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 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.19.1	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	2.639 ms	1 - 189 MB	NPU
WideResNet50	ONNX	float	Snapdragon® X2 Elite	2.207 ms	132 - 132 MB	NPU
WideResNet50	ONNX	float	Snapdragon® X Elite	4.434 ms	132 - 132 MB	NPU
WideResNet50	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.471 ms	0 - 227 MB	NPU
WideResNet50	ONNX	float	Qualcomm® QCS8550 (Proxy)	4.577 ms	0 - 41 MB	NPU
WideResNet50	ONNX	float	Qualcomm® QCS9075	6.781 ms	0 - 4 MB	NPU
WideResNet50	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.814 ms	0 - 168 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.153 ms	0 - 52 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® X2 Elite	0.839 ms	66 - 66 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® X Elite	1.801 ms	66 - 66 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	1.401 ms	0 - 129 MB	NPU
WideResNet50	ONNX	w8a8	Qualcomm® QCS6490	78.276 ms	10 - 109 MB	CPU
WideResNet50	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.85 ms	0 - 83 MB	NPU
WideResNet50	ONNX	w8a8	Qualcomm® QCS9075	1.922 ms	0 - 3 MB	NPU
WideResNet50	ONNX	w8a8	Qualcomm® QCM6690	61.406 ms	8 - 17 MB	CPU
WideResNet50	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.228 ms	0 - 52 MB	NPU
WideResNet50	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	57.337 ms	8 - 17 MB	CPU
WideResNet50	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.54 ms	0 - 172 MB	NPU
WideResNet50	QNN_DLC	float	Snapdragon® X2 Elite	2.528 ms	1 - 1 MB	NPU
WideResNet50	QNN_DLC	float	Snapdragon® X Elite	4.743 ms	1 - 1 MB	NPU
WideResNet50	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.655 ms	0 - 228 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	24.583 ms	1 - 175 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	4.857 ms	1 - 3 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® SA8775P	7.183 ms	1 - 170 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® QCS9075	7.084 ms	1 - 3 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	9.194 ms	0 - 199 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® SA7255P	24.583 ms	1 - 175 MB	NPU
WideResNet50	QNN_DLC	float	Qualcomm® SA8295P	7.914 ms	1 - 153 MB	NPU
WideResNet50	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	3.018 ms	0 - 175 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.088 ms	0 - 53 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.898 ms	0 - 0 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® X Elite	1.785 ms	0 - 0 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	1.43 ms	0 - 127 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS6490	7.731 ms	0 - 2 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	3.973 ms	0 - 51 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.86 ms	0 - 2 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® SA8775P	2.014 ms	0 - 52 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS9075	1.906 ms	0 - 2 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCM6690	17.897 ms	0 - 212 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	2.525 ms	0 - 127 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® SA7255P	3.973 ms	0 - 51 MB	NPU
WideResNet50	QNN_DLC	w8a8	Qualcomm® SA8295P	2.746 ms	0 - 54 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.146 ms	0 - 50 MB	NPU
WideResNet50	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	2.868 ms	0 - 207 MB	NPU
WideResNet50	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.504 ms	0 - 118 MB	NPU
WideResNet50	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.547 ms	0 - 253 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® QCS8275 (Proxy)	23.655 ms	0 - 115 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® QCS8550 (Proxy)	4.766 ms	0 - 2 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® SA8775P	7.036 ms	0 - 115 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® QCS9075	7.063 ms	0 - 134 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® QCS8450 (Proxy)	8.207 ms	0 - 231 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® SA7255P	23.655 ms	0 - 115 MB	NPU
WideResNet50	TFLITE	float	Qualcomm® SA8295P	7.679 ms	0 - 104 MB	NPU
WideResNet50	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.851 ms	0 - 119 MB	NPU
WideResNet50	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.047 ms	0 - 55 MB	NPU
WideResNet50	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	1.306 ms	0 - 130 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS6490	6.767 ms	0 - 68 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	3.726 ms	0 - 52 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.723 ms	0 - 2 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® SA8775P	1.906 ms	0 - 52 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS9075	1.741 ms	0 - 68 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCM6690	18.699 ms	0 - 212 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	2.396 ms	0 - 133 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® SA7255P	3.726 ms	0 - 52 MB	NPU
WideResNet50	TFLITE	w8a8	Qualcomm® SA8295P	2.588 ms	0 - 50 MB	NPU
WideResNet50	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.115 ms	0 - 55 MB	NPU
WideResNet50	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	2.74 ms	0 - 211 MB	NPU

License

The license for the original implementation of WideResNet50 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/WideResNet50

Wide Residual Networks

Paper • 1605.07146 • Published May 23, 2016 • 2