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 1.30.0	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	2.279 ms	0 - 94 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.641 ms	0 - 94 MB	NPU
CavaFace	ONNX	float	Snapdragon® X2 Elite	2.291 ms	1 - 1 MB	NPU
CavaFace	ONNX	float	Snapdragon® X Elite	4.292 ms	127 - 127 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.194 ms	0 - 145 MB	NPU
CavaFace	ONNX	float	Snapdragon® 8 Gen 1 Mobile	7.11 ms	0 - 223 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	7.648 ms	0 - 4 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.306 ms	0 - 130 MB	NPU
CavaFace	ONNX	float	Qualcomm® QCS8450	7.11 ms	0 - 223 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	6.688 ms	0 - 3 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	4.292 ms	127 - 127 MB	NPU
CavaFace	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.641 ms	0 - 94 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.259 ms	0 - 87 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.625 ms	0 - 87 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® X2 Elite	2.583 ms	0 - 0 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® X Elite	4.466 ms	0 - 0 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.187 ms	0 - 133 MB	NPU
CavaFace	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	7.105 ms	0 - 213 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	7.606 ms	0 - 3 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.297 ms	0 - 2 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® QCS8450	7.105 ms	0 - 213 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	6.68 ms	2 - 4 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	4.466 ms	0 - 0 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.625 ms	0 - 87 MB	NPU
CavaFace	QNN_DLC	float	Qualcomm® SA8295P	7.822 ms	0 - 194 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.251 ms	0 - 99 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.588 ms	0 - 104 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.148 ms	0 - 251 MB	NPU
CavaFace	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	7.028 ms	0 - 328 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	7.545 ms	0 - 129 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.157 ms	0 - 2 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8775P	6.782 ms	0 - 100 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8650P	6.782 ms	0 - 100 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA8255P	6.782 ms	0 - 100 MB	NPU
CavaFace	TFLITE	float	Qualcomm® QCS8450	7.028 ms	0 - 328 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	6.601 ms	0 - 129 MB	NPU
CavaFace	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.588 ms	0 - 104 MB	NPU
CavaFace	TFLITE	float	Qualcomm® SA7255P	160.524 ms	0 - 23 MB	GPU
CavaFace	TFLITE	float	Qualcomm® SA8295P	7.768 ms	0 - 204 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