EfficientNet-B0: Optimized for Qualcomm Devices

EfficientNetB0 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 EfficientNet-B0 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 1.25.0	Download
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.25.0	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit EfficientNet-B0 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 EfficientNet-B0 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: 5.27M
Model size (float): 20.1 MB
Model size (w8a16): 6.99 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
EfficientNet-B0	ONNX	float	Snapdragon® X2 Elite	0.652 ms	2 - 2 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® X Elite	1.313 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.894 ms	0 - 67 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Gen 1 Mobile	2.869 ms	1 - 77 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.245 ms	1 - 3 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® QCS8450	2.869 ms	1 - 77 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	1.62 ms	1 - 3 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.552 ms	0 - 42 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Elite Mobile	0.699 ms	0 - 37 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.699 ms	0 - 37 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	1.313 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X2 Elite	0.565 ms	1 - 1 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X Elite	1.477 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.947 ms	0 - 83 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	1.671 ms	0 - 84 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	3.858 ms	0 - 3 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.422 ms	0 - 96 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS8450	1.671 ms	0 - 84 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	1.564 ms	0 - 3 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	1.454 ms	0 - 59 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.554 ms	0 - 59 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	5.69 ms	0 - 66 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite Mobile	0.67 ms	0 - 63 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	1.454 ms	0 - 59 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	0.67 ms	0 - 63 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	1.477 ms	6 - 6 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X2 Elite	0.85 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X Elite	1.744 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.072 ms	0 - 60 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	3.593 ms	0 - 73 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8275	4.909 ms	1 - 37 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.559 ms	1 - 30 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8775P	2.01 ms	1 - 39 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8650P	2.01 ms	1 - 39 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8255P	2.01 ms	1 - 39 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8450	3.593 ms	0 - 73 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	1.868 ms	1 - 3 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.612 ms	1 - 42 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA7255P	4.909 ms	1 - 37 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.806 ms	1 - 37 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8295P	3.619 ms	1 - 44 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	0.806 ms	1 - 37 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	1.744 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.803 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X Elite	1.859 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.135 ms	0 - 66 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	1.946 ms	0 - 71 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	5.224 ms	0 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8275	3.294 ms	0 - 47 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.671 ms	0 - 82 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8775P	1.939 ms	0 - 50 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8650P	1.939 ms	0 - 50 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8255P	1.939 ms	0 - 50 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8450	1.946 ms	0 - 71 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	1.781 ms	0 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	1.693 ms	0 - 48 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.638 ms	0 - 51 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	6.519 ms	0 - 164 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA7255P	3.294 ms	0 - 47 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	0.772 ms	0 - 47 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8295P	2.366 ms	0 - 46 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	1.693 ms	0 - 48 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	0.772 ms	0 - 47 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	1.859 ms	0 - 0 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.069 ms	0 - 69 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	3.6 ms	0 - 76 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8275	4.956 ms	0 - 41 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.535 ms	0 - 77 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8775P	2.04 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8650P	2.04 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8255P	2.04 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8450	3.6 ms	0 - 76 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	1.886 ms	0 - 16 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.613 ms	0 - 42 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA7255P	4.956 ms	0 - 41 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite Mobile	0.815 ms	0 - 40 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8295P	3.616 ms	0 - 48 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	0.815 ms	0 - 40 MB	NPU

License

The license for the original implementation of EfficientNet-B0 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/EfficientNet-B0

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Paper • 1905.11946 • Published May 28, 2019 • 4