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 2.45	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® 8 Elite Gen 5 Mobile	0.544 ms	0 - 43 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Elite Mobile	0.697 ms	0 - 38 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® X2 Elite	0.672 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® X Elite	1.464 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® X Elite	1.464 ms	13 - 13 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.897 ms	0 - 73 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.26 ms	0 - 15 MB	NPU
EfficientNet-B0	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.697 ms	0 - 38 MB	NPU
EfficientNet-B0	ONNX	float	Qualcomm® QCS9075	1.624 ms	1 - 3 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.557 ms	0 - 59 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite Mobile	0.669 ms	0 - 52 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X2 Elite	0.585 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X Elite	1.642 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® X Elite	1.642 ms	6 - 6 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	0.948 ms	0 - 84 MB	NPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS6490	106.123 ms	43 - 46 MB	CPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	1.417 ms	0 - 10 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.669 ms	0 - 52 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	38.224 ms	48 - 57 MB	CPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCM6690	48.062 ms	40 - 49 MB	CPU
EfficientNet-B0	ONNX	w8a16	Qualcomm® QCS9075	1.615 ms	0 - 3 MB	NPU
EfficientNet-B0	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	38.224 ms	48 - 57 MB	CPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.595 ms	1 - 42 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.806 ms	0 - 36 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X2 Elite	0.847 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X Elite	1.753 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® X Elite	1.753 ms	1 - 1 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.079 ms	0 - 61 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.562 ms	1 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8775P	2.014 ms	1 - 40 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8775P	2.014 ms	1 - 40 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8775P	2.014 ms	1 - 40 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA7255P	4.931 ms	1 - 37 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	3.611 ms	0 - 70 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® SA8295P	3.602 ms	0 - 43 MB	NPU
EfficientNet-B0	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.806 ms	0 - 36 MB	NPU
EfficientNet-B0	QNN_DLC	float	Qualcomm® QCS9075	1.905 ms	1 - 3 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	0.637 ms	0 - 50 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	0.774 ms	0 - 50 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X2 Elite	0.801 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X Elite	1.878 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® X Elite	1.878 ms	0 - 0 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	1.125 ms	0 - 65 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS6490	4.281 ms	2 - 4 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	1.665 ms	0 - 86 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8775P	1.938 ms	0 - 49 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8775P	1.938 ms	0 - 49 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8775P	1.938 ms	0 - 49 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA7255P	3.281 ms	0 - 46 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	0.774 ms	0 - 50 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	1.681 ms	0 - 47 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCM6690	6.483 ms	0 - 164 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® SA8295P	2.353 ms	0 - 44 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS9075	1.852 ms	0 - 2 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	1.966 ms	0 - 66 MB	NPU
EfficientNet-B0	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	1.681 ms	0 - 47 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.598 ms	0 - 47 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite Mobile	0.815 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.066 ms	0 - 67 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.536 ms	0 - 2 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8775P	2.034 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8775P	2.034 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8775P	2.034 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA7255P	4.937 ms	0 - 42 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS8450 (Proxy)	3.615 ms	0 - 76 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® SA8295P	3.634 ms	0 - 48 MB	NPU
EfficientNet-B0	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.815 ms	0 - 45 MB	NPU
EfficientNet-B0	TFLITE	float	Qualcomm® QCS9075	1.888 ms	0 - 16 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