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 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
CavaFace	ONNX	float	Snapdragon® X2 Elite	2.34 ms	1 - 1 MB	NPU
CavaFace	ONNX	float	Snapdragon® X Elite	4.307 ms	127 - 127 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.206 ms	0 - 137 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Gen 1 Mobile	9.549 ms	0 - 229 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.312 ms	0 - 130 MB	NPU
CavaFace	ONNX	float	Qualcomm® QCS8450	9.549 ms	0 - 229 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	7.081 ms	0 - 3 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	4.307 ms	127 - 127 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.625 ms	0 - 89 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Elite Mobile	2.625 ms	0 - 89 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.271 ms	0 - 90 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® X2 Elite	2.57 ms	0 - 0 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® X Elite	4.464 ms	0 - 0 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.192 ms	0 - 129 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	9.582 ms	0 - 221 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8275	24.708 ms	0 - 81 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.286 ms	0 - 2 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA8775P	6.913 ms	0 - 82 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA8650P	6.913 ms	0 - 82 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA8255P	6.913 ms	0 - 82 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® QCS8450	9.582 ms	0 - 221 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	6.669 ms	0 - 2 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	4.464 ms	0 - 0 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.61 ms	0 - 83 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA7255P	24.708 ms	0 - 81 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA8295P	8.026 ms	0 - 199 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.61 ms	0 - 83 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.253 ms	0 - 84 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.123 ms	0 - 245 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	9.428 ms	0 - 333 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ QCS8275	24.517 ms	0 - 95 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.17 ms	0 - 3 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8775P	6.892 ms	0 - 96 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8650P	6.892 ms	0 - 96 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8255P	6.892 ms	0 - 96 MB	NPU
CavaFace	TFLITE	float	Qualcomm® QCS8450	9.428 ms	0 - 333 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	6.593 ms	0 - 128 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.612 ms	0 - 99 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA7255P	24.517 ms	0 - 95 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8295P	7.989 ms	0 - 210 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Elite Mobile	2.612 ms	0 - 99 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.22 ms	0 - 97 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