Facial-Attribute-Detection: Optimized for Qualcomm Devices
Detects attributes (eye closeness, mask presence, eyeglasses presence, sunglasses presence) that apply to a given face. 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 2.45 | Download |
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | Download |
| TFLITE | float | Universal | QAIRT 2.45 | Download |
| TFLITE | w8a8 | Universal | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit Facial-Attribute-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-Attribute-Detection on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.object_detection
Model Stats:
- Model checkpoint: multitask_FR_state_dict.pt
- Input resolution: 128x128
- Number of parameters: 12.1M
- Model size (float): 46.3 MB
- Model size (w8a8): 12.3 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.429 ms | 0 - 66 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® X2 Elite | 0.413 ms | 22 - 22 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® X Elite | 1.0 ms | 22 - 22 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.636 ms | 0 - 90 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.863 ms | 0 - 5 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Qualcomm® QCS9075 | 1.24 ms | 0 - 3 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.505 ms | 0 - 66 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.221 ms | 0 - 61 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® X2 Elite | 0.198 ms | 11 - 11 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® X Elite | 0.542 ms | 11 - 11 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.287 ms | 0 - 84 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS6490 | 35.427 ms | 20 - 27 MB | CPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.404 ms | 0 - 17 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS9075 | 0.54 ms | 0 - 3 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCM6690 | 16.935 ms | 18 - 26 MB | CPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.249 ms | 0 - 61 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 12.602 ms | 20 - 29 MB | CPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.422 ms | 0 - 56 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® X2 Elite | 0.549 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® X Elite | 0.991 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.636 ms | 0 - 80 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.245 ms | 0 - 51 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.867 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA8775P | 1.363 ms | 0 - 54 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS9075 | 1.23 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.353 ms | 0 - 76 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA7255P | 4.245 ms | 0 - 51 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA8295P | 1.56 ms | 0 - 48 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.516 ms | 0 - 57 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.201 ms | 0 - 51 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.28 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.498 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.28 ms | 0 - 63 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 1.304 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.073 ms | 0 - 48 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.38 ms | 0 - 10 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.563 ms | 0 - 50 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.475 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 2.876 ms | 0 - 50 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.609 ms | 0 - 65 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.073 ms | 0 - 48 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.817 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.237 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.489 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.416 ms | 0 - 72 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.621 ms | 0 - 95 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.201 ms | 0 - 66 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 0.809 ms | 0 - 3 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA8775P | 1.35 ms | 0 - 71 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS9075 | 1.191 ms | 0 - 24 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.302 ms | 0 - 93 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA7255P | 4.201 ms | 0 - 66 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA8295P | 1.545 ms | 0 - 60 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.494 ms | 0 - 71 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.206 ms | 0 - 50 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.278 ms | 0 - 63 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.203 ms | 0 - 13 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.086 ms | 0 - 46 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.383 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA8775P | 0.586 ms | 0 - 46 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.483 ms | 0 - 13 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCM6690 | 2.94 ms | 0 - 44 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.636 ms | 0 - 64 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA7255P | 1.086 ms | 0 - 46 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA8295P | 0.857 ms | 0 - 43 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.241 ms | 0 - 52 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.488 ms | 0 - 43 MB | NPU |
License
- The license for the original implementation of Facial-Attribute-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.