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 2.50, ONNX Runtime 1.27.1	Download
ONNX	w8a8	Universal	QAIRT 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
QNN_DLC	w8a8	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download
TFLITE	w8a8	Universal	QAIRT 2.50	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
• Model size (float): 20.7 MB
• Model size (w8a8): 5.27 MB
• Number of parameters: 5.42M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.208 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.217 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® X2 Elite	0.151 ms	1 - 1 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® X Elite	0.273 ms	11 - 11 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.239 ms	0 - 34 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Gen 1 Mobile	0.437 ms	0 - 39 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	0.459 ms	0 - 4 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.309 ms	0 - 14 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® QCS8450	0.437 ms	0 - 39 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	0.437 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	0.273 ms	11 - 11 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.217 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.118 ms	0 - 27 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.122 ms	0 - 26 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® X2 Elite	0.077 ms	1 - 1 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® X Elite	0.128 ms	6 - 6 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.144 ms	0 - 44 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Gen 1 Mobile	0.218 ms	0 - 49 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® Dragonwing™ QCS6490	0.765 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-8275	0.255 ms	0 - 4 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.168 ms	0 - 63 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS8450	0.218 ms	0 - 49 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.263 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-X7181	0.128 ms	6 - 6 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® Dragonwing™ Q-6690	0.625 ms	0 - 31 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® Dragonwing™ Q-7790	0.226 ms	0 - 31 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® Dragonwing™ Q-8750	0.122 ms	0 - 26 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	0.226 ms	0 - 31 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.199 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.204 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® X2 Elite	0.24 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® X Elite	0.371 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.241 ms	0 - 33 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	0.489 ms	0 - 39 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	0.42 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.296 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8650P	0.5 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8255P	0.5 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8450	0.489 ms	0 - 39 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	0.425 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	0.371 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	0.204 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8295P	0.534 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.125 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.128 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.17 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® X Elite	0.228 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.127 ms	0 - 41 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Gen 1 Mobile	0.212 ms	0 - 47 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS6490	0.63 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-8275	0.323 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.17 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8450	0.212 ms	0 - 47 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.221 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-X7181	0.228 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-6690	0.601 ms	0 - 29 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-7790	0.227 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-8750	0.128 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA8295P	0.337 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.227 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.196 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.199 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.236 ms	0 - 45 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	0.393 ms	0 - 50 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	0.409 ms	0 - 14 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.282 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8650P	0.49 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8255P	0.49 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8450	0.393 ms	0 - 50 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	0.374 ms	0 - 13 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	0.199 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8295P	0.559 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.123 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.127 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.142 ms	0 - 41 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	0.213 ms	0 - 47 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS6490	0.575 ms	0 - 7 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-8275	0.253 ms	0 - 8 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.174 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8775P	3.765 ms	0 - 31 MB	GPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8650P	3.765 ms	0 - 31 MB	GPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8255P	3.765 ms	0 - 31 MB	GPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8450	0.213 ms	0 - 47 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	0.242 ms	0 - 8 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-6690	0.597 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-7790	0.219 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	0.127 ms	0 - 28 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA7255P	0.476 ms	0 - 25 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8295P	0.349 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.219 ms	0 - 28 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.