Facial-Landmark-Detection: Optimized for Qualcomm Devices

Detects facial landmarks (eg, nose, mouth, etc.). This model's architecture was developed by Qualcomm. The model was trained by Qualcomm on a proprietary dataset of faces, but can be used on any image.

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 2.37, ONNX Runtime 1.23.0	Download
ONNX	w8a8	Universal	QAIRT 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
QNN_DLC	w8a8	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.42, TFLite 2.17.0	Download

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

Model Details

Model Type: Model_use_case.pose_estimation

Model Stats:

• Input resolution: 128x128
• Number of parameters: 5.42M
• Model size (float): 20.7 MB
• Model size (w8a8): 5.27 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Facial-Landmark-Detection	ONNX	float	Snapdragon® X Elite	0.391 ms	10 - 10 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.348 ms	0 - 99 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.481 ms	0 - 18 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® QCS9075	0.673 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.325 ms	0 - 90 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.3 ms	0 - 90 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® X Elite	0.246 ms	5 - 5 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.312 ms	0 - 105 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS6490	3.018 ms	0 - 10 MB	CPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.317 ms	0 - 45 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS9075	0.449 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCM6690	1.691 ms	0 - 7 MB	CPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.23 ms	0 - 90 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	1.263 ms	0 - 7 MB	CPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.207 ms	0 - 92 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® X Elite	0.368 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.224 ms	0 - 30 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	1.169 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.305 ms	0 - 1 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8775P	0.495 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS9075	0.411 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	0.55 ms	0 - 30 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA7255P	1.169 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8295P	0.654 ms	0 - 17 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.203 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.193 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® X Elite	0.24 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.14 ms	0 - 35 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS6490	0.716 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.43 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.162 ms	0 - 1 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA8775P	0.309 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS9075	0.222 ms	2 - 4 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCM6690	0.596 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.241 ms	0 - 37 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA7255P	0.43 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA8295P	0.441 ms	0 - 17 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.121 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.22 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.113 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.224 ms	0 - 40 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8275 (Proxy)	1.179 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.273 ms	0 - 14 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8775P	0.513 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS9075	0.379 ms	0 - 12 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8450 (Proxy)	0.484 ms	0 - 41 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA7255P	1.179 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8295P	0.646 ms	0 - 19 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.194 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.191 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.142 ms	0 - 35 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS6490	0.654 ms	0 - 7 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.451 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.169 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8775P	0.322 ms	0 - 21 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS9075	0.224 ms	0 - 7 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCM6690	0.598 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.241 ms	0 - 37 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA7255P	0.451 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8295P	0.452 ms	0 - 18 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.121 ms	0 - 18 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.221 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.118 ms	0 - 22 MB	NPU

License

• The license for the original implementation of Facial-Landmark-Detection can be found here.

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.