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 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	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® 8 Elite Gen 5 Mobile	0.548 ms	0 - 43 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® X2 Elite	0.675 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® X Elite	1.457 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.897 ms	0 - 65 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.261 ms	0 - 15 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® QCS9075	1.627 ms	1 - 3 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.696 ms	0 - 44 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.55 ms	0 - 58 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X2 Elite	0.573 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X Elite	1.649 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.946 ms	0 - 85 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS6490	113.457 ms	45 - 48 MB	CPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	1.419 ms	0 - 126 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS9075	1.612 ms	0 - 3 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCM6690	48.891 ms	44 - 53 MB	CPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.667 ms	0 - 51 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	42.104 ms	42 - 52 MB	CPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.61 ms	1 - 44 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X2 Elite	0.876 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X Elite	1.785 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.082 ms	0 - 63 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	4.901 ms	1 - 38 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.568 ms	1 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8775P	2.053 ms	0 - 42 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS9075	1.865 ms	3 - 5 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	3.617 ms	0 - 73 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA7255P	4.901 ms	1 - 38 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8295P	3.674 ms	0 - 46 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.819 ms	0 - 43 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.643 ms	0 - 48 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.809 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X Elite	1.9 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.143 ms	0 - 66 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS6490	4.063 ms	0 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	3.321 ms	0 - 45 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	1.685 ms	0 - 81 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8775P	1.969 ms	0 - 49 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS9075	1.855 ms	0 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCM6690	6.512 ms	0 - 164 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	1.95 ms	0 - 66 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA7255P	3.321 ms	0 - 45 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8295P	2.44 ms	0 - 43 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.786 ms	0 - 44 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	1.714 ms	0 - 46 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.613 ms	0 - 50 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.07 ms	4 - 75 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8275 (Proxy)	4.902 ms	0 - 46 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.571 ms	0 - 3 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8775P	2.071 ms	0 - 50 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS9075	1.877 ms	0 - 16 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8450 (Proxy)	3.61 ms	0 - 87 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA7255P	4.902 ms	0 - 46 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8295P	3.685 ms	0 - 52 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.822 ms	0 - 45 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