ResNet18: Optimized for Qualcomm Devices

ResNet18 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 ResNet18 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 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit ResNet18 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 ResNet18 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: 11.7M
• Model size (float): 44.6 MB
• Model size (w8a8): 11.3 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ResNet18	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.556 ms	0 - 25 MB	NPU
ResNet18	ONNX	float	Snapdragon® X2 Elite	0.517 ms	23 - 23 MB	NPU
ResNet18	ONNX	float	Snapdragon® X Elite	1.165 ms	22 - 22 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.778 ms	0 - 39 MB	NPU
ResNet18	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.065 ms	0 - 25 MB	NPU
ResNet18	ONNX	float	Qualcomm® QCS9075	1.799 ms	1 - 3 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.628 ms	0 - 20 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.347 ms	0 - 26 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X2 Elite	0.33 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X Elite	0.659 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.414 ms	0 - 49 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCS6490	13.69 ms	7 - 23 MB	CPU
ResNet18	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.556 ms	0 - 9 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCS9075	0.654 ms	0 - 3 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCM6690	11.308 ms	6 - 13 MB	CPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.366 ms	0 - 27 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	8.702 ms	8 - 15 MB	CPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.589 ms	1 - 27 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X2 Elite	0.679 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X Elite	1.448 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.91 ms	0 - 35 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	5.827 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.33 ms	1 - 114 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8775P	1.98 ms	1 - 27 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS9075	2.06 ms	1 - 3 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	2.441 ms	0 - 37 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA7255P	5.827 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8295P	2.316 ms	0 - 19 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.698 ms	0 - 23 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.263 ms	0 - 25 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.308 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X Elite	0.621 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.388 ms	0 - 47 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS6490	1.814 ms	2 - 4 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.272 ms	0 - 23 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.525 ms	0 - 2 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8775P	0.702 ms	0 - 25 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS9075	0.623 ms	0 - 2 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCM6690	3.226 ms	0 - 31 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.744 ms	0 - 49 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA7255P	1.272 ms	0 - 23 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8295P	0.915 ms	0 - 21 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.29 ms	0 - 22 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.684 ms	0 - 31 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.588 ms	0 - 31 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.915 ms	0 - 62 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8275 (Proxy)	5.722 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.34 ms	0 - 93 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8775P	1.948 ms	0 - 30 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS9075	2.037 ms	0 - 25 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.468 ms	0 - 63 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA7255P	5.722 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8295P	2.273 ms	0 - 22 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.707 ms	0 - 26 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.228 ms	0 - 26 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.289 ms	0 - 47 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS6490	1.536 ms	0 - 13 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.01 ms	0 - 23 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.385 ms	0 - 1 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8775P	2.032 ms	0 - 24 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS9075	0.478 ms	0 - 13 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCM6690	2.803 ms	0 - 31 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.599 ms	0 - 49 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA7255P	1.01 ms	0 - 23 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8295P	0.752 ms	0 - 20 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.24 ms	0 - 26 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.55 ms	0 - 30 MB	NPU

License

• The license for the original implementation of ResNet18 can be found here.

References

• Deep Residual Learning for Image Recognition
• 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.