Hugging Face's logo

qualcomm
/
Facial-Attribute-Detection

Object Detection
PyTorch
real_time
bu_iot
android
Model card Files
xet
 Community
1

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 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 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:

  • Input resolution: 128x128
  • Model checkpoint: multitask_FR_state_dict.pt
  • Model size (float): 46.3 MB
  • Model size (w8a8): 12.3 MB
  • Number of parameters: 12.1M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Facial-Attribute-Detection ONNX float Snapdragon® X2 Elite 0.42 ms 1 - 1 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® X Elite 0.848 ms 23 - 23 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 0.638 ms 0 - 81 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® 8 Gen 1 Mobile 1.305 ms 0 - 78 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® Dragonwing™ IQ-8275 1.329 ms 0 - 4 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.857 ms 0 - 26 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® QCS8450 1.305 ms 0 - 78 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® Dragonwing™ IQ-9075 1.225 ms 0 - 3 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.848 ms 23 - 23 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® Dragonwing™ Q-8750 0.509 ms 0 - 57 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® 8 Elite Mobile 0.509 ms 0 - 57 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.437 ms 0 - 59 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® X2 Elite 0.179 ms 1 - 1 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® X Elite 0.389 ms 11 - 11 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.293 ms 0 - 81 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.643 ms 0 - 83 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 1.569 ms 0 - 3 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.545 ms 0 - 3 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.393 ms 0 - 14 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCS8450 0.643 ms 0 - 83 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.507 ms 0 - 3 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.389 ms 11 - 11 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 2.966 ms 0 - 56 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.506 ms 0 - 54 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.249 ms 0 - 59 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 8 Elite Mobile 0.249 ms 0 - 59 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.22 ms 0 - 58 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.506 ms 0 - 54 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® X2 Elite 0.547 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® X Elite 0.963 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.631 ms 0 - 82 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.332 ms 0 - 76 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.276 ms 0 - 51 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.861 ms 0 - 36 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® SA8775P 1.366 ms 0 - 55 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® SA8650P 1.366 ms 0 - 55 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® SA8255P 1.366 ms 0 - 55 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® QCS8450 1.332 ms 0 - 76 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.219 ms 2 - 4 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 0.963 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.506 ms 0 - 58 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® SA7255P 4.276 ms 0 - 51 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® SA8295P 1.563 ms 0 - 48 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® 8 Elite Mobile 0.506 ms 0 - 58 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.422 ms 0 - 55 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® X2 Elite 0.277 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® X Elite 0.498 ms 1 - 1 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.287 ms 0 - 63 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.609 ms 0 - 66 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 1.396 ms 0 - 2 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.458 ms 0 - 2 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.064 ms 0 - 47 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.385 ms 0 - 2 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® SA8775P 0.565 ms 0 - 50 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® SA8650P 0.565 ms 0 - 50 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® SA8255P 0.565 ms 0 - 50 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS8450 0.609 ms 0 - 66 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.451 ms 2 - 4 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.498 ms 1 - 1 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 2.94 ms 0 - 49 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.492 ms 0 - 47 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.24 ms 0 - 47 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® SA7255P 1.064 ms 0 - 47 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® SA8295P 0.811 ms 0 - 46 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.24 ms 0 - 47 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.211 ms 0 - 47 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.492 ms 0 - 47 MB NPU
Facial-Attribute-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 0.622 ms 0 - 97 MB NPU
Facial-Attribute-Detection TFLITE float Snapdragon® 8 Gen 1 Mobile 1.302 ms 0 - 93 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.292 ms 0 - 25 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.265 ms 0 - 67 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.81 ms 0 - 3 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA8775P 1.349 ms 0 - 72 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA8650P 1.349 ms 0 - 72 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA8255P 1.349 ms 0 - 72 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® QCS8450 1.302 ms 0 - 93 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.18 ms 0 - 24 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® Dragonwing™ Q-8750 0.485 ms 0 - 61 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA7255P 4.265 ms 0 - 67 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA8295P 1.533 ms 0 - 60 MB NPU
Facial-Attribute-Detection TFLITE float Snapdragon® 8 Elite Mobile 0.485 ms 0 - 61 MB NPU
Facial-Attribute-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.418 ms 0 - 64 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.286 ms 0 - 62 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.614 ms 0 - 70 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.455 ms 0 - 13 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.459 ms 0 - 14 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.079 ms 0 - 46 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.38 ms 0 - 2 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA8775P 0.585 ms 0 - 51 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA8650P 0.585 ms 0 - 51 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA8255P 0.585 ms 0 - 51 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCS8450 0.614 ms 0 - 70 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.466 ms 0 - 13 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 2.901 ms 0 - 44 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.491 ms 0 - 42 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.241 ms 0 - 43 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA7255P 1.079 ms 0 - 46 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA8295P 0.829 ms 0 - 43 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.241 ms 0 - 43 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.21 ms 0 - 41 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.491 ms 0 - 42 MB NPU

License

  • The license for the original implementation of Facial-Attribute-Detection can be found here.

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support