EfficientNet-B4: Optimized for Qualcomm Devices

EfficientNetB4 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-B4 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 2.50, ONNX Runtime 1.30.0	Download
ONNX	w8a16	Universal	QAIRT 2.50, ONNX Runtime 1.30.0	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
QNN_DLC	w8a16	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit EfficientNet-B4 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-B4 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

Input resolution: 380x380
Model checkpoint: Imagenet
Model size (float): 73.6 MB
Model size (w8a16): 24.0 MB
Number of parameters: 19.3M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
EfficientNet-B4	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	3.231 ms	0 - 200 MB	NPU
EfficientNet-B4	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.073 ms	1 - 90 MB	NPU
EfficientNet-B4	ONNX	float	Snapdragon® X2 Elite	4.07 ms	2 - 2 MB	NPU
EfficientNet-B4	ONNX	float	Snapdragon® X Elite	7.637 ms	44 - 44 MB	NPU
EfficientNet-B4	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.288 ms	0 - 147 MB	NPU
EfficientNet-B4	ONNX	float	Snapdragon® 8 Gen 1 Mobile	17.175 ms	2 - 190 MB	NPU
EfficientNet-B4	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	9.559 ms	2 - 7 MB	NPU
EfficientNet-B4	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.256 ms	0 - 207 MB	NPU
EfficientNet-B4	ONNX	float	Qualcomm® QCS8450	17.175 ms	2 - 190 MB	NPU
EfficientNet-B4	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	9.33 ms	1 - 6 MB	NPU
EfficientNet-B4	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	7.637 ms	44 - 44 MB	NPU
EfficientNet-B4	ONNX	float	Qualcomm® Dragonwing™ Q-8750	4.073 ms	1 - 90 MB	NPU
EfficientNet-B4	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.762 ms	0 - 174 MB	NPU
EfficientNet-B4	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.485 ms	0 - 166 MB	NPU
EfficientNet-B4	ONNX	w8a16	Snapdragon® X2 Elite	2.913 ms	2 - 2 MB	NPU
EfficientNet-B4	ONNX	w8a16	Snapdragon® X Elite	8.141 ms	23 - 23 MB	NPU
EfficientNet-B4	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	5.112 ms	1 - 224 MB	NPU
EfficientNet-B4	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	8.685 ms	0 - 228 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	25.198 ms	0 - 4 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	6.969 ms	1 - 5 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	7.741 ms	0 - 30 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® QCS8450	8.685 ms	0 - 228 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	8.057 ms	1 - 4 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	8.141 ms	23 - 23 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	43.701 ms	0 - 288 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	8.97 ms	1 - 280 MB	NPU
EfficientNet-B4	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	3.485 ms	0 - 166 MB	NPU
EfficientNet-B4	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	8.97 ms	1 - 280 MB	NPU
EfficientNet-B4	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	3.231 ms	2 - 202 MB	NPU
EfficientNet-B4	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	4.309 ms	2 - 85 MB	NPU
EfficientNet-B4	QNN_DLC	float	Snapdragon® X2 Elite	4.43 ms	2 - 2 MB	NPU
EfficientNet-B4	QNN_DLC	float	Snapdragon® X Elite	8.804 ms	2 - 2 MB	NPU
EfficientNet-B4	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	5.823 ms	0 - 141 MB	NPU
EfficientNet-B4	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	19.968 ms	0 - 183 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	10.033 ms	2 - 6 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	8.059 ms	2 - 104 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® SA8775P	10.279 ms	2 - 84 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® SA8650P	10.279 ms	2 - 84 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® SA8255P	10.279 ms	2 - 84 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® QCS8450	19.968 ms	0 - 183 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	10.04 ms	4 - 7 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	8.804 ms	2 - 2 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	4.309 ms	2 - 85 MB	NPU
EfficientNet-B4	QNN_DLC	float	Qualcomm® SA8295P	18.639 ms	2 - 123 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	3.042 ms	1 - 160 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	3.762 ms	0 - 150 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Snapdragon® X2 Elite	3.52 ms	1 - 1 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Snapdragon® X Elite	9.143 ms	1 - 1 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	5.665 ms	1 - 201 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	10.357 ms	1 - 205 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	27.297 ms	1 - 4 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	7.611 ms	1 - 5 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	8.451 ms	1 - 2 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® SA8775P	8.971 ms	1 - 147 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® SA8650P	8.971 ms	1 - 147 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® SA8255P	8.971 ms	1 - 147 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® QCS8450	10.357 ms	1 - 205 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	8.751 ms	3 - 6 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	9.143 ms	1 - 1 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	45.674 ms	1 - 271 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	9.551 ms	1 - 265 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	3.762 ms	0 - 150 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Qualcomm® SA8295P	10.839 ms	1 - 146 MB	NPU
EfficientNet-B4	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	9.551 ms	1 - 265 MB	NPU
EfficientNet-B4	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	3.23 ms	0 - 99 MB	NPU
EfficientNet-B4	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	4.31 ms	0 - 104 MB	NPU
EfficientNet-B4	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	5.774 ms	0 - 163 MB	NPU
EfficientNet-B4	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	19.923 ms	0 - 205 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	10.01 ms	0 - 50 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	8.044 ms	0 - 51 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® SA8775P	10.202 ms	0 - 101 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® SA8650P	10.202 ms	0 - 101 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® SA8255P	10.202 ms	0 - 101 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® QCS8450	19.923 ms	0 - 205 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	9.951 ms	0 - 50 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	4.31 ms	0 - 104 MB	NPU
EfficientNet-B4	TFLITE	float	Qualcomm® SA8295P	18.591 ms	0 - 139 MB	NPU

License

The license for the original implementation of EfficientNet-B4 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-B4

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Paper • 1905.11946 • Published May 28, 2019 • 4