCS9075	7.057 ms	0 - 134 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® QCS8450 (Proxy)	8.181 ms	0 - 191 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® SA7255P	23.784 ms	0 - 100 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® SA8295P	7.772 ms	0 - 88 MB	NPU
WideResNet50	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.848 ms	0 - 106 MB	NPU
WideResNet50	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.05 ms	0 - 57 MB	NPU
WideResNet50	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	1.329 ms	0 - 131 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS6490	6.887 ms	0 - 68 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	3.762 ms	0 - 52 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.732 ms	0 - 3 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® SA8775P	1.887 ms	0 - 53 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS9075	1.75 ms	0 - 68 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCM6690	17.549 ms	0 - 214 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	2.397 ms	0 - 126 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® SA7255P	3.762 ms	0 - 52 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® SA8295P	2.572 ms	0 - 56 MB	NPU
WideResNet50	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.118 ms	0 - 53 MB	NPU
WideResNet50	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	2.72 ms	0 - 208 MB	NPU

License

• The license for the original implementation of WideResNet50 can be found here.

References

• Wide Residual Networks
• 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.