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 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	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	0.668 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® X Elite	1.462 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.897 ms	1 - 65 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.266 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	0.695 ms	0 - 45 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.547 ms	0 - 43 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X2 Elite	0.578 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X Elite	1.634 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.932 ms	0 - 83 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS6490	112.896 ms	43 - 46 MB	CPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	1.416 ms	0 - 9 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS9075	1.613 ms	0 - 3 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCM6690	49.256 ms	42 - 51 MB	CPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.668 ms	0 - 60 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	39.943 ms	42 - 51 MB	CPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.554 ms	0 - 58 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X2 Elite	0.893 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X Elite	1.783 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.088 ms	0 - 64 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	4.913 ms	1 - 38 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.563 ms	1 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8775P	2.059 ms	1 - 42 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS9075	1.889 ms	3 - 5 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	3.602 ms	0 - 73 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA7255P	4.913 ms	1 - 38 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8295P	3.678 ms	0 - 46 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.817 ms	0 - 43 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.611 ms	1 - 44 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.827 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X Elite	1.91 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.149 ms	0 - 66 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS6490	4.196 ms	0 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	3.342 ms	0 - 45 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	1.694 ms	0 - 18 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8775P	8.625 ms	0 - 45 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS9075	1.863 ms	2 - 4 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCM6690	6.515 ms	0 - 163 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	1.956 ms	0 - 67 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA7255P	3.342 ms	0 - 45 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8295P	2.431 ms	0 - 43 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.788 ms	0 - 44 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	1.73 ms	0 - 46 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.643 ms	0 - 48 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.079 ms	0 - 74 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8275 (Proxy)	4.951 ms	0 - 46 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.563 ms	0 - 2 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8775P	2.065 ms	0 - 49 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS9075	1.886 ms	0 - 16 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8450 (Proxy)	3.618 ms	0 - 81 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA7255P	4.951 ms	0 - 46 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8295P	3.69 ms	0 - 52 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.823 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.609 ms	0 - 50 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 • 3