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 1.30.0 | Download |
| ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | 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 | 0.216 ms | 0 - 24 MB | NPU |
| Facial-Landmark-Detection | ONNX | float | Snapdragon® X2 Elite | 0.167 ms | 1 - 1 MB | NPU |
| Facial-Landmark-Detection | ONNX | float | Snapdragon® X Elite | 0.269 ms | 10 - 10 MB | NPU |
| Facial-Landmark-Detection | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.238 ms | 0 - 34 MB | NPU |
| Facial-Landmark-Detection | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 0.439 ms | 0 - 40 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) | 0.302 ms | 0 - 19 MB | NPU |
| Facial-Landmark-Detection | ONNX | float | Qualcomm® QCS8450 | 0.439 ms | 0 - 40 MB | NPU |
| Facial-Landmark-Detection | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 0.438 ms | 0 - 3 MB | NPU |
| Facial-Landmark-Detection | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.269 ms | 10 - 10 MB | NPU |
| Facial-Landmark-Detection | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.216 ms | 0 - 24 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.12 ms | 0 - 27 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.124 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Snapdragon® X2 Elite | 0.074 ms | 1 - 1 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Snapdragon® X Elite | 0.124 ms | 5 - 5 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.135 ms | 0 - 45 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.23 ms | 0 - 50 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 0.782 ms | 0 - 3 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.313 ms | 0 - 4 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.163 ms | 0 - 8 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® QCS8450 | 0.23 ms | 0 - 50 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.26 ms | 0 - 3 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.124 ms | 5 - 5 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 0.619 ms | 0 - 31 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.221 ms | 0 - 31 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.124 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.221 ms | 0 - 31 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.206 ms | 0 - 25 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.206 ms | 0 - 24 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Snapdragon® X2 Elite | 0.234 ms | 0 - 0 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Snapdragon® X Elite | 0.359 ms | 0 - 0 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.245 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 | 0.421 ms | 0 - 3 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.294 ms | 0 - 60 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 | 0.397 ms | 0 - 2 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.359 ms | 0 - 0 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.206 ms | 0 - 24 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Qualcomm® SA7255P | 1.153 ms | 0 - 25 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | float | Qualcomm® SA8295P | 0.523 ms | 0 - 22 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.122 ms | 0 - 29 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.123 ms | 0 - 28 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.177 ms | 0 - 0 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.238 ms | 1 - 1 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.135 ms | 0 - 41 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.213 ms | 0 - 43 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 0.631 ms | 0 - 2 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.233 ms | 0 - 3 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.172 ms | 0 - 6 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.303 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.303 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.303 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.213 ms | 0 - 43 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.224 ms | 0 - 2 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.238 ms | 1 - 1 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 0.596 ms | 0 - 29 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.221 ms | 0 - 29 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.123 ms | 0 - 28 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® SA7255P | 0.453 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.33 ms | 0 - 22 MB | NPU |
| Facial-Landmark-Detection | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.221 ms | 0 - 29 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.198 ms | 0 - 25 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.192 ms | 0 - 24 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.225 ms | 0 - 45 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 0.385 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) | 0.283 ms | 0 - 2 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Qualcomm® SA8775P | 0.5 ms | 0 - 28 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Qualcomm® SA8650P | 0.5 ms | 0 - 28 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Qualcomm® SA8255P | 0.5 ms | 0 - 28 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Qualcomm® QCS8450 | 0.385 ms | 0 - 50 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 0.375 ms | 0 - 13 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.192 ms | 0 - 24 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Qualcomm® SA7255P | 1.154 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | TFLITE | float | Qualcomm® SA8295P | 0.566 ms | 0 - 22 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.121 ms | 0 - 24 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® 8 Gen 3 Mobile | 0.14 ms | 0 - 40 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.211 ms | 0 - 47 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 0.553 ms | 0 - 7 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.265 ms | 0 - 8 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.171 ms | 0 - 2 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® SA8775P | 0.33 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® SA8650P | 0.33 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® SA8255P | 0.33 ms | 0 - 26 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.211 ms | 0 - 47 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.246 ms | 0 - 8 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 0.6 ms | 0 - 27 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.227 ms | 0 - 27 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.124 ms | 0 - 23 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® SA7255P | 0.462 ms | 0 - 25 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Qualcomm® SA8295P | 0.353 ms | 0 - 22 MB | NPU |
| Facial-Landmark-Detection | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.227 ms | 0 - 27 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.
