CavaFace: Optimized for Qualcomm Devices

A PyTorch-based framework for training face recognition models that generates facial embeddings for verification and identification tasks

This is based on the implementation of CavaFace 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 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

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

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

Input resolution: 112x112
Model checkpoint: IR_SE_100_Combined_Epoch_24.pt
Model size (float): 249.96MB
Number of parameters: 65.5M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
CavaFace	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.277 ms	0 - 98 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.633 ms	0 - 95 MB	NPU
CavaFace	ONNX	float	Snapdragon® X2 Elite	2.304 ms	1 - 1 MB	NPU
CavaFace	ONNX	float	Snapdragon® X Elite	4.253 ms	127 - 127 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.194 ms	0 - 141 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Gen 1 Mobile	7.112 ms	0 - 224 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	7.639 ms	0 - 4 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.305 ms	0 - 130 MB	NPU
CavaFace	ONNX	float	Qualcomm® QCS8450	7.112 ms	0 - 224 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	6.687 ms	0 - 3 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	4.253 ms	127 - 127 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.633 ms	0 - 95 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.262 ms	0 - 89 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.609 ms	0 - 86 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® X2 Elite	2.609 ms	0 - 0 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® X Elite	4.452 ms	1 - 1 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.21 ms	0 - 133 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	7.098 ms	0 - 213 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	7.597 ms	0 - 3 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.299 ms	0 - 2 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA8650P	6.932 ms	0 - 82 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA8255P	6.932 ms	0 - 82 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® QCS8450	7.098 ms	0 - 213 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	6.66 ms	0 - 2 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	4.452 ms	1 - 1 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.609 ms	0 - 86 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA8295P	7.82 ms	0 - 194 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.251 ms	0 - 104 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.58 ms	0 - 103 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.132 ms	0 - 250 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	7.016 ms	0 - 328 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	7.549 ms	0 - 129 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.216 ms	0 - 2 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8650P	6.893 ms	0 - 96 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8255P	6.893 ms	0 - 96 MB	NPU
CavaFace	TFLITE	float	Qualcomm® QCS8450	7.016 ms	0 - 328 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	6.603 ms	0 - 129 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.58 ms	0 - 103 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA7255P	159.788 ms	0 - 23 MB	GPU
CavaFace	TFLITE	float	Qualcomm® SA8295P	7.754 ms	0 - 205 MB	NPU

License

The license for the original implementation of CavaFace can be found here.

References

Source Model Implementation

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