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 1.24.1 | 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-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® X2 Elite | 0.422 ms | 22 - 22 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® X Elite | 0.986 ms | 22 - 22 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.623 ms | 0 - 82 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.862 ms | 0 - 29 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Qualcomm® QCS9075 | 1.236 ms | 0 - 3 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.51 ms | 0 - 65 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.429 ms | 0 - 66 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® X2 Elite | 0.186 ms | 11 - 11 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® X Elite | 0.537 ms | 11 - 11 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.3 ms | 0 - 76 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS6490 | 35.264 ms | 20 - 27 MB | CPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.405 ms | 0 - 14 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS9075 | 0.517 ms | 0 - 3 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCM6690 | 17.102 ms | 18 - 27 MB | CPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.243 ms | 0 - 61 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 12.531 ms | 19 - 28 MB | CPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.222 ms | 0 - 60 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® X2 Elite | 0.572 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® X Elite | 0.968 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.624 ms | 0 - 82 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.268 ms | 0 - 54 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.851 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA8775P | 1.385 ms | 0 - 56 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS9075 | 1.234 ms | 2 - 4 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.336 ms | 0 - 77 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA7255P | 4.268 ms | 0 - 54 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 | 0.5 ms | 0 - 58 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.42 ms | 0 - 58 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.313 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.522 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.279 ms | 0 - 63 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 1.294 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.062 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.375 ms | 0 - 10 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA8775P | 2.286 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.476 ms | 2 - 4 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 2.885 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.606 ms | 0 - 65 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.062 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.815 ms | 0 - 45 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.238 ms | 0 - 46 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.497 ms | 0 - 46 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.209 ms | 0 - 49 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.624 ms | 0 - 105 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.234 ms | 0 - 71 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 0.819 ms | 0 - 7 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA8775P | 1.388 ms | 0 - 73 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS9075 | 1.203 ms | 0 - 24 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.302 ms | 0 - 97 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA7255P | 4.234 ms | 0 - 71 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA8295P | 1.564 ms | 0 - 63 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.493 ms | 0 - 65 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.405 ms | 0 - 76 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.282 ms | 0 - 64 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.258 ms | 0 - 13 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.111 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.383 ms | 0 - 1 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA8775P | 2.29 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.479 ms | 0 - 13 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCM6690 | 2.969 ms | 0 - 43 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.61 ms | 0 - 65 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA7255P | 1.111 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA8295P | 0.819 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 | 0.497 ms | 0 - 42 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.206 ms | 0 - 50 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.