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 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.19.1	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® 8 Elite Gen 5 Mobile	0.207 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® X2 Elite	0.173 ms	10 - 10 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® X Elite	0.386 ms	10 - 10 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.243 ms	0 - 30 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.316 ms	0 - 14 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® QCS9075	0.437 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.224 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.119 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® X2 Elite	0.077 ms	5 - 5 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® X Elite	0.234 ms	5 - 5 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.139 ms	0 - 37 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS6490	3.063 ms	1 - 8 MB	CPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.166 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS9075	0.255 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCM6690	1.73 ms	0 - 6 MB	CPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.117 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	1.278 ms	0 - 7 MB	CPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.185 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® X2 Elite	0.262 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® X Elite	0.373 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.227 ms	0 - 30 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	1.129 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.294 ms	0 - 1 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8775P	0.499 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS9075	0.411 ms	2 - 4 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	0.547 ms	0 - 29 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA7255P	1.129 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8295P	0.66 ms	0 - 17 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.202 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.113 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.196 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® X Elite	0.236 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	0.668 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.453 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.173 ms	0 - 1 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA8775P	0.32 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS9075	0.224 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCM6690	0.587 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.238 ms	0 - 37 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA7255P	0.453 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA8295P	0.458 ms	0 - 18 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.116 ms	0 - 19 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.22 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.193 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.229 ms	0 - 40 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8275 (Proxy)	1.154 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.277 ms	0 - 5 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8775P	0.497 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS9075	0.386 ms	0 - 12 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8450 (Proxy)	0.483 ms	0 - 39 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA7255P	1.154 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8295P	0.696 ms	0 - 19 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.209 ms	0 - 26 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.117 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.142 ms	0 - 36 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS6490	0.609 ms	0 - 7 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.49 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.164 ms	0 - 1 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8775P	0.33 ms	0 - 21 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS9075	0.269 ms	0 - 7 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCM6690	0.596 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.242 ms	0 - 36 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA7255P	0.49 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8295P	0.478 ms	0 - 17 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.116 ms	0 - 19 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.223 ms	0 - 23 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.