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® 8 Elite Gen 5 Mobile | 0.429 ms | 0 - 66 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® X2 Elite | 0.419 ms | 22 - 22 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® X Elite | 0.985 ms | 22 - 22 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.641 ms | 0 - 94 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.859 ms | 0 - 3 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Qualcomm® QCS9075 | 1.238 ms | 0 - 3 MB | NPU |
| Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.508 ms | 0 - 66 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.216 ms | 0 - 61 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® X2 Elite | 0.195 ms | 11 - 11 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® X Elite | 0.549 ms | 11 - 11 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.299 ms | 0 - 86 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS6490 | 35.767 ms | 20 - 27 MB | CPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.403 ms | 0 - 17 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS9075 | 0.525 ms | 0 - 3 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCM6690 | 17.087 ms | 18 - 27 MB | CPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.25 ms | 0 - 61 MB | NPU |
| Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 12.613 ms | 25 - 34 MB | CPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.422 ms | 0 - 58 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® X2 Elite | 0.573 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® X Elite | 0.972 ms | 0 - 0 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.636 ms | 0 - 83 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.259 ms | 0 - 54 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.849 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA8775P | 1.388 ms | 0 - 56 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS9075 | 1.232 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.34 ms | 0 - 76 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA7255P | 4.259 ms | 0 - 54 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA8295P | 1.543 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.497 ms | 0 - 58 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.206 ms | 0 - 49 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.306 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 | 0.281 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) | 1.06 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.39 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.577 ms | 0 - 50 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.478 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 2.881 ms | 0 - 48 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.624 ms | 0 - 65 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.06 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.811 ms | 0 - 45 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.239 ms | 0 - 46 MB | NPU |
| Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.501 ms | 0 - 46 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.415 ms | 0 - 75 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.633 ms | 0 - 105 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.222 ms | 0 - 72 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 0.818 ms | 0 - 5 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA8775P | 5.722 ms | 0 - 72 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS9075 | 1.202 ms | 0 - 24 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.306 ms | 0 - 95 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA7255P | 4.222 ms | 0 - 72 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA8295P | 1.556 ms | 0 - 63 MB | NPU |
| Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.499 ms | 0 - 65 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.206 ms | 0 - 51 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.288 ms | 36 - 102 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.28 ms | 0 - 13 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.083 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.378 ms | 0 - 2 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA8775P | 0.596 ms | 0 - 51 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.479 ms | 0 - 13 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCM6690 | 2.91 ms | 0 - 43 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.632 ms | 0 - 66 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA7255P | 1.083 ms | 0 - 47 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA8295P | 0.831 ms | 0 - 43 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.243 ms | 0 - 41 MB | NPU |
| Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.498 ms | 0 - 42 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.