--- library_name: pytorch license: other tags: - real_time - bu_iot - android pipeline_tag: object-detection --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/face_attrib_net/web-assets/model_demo.png) # 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](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/face_attrib_net) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/face_attrib_net/releases/v0.46.0/face_attrib_net-onnx-float.zip) | ONNX | w8a8 | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/face_attrib_net/releases/v0.46.0/face_attrib_net-onnx-w8a8.zip) | QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/face_attrib_net/releases/v0.46.0/face_attrib_net-qnn_dlc-float.zip) | QNN_DLC | w8a8 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/face_attrib_net/releases/v0.46.0/face_attrib_net-qnn_dlc-w8a8.zip) | TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/face_attrib_net/releases/v0.46.0/face_attrib_net-tflite-float.zip) | TFLITE | w8a8 | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/face_attrib_net/releases/v0.46.0/face_attrib_net-tflite-w8a8.zip) For more device-specific assets and performance metrics, visit **[Facial-Attribute-Detection on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/face_attrib_net)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/face_attrib_net) 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](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/face_attrib_net) 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® X Elite | 0.986 ms | 22 - 22 MB | NPU | Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.859 ms | 0 - 145 MB | NPU | Facial-Attribute-Detection | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.096 ms | 0 - 29 MB | NPU | Facial-Attribute-Detection | ONNX | float | Qualcomm® QCS9075 | 1.503 ms | 0 - 3 MB | NPU | Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.623 ms | 0 - 120 MB | NPU | Facial-Attribute-Detection | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.554 ms | 0 - 120 MB | NPU | Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® X Elite | 0.514 ms | 11 - 11 MB | NPU | Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.475 ms | 0 - 151 MB | NPU | Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS6490 | 35.118 ms | 21 - 28 MB | CPU | Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.615 ms | 0 - 128 MB | NPU | Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCS9075 | 0.72 ms | 0 - 3 MB | NPU | Facial-Attribute-Detection | ONNX | w8a8 | Qualcomm® QCM6690 | 16.742 ms | 20 - 30 MB | CPU | Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.358 ms | 0 - 124 MB | NPU | Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 12.327 ms | 19 - 28 MB | CPU | Facial-Attribute-Detection | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.339 ms | 0 - 127 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® X Elite | 0.999 ms | 0 - 0 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.652 ms | 0 - 81 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.312 ms | 0 - 53 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 | 1.375 ms | 0 - 57 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS9075 | 1.209 ms | 2 - 4 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.339 ms | 0 - 77 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA7255P | 4.312 ms | 0 - 53 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Qualcomm® SA8295P | 1.521 ms | 0 - 48 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.517 ms | 0 - 58 MB | NPU | Facial-Attribute-Detection | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.421 ms | 0 - 58 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.507 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 | 1.301 ms | 0 - 2 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.069 ms | 0 - 47 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.389 ms | 0 - 1 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.564 ms | 0 - 50 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.466 ms | 0 - 2 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 2.948 ms | 0 - 49 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.633 ms | 0 - 65 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.069 ms | 0 - 47 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.802 ms | 0 - 45 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.237 ms | 0 - 50 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.484 ms | 0 - 46 MB | NPU | Facial-Attribute-Detection | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.211 ms | 0 - 49 MB | NPU | Facial-Attribute-Detection | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.63 ms | 0 - 105 MB | NPU | Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.258 ms | 0 - 75 MB | NPU | Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 0.813 ms | 0 - 9 MB | NPU | Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA8775P | 1.372 ms | 0 - 77 MB | NPU | Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS9075 | 1.194 ms | 0 - 24 MB | NPU | Facial-Attribute-Detection | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.327 ms | 0 - 99 MB | NPU | Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA7255P | 4.258 ms | 0 - 75 MB | NPU | Facial-Attribute-Detection | TFLITE | float | Qualcomm® SA8295P | 1.507 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 | 0.417 ms | 0 - 79 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.284 ms | 0 - 63 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.296 ms | 0 - 13 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 1.102 ms | 0 - 49 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.376 ms | 0 - 2 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA8775P | 0.586 ms | 0 - 51 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.487 ms | 0 - 13 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCM6690 | 2.962 ms | 0 - 42 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.63 ms | 0 - 65 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA7255P | 1.102 ms | 0 - 49 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Qualcomm® SA8295P | 0.836 ms | 0 - 43 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.241 ms | 0 - 42 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.496 ms | 0 - 43 MB | NPU | Facial-Attribute-Detection | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.212 ms | 0 - 53 MB | NPU ## License * The license for the original implementation of Facial-Attribute-Detection can be found [here](https://github.com/quic/ai-hub-models/blob/main/LICENSE). ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).