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 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, 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® 8 Elite Gen 5 Mobile	0.211 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® X2 Elite	0.163 ms	10 - 10 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® X Elite	0.395 ms	10 - 10 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.246 ms	0 - 29 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.322 ms	0 - 37 MB	NPU
Facial-Landmark-Detection	ONNX	float	Qualcomm® QCS9075	0.427 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.229 ms	0 - 18 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.118 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	0.249 ms	5 - 5 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.134 ms	0 - 37 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS6490	2.872 ms	1 - 8 MB	CPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.174 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCS9075	0.258 ms	0 - 3 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Qualcomm® QCM6690	1.723 ms	0 - 6 MB	CPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.116 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	1.276 ms	0 - 7 MB	CPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.188 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® X2 Elite	0.245 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® X Elite	0.374 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.224 ms	0 - 29 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	1.118 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.293 ms	0 - 59 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8775P	0.502 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® QCS9075	0.394 ms	2 - 4 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	1.118 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Qualcomm® SA8295P	0.673 ms	0 - 17 MB	NPU
Facial-Landmark-Detection	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.202 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.12 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.164 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® X Elite	0.235 ms	0 - 0 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.136 ms	0 - 35 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS6490	0.699 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.46 ms	0 - 21 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.168 ms	0 - 1 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA8775P	0.936 ms	0 - 21 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCS9075	0.236 ms	0 - 2 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® QCM6690	0.598 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	0.46 ms	0 - 21 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Qualcomm® SA8295P	0.469 ms	0 - 17 MB	NPU
Facial-Landmark-Detection	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.122 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	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.19 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.222 ms	0 - 41 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8275 (Proxy)	1.147 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.283 ms	0 - 113 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8775P	0.493 ms	0 - 24 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS9075	0.384 ms	0 - 12 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® QCS8450 (Proxy)	0.485 ms	0 - 41 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA7255P	1.147 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Qualcomm® SA8295P	0.678 ms	0 - 19 MB	NPU
Facial-Landmark-Detection	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.198 ms	0 - 21 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.12 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.139 ms	0 - 36 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS6490	0.572 ms	0 - 7 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.477 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.171 ms	0 - 1 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8775P	0.331 ms	0 - 21 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS9075	0.228 ms	0 - 7 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCM6690	0.593 ms	0 - 22 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.239 ms	0 - 37 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA7255P	0.477 ms	0 - 20 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Qualcomm® SA8295P	0.468 ms	0 - 17 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.124 ms	0 - 23 MB	NPU
Facial-Landmark-Detection	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.217 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.