EfficientViT-b2-cls: Optimized for Qualcomm Devices

EfficientViT 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 EfficientViT-b2-cls 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 1.27.1	Download
ONNX	w8a16	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	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 EfficientViT-b2-cls 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 EfficientViT-b2-cls on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

Input resolution: 224x224
Model checkpoint: Imagenet
Model size (float): 92.9 MB
Number of parameters: 24.3M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
EfficientViT-b2-cls	ONNX	float	Snapdragon® X2 Elite	2.529 ms	2 - 2 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® X Elite	5.071 ms	50 - 50 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.223 ms	0 - 144 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® 8 Gen 1 Mobile	6.353 ms	1 - 145 MB	NPU
EfficientViT-b2-cls	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	5.066 ms	0 - 4 MB	NPU
EfficientViT-b2-cls	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.869 ms	0 - 73 MB	NPU
EfficientViT-b2-cls	ONNX	float	Qualcomm® QCS8450	6.353 ms	1 - 145 MB	NPU
EfficientViT-b2-cls	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	5.53 ms	0 - 4 MB	NPU
EfficientViT-b2-cls	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	5.071 ms	50 - 50 MB	NPU
EfficientViT-b2-cls	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.7 ms	0 - 71 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® 8 Elite Mobile	2.7 ms	0 - 71 MB	NPU
EfficientViT-b2-cls	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.442 ms	1 - 72 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Snapdragon® X2 Elite	2.342 ms	1 - 1 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Snapdragon® X Elite	4.847 ms	27 - 27 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	3.094 ms	0 - 157 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	5.8 ms	0 - 169 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	15.089 ms	0 - 3 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	4.213 ms	0 - 4 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.6 ms	0 - 213 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® QCS8450	5.8 ms	0 - 169 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	4.941 ms	0 - 3 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	4.847 ms	27 - 27 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	19.551 ms	0 - 255 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	4.99 ms	0 - 117 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	2.516 ms	0 - 114 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Snapdragon® 8 Elite Mobile	2.516 ms	0 - 114 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.169 ms	0 - 115 MB	NPU
EfficientViT-b2-cls	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	4.99 ms	0 - 117 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® X2 Elite	2.949 ms	1 - 1 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® X Elite	6.23 ms	1 - 1 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.738 ms	0 - 142 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	7.122 ms	0 - 146 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	6.15 ms	1 - 4 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	12.815 ms	1 - 67 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.456 ms	0 - 6 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® SA8775P	6.789 ms	1 - 69 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® SA8650P	6.789 ms	1 - 69 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® SA8255P	6.789 ms	1 - 69 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® QCS8450	7.122 ms	0 - 146 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	6.513 ms	1 - 3 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	6.23 ms	1 - 1 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.788 ms	0 - 69 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® SA7255P	12.815 ms	1 - 67 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Qualcomm® SA8295P	7.42 ms	1 - 72 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.788 ms	0 - 69 MB	NPU
EfficientViT-b2-cls	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.34 ms	1 - 74 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Snapdragon® X2 Elite	2.633 ms	0 - 0 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Snapdragon® X Elite	5.445 ms	0 - 0 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	3.296 ms	0 - 146 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	4.433 ms	0 - 3 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	9.238 ms	0 - 103 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.985 ms	0 - 87 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® SA8775P	5.476 ms	0 - 106 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® SA8650P	5.476 ms	0 - 106 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® SA8255P	5.476 ms	0 - 106 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	5.291 ms	0 - 2 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	5.445 ms	0 - 0 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	21.198 ms	0 - 229 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	5.184 ms	0 - 101 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	2.514 ms	0 - 105 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Qualcomm® SA7255P	9.238 ms	0 - 103 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Snapdragon® 8 Elite Mobile	2.514 ms	0 - 105 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2.113 ms	0 - 107 MB	NPU
EfficientViT-b2-cls	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	5.184 ms	0 - 101 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.748 ms	0 - 183 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	7.125 ms	0 - 186 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	6.181 ms	0 - 52 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	12.891 ms	0 - 110 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.497 ms	0 - 2 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® SA8775P	6.769 ms	0 - 111 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® SA8650P	6.769 ms	0 - 111 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® SA8255P	6.769 ms	0 - 111 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® QCS8450	7.125 ms	0 - 186 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	6.526 ms	0 - 52 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.768 ms	0 - 98 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® SA7255P	12.891 ms	0 - 110 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Qualcomm® SA8295P	7.469 ms	0 - 115 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Snapdragon® 8 Elite Mobile	2.768 ms	0 - 98 MB	NPU
EfficientViT-b2-cls	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.344 ms	0 - 117 MB	NPU

License

The license for the original implementation of EfficientViT-b2-cls 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/EfficientViT-b2-cls

EfficientViT: Lightweight Multi-Scale Attention for On-Device Semantic Segmentation

Paper • 2205.14756 • Published May 29, 2022 • 1