Modelpublic

qualcomm/EfficientViT-l2-cls

sourceHugging Facebsd-3-clauseupdated 3d agoView on Hugging Face

0likes55downloads

Model Card

EfficientViT-l2-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-l2-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 2.50, 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 [EfficientViT-l2-cls on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientvit_l2_cls).

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-l2-cls on GitHub for usage instructions.

Model Details

Model Type: Modelusecase.image_classification

Model Stats:

—Input resolution: 224x224
—Model checkpoint: Imagenet
—Model size (float): 243 MB
—Number of parameters: 63.7M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
EfficientViT-l2-cls	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	5.845 ms	2 - 253 MB	NPU
EfficientViT-l2-cls	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	7.669 ms	2 - 246 MB	NPU
EfficientViT-l2-cls	ONNX	float	Snapdragon® X2 Elite	6.828 ms	2 - 2 MB	NPU
EfficientViT-l2-cls	ONNX	float	Snapdragon® X Elite	14.566 ms	131 - 131 MB	NPU
EfficientViT-l2-cls	ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.867 ms	0 - 377 MB	NPU
EfficientViT-l2-cls	ONNX	float	Snapdragon® 8 Gen 1 Mobile	33.849 ms	2 - 355 MB	NPU
EfficientViT-l2-cls	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	18.744 ms	2 - 7 MB	NPU
EfficientViT-l2-cls	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	14.09 ms	0 - 161 MB	NPU
EfficientViT-l2-cls	ONNX	float	Qualcomm® QCS8450	33.849 ms	2 - 355 MB	NPU
EfficientViT-l2-cls	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	18.521 ms	1 - 6 MB	NPU
EfficientViT-l2-cls	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	14.566 ms	131 - 131 MB	NPU
EfficientViT-l2-cls	ONNX	float	Qualcomm® Dragonwing™ Q-8750	7.669 ms	2 - 246 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	4.424 ms	0 - 217 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	5.585 ms	1 - 216 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Snapdragon® X2 Elite	5.032 ms	2 - 2 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Snapdragon® X Elite	12.174 ms	68 - 68 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	7.504 ms	0 - 336 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	14.665 ms	0 - 338 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	37.394 ms	0 - 4 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	10.216 ms	1 - 6 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	11.6 ms	0 - 83 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® QCS8450	14.665 ms	0 - 338 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	11.828 ms	0 - 4 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	12.174 ms	68 - 68 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	103.81 ms	0 - 421 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	13.974 ms	1 - 406 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	5.585 ms	1 - 216 MB	NPU
EfficientViT-l2-cls	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	13.974 ms	1 - 406 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	6.17 ms	0 - 244 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	8.06 ms	2 - 243 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Snapdragon® X2 Elite	7.593 ms	2 - 2 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Snapdragon® X Elite	16.215 ms	2 - 2 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	10.725 ms	2 - 373 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	36.154 ms	0 - 345 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	19.672 ms	2 - 6 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	15.598 ms	2 - 4 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Qualcomm® QCS8450	36.154 ms	0 - 345 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	19.863 ms	4 - 7 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	16.215 ms	2 - 2 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	8.06 ms	2 - 243 MB	NPU
EfficientViT-l2-cls	QNN_DLC	float	Qualcomm® SA8295P	32.88 ms	2 - 240 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	5.191 ms	1 - 209 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	6.587 ms	1 - 205 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Snapdragon® X2 Elite	6.146 ms	1 - 1 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Snapdragon® X Elite	15.087 ms	1 - 1 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	9.306 ms	1 - 328 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	12.676 ms	1 - 5 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	14.256 ms	1 - 220 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® SA8650P	14.996 ms	1 - 255 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® SA8255P	14.996 ms	1 - 255 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	14.484 ms	3 - 6 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	15.087 ms	1 - 1 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	87.817 ms	1 - 412 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	16.892 ms	1 - 399 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	6.587 ms	1 - 205 MB	NPU
EfficientViT-l2-cls	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	16.892 ms	1 - 399 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	6.175 ms	0 - 323 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	7.792 ms	0 - 316 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	10.001 ms	0 - 453 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	36.209 ms	0 - 447 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	18.614 ms	0 - 136 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	14.225 ms	0 - 3 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® SA8775P	79.875 ms	0 - 31 MB	GPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® SA8650P	79.875 ms	0 - 31 MB	GPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® SA8255P	79.875 ms	0 - 31 MB	GPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® QCS8450	36.209 ms	0 - 447 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	18.496 ms	0 - 136 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	7.792 ms	0 - 316 MB	NPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® SA7255P	205.468 ms	0 - 32 MB	GPU
EfficientViT-l2-cls	TFLITE	float	Qualcomm® SA8295P	32.321 ms	0 - 306 MB	NPU

License

—The license for the original implementation of EfficientViT-l2-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.