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 2.45, ONNX Runtime 1.27.1	Download
ONNX	w8a8	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	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 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:

Input resolution: 224x224
Model checkpoint: Imagenet
Model size (float): 44.6 MB
Model size (w8a8): 11.3 MB
Number of parameters: 11.7M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ResNet18	ONNX	float	Snapdragon® X2 Elite	0.514 ms	2 - 2 MB	NPU
ResNet18	ONNX	float	Snapdragon® X Elite	1.029 ms	23 - 23 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.783 ms	0 - 39 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Gen 1 Mobile	1.834 ms	1 - 40 MB	NPU
ResNet18	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	1.82 ms	1 - 4 MB	NPU
ResNet18	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.044 ms	0 - 25 MB	NPU
ResNet18	ONNX	float	Qualcomm® QCS8450	1.834 ms	1 - 40 MB	NPU
ResNet18	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	1.693 ms	1 - 3 MB	NPU
ResNet18	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	1.029 ms	23 - 23 MB	NPU
ResNet18	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.614 ms	0 - 22 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Elite Mobile	0.614 ms	0 - 22 MB	NPU
ResNet18	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.556 ms	0 - 27 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X2 Elite	0.263 ms	1 - 1 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® X Elite	0.495 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.415 ms	0 - 50 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Gen 1 Mobile	0.763 ms	0 - 54 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® Dragonwing™ QCS6490	1.92 ms	0 - 3 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-8275	0.618 ms	0 - 4 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.55 ms	0 - 14 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® QCS8450	0.763 ms	0 - 54 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.767 ms	0 - 3 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-X7181	0.495 ms	11 - 11 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® Dragonwing™ Q-6690	3.133 ms	0 - 35 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® Dragonwing™ Q-7790	0.649 ms	0 - 34 MB	NPU
ResNet18	ONNX	w8a8	Qualcomm® Dragonwing™ Q-8750	0.358 ms	0 - 30 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.358 ms	0 - 30 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.34 ms	0 - 25 MB	NPU
ResNet18	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	0.649 ms	0 - 34 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X2 Elite	0.658 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® X Elite	1.451 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.915 ms	0 - 35 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	2.43 ms	0 - 37 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	1.869 ms	1 - 4 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5.846 ms	1 - 25 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.324 ms	1 - 2 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8775P	1.941 ms	1 - 26 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8650P	1.941 ms	1 - 26 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8255P	1.941 ms	1 - 26 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® QCS8450	2.43 ms	0 - 37 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	1.819 ms	1 - 3 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	1.451 ms	1 - 1 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	0.709 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA7255P	5.846 ms	1 - 25 MB	NPU
ResNet18	QNN_DLC	float	Qualcomm® SA8295P	2.308 ms	0 - 20 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.709 ms	1 - 24 MB	NPU
ResNet18	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.596 ms	0 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.305 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® X Elite	0.616 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.404 ms	0 - 48 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Gen 1 Mobile	0.745 ms	0 - 52 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS6490	2.034 ms	0 - 2 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-8275	0.621 ms	0 - 3 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.295 ms	0 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.539 ms	0 - 2 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8775P	0.709 ms	0 - 26 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8650P	0.709 ms	0 - 26 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8255P	0.709 ms	0 - 26 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® QCS8450	0.745 ms	0 - 52 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.621 ms	2 - 4 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-X7181	0.616 ms	0 - 0 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-6690	3.239 ms	0 - 33 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-7790	0.675 ms	0 - 32 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-8750	0.316 ms	0 - 27 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA7255P	1.295 ms	0 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Qualcomm® SA8295P	0.96 ms	0 - 22 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.316 ms	0 - 27 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.271 ms	0 - 24 MB	NPU
ResNet18	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.675 ms	0 - 32 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.916 ms	0 - 55 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	2.461 ms	0 - 59 MB	NPU
ResNet18	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	1.859 ms	0 - 26 MB	NPU
ResNet18	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5.873 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.317 ms	0 - 3 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8775P	1.934 ms	0 - 29 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8650P	1.934 ms	0 - 29 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8255P	1.934 ms	0 - 29 MB	NPU
ResNet18	TFLITE	float	Qualcomm® QCS8450	2.461 ms	0 - 59 MB	NPU
ResNet18	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	1.792 ms	0 - 25 MB	NPU
ResNet18	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	0.711 ms	0 - 32 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA7255P	5.873 ms	0 - 27 MB	NPU
ResNet18	TFLITE	float	Qualcomm® SA8295P	2.291 ms	0 - 22 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite Mobile	0.711 ms	0 - 32 MB	NPU
ResNet18	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.592 ms	0 - 31 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.298 ms	0 - 48 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	0.598 ms	0 - 53 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS6490	1.677 ms	0 - 13 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	0.446 ms	0 - 14 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	1.035 ms	0 - 24 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.388 ms	0 - 2 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8775P	0.55 ms	0 - 25 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8650P	0.55 ms	0 - 25 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8255P	0.55 ms	0 - 25 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® QCS8450	0.598 ms	0 - 53 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.518 ms	0 - 13 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-6690	2.807 ms	0 - 31 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-7790	0.547 ms	0 - 31 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	0.246 ms	0 - 22 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA7255P	1.035 ms	0 - 24 MB	NPU
ResNet18	TFLITE	w8a8	Qualcomm® SA8295P	0.753 ms	0 - 21 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.246 ms	0 - 22 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.226 ms	0 - 23 MB	NPU
ResNet18	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.547 ms	0 - 31 MB	NPU

License

The license for the original implementation of ResNet18 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/ResNet18

Deep Residual Learning for Image Recognition

Paper • 1512.03385 • Published Dec 10, 2015 • 17