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 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.25.0 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® X2 Elite 0.42 ms 213 - 213 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® X Elite 0.846 ms 149 - 149 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 0.645 ms 0 - 72 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® 8 Gen 1 Mobile 1.3 ms 0 - 68 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® QCS8550 (Proxy) 0.86 ms 0 - 32 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® QCS8450 1.3 ms 0 - 68 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® 8 Elite Mobile 0.511 ms 0 - 53 MB NPU
Facial-Attribute-Detection ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.429 ms 0 - 51 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® QCS9075 1.233 ms 0 - 45 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® QCS8750 0.511 ms 0 - 53 MB NPU
Facial-Attribute-Detection ONNX float Qualcomm® QCS7181 0.846 ms 149 - 149 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® X2 Elite 0.206 ms 181 - 181 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® X Elite 0.394 ms 149 - 149 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.298 ms 0 - 71 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.644 ms 0 - 72 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCS6490 1.202 ms 0 - 45 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.396 ms 0 - 28 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCS8450 0.644 ms 0 - 72 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.221 ms 0 - 52 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.512 ms 0 - 51 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCM6690 2.999 ms 0 - 52 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCS9075 0.526 ms 0 - 45 MB NPU
Facial-Attribute-Detection ONNX w8a8 Snapdragon® 8 Elite Mobile 0.255 ms 0 - 58 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCS7790 0.512 ms 0 - 51 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCS8750 0.255 ms 0 - 58 MB NPU
Facial-Attribute-Detection ONNX w8a8 Qualcomm® QCS7181 0.394 ms 149 - 149 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® X2 Elite 0.535 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® X Elite 0.964 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.637 ms 0 - 80 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.35 ms 0 - 76 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® QCS8275 4.286 ms 0 - 51 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 0.873 ms 0 - 25 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® QCS8450 1.35 ms 0 - 76 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® 8 Elite Mobile 0.511 ms 0 - 57 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® SA8295P 1.555 ms 0 - 48 MB NPU
Facial-Attribute-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.425 ms 0 - 56 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® SA7255P 4.286 ms 0 - 51 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® QCS9075 1.221 ms 0 - 2 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® QCS8750 0.511 ms 0 - 57 MB NPU
Facial-Attribute-Detection QNN_DLC float Qualcomm® QCS7181 0.964 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® X2 Elite 0.276 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® X Elite 0.49 ms 0 - 0 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.275 ms 0 - 66 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.612 ms 0 - 67 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS6490 1.296 ms 0 - 2 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS8275 1.038 ms 0 - 48 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.383 ms 0 - 83 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS8450 0.612 ms 0 - 67 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.2 ms 0 - 46 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.489 ms 0 - 47 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCM6690 2.97 ms 0 - 49 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS9075 0.477 ms 0 - 2 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® SA7255P 1.038 ms 0 - 48 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.241 ms 0 - 52 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® SA8295P 0.826 ms 0 - 46 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS7790 0.489 ms 0 - 47 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS8750 0.241 ms 0 - 52 MB NPU
Facial-Attribute-Detection QNN_DLC w8a8 Qualcomm® QCS7181 0.49 ms 0 - 0 MB NPU
Facial-Attribute-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 0.608 ms 0 - 97 MB NPU
Facial-Attribute-Detection TFLITE float Snapdragon® 8 Gen 1 Mobile 1.298 ms 0 - 94 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® QCS8275 4.234 ms 0 - 67 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® QCS8550 (Proxy) 0.813 ms 0 - 5 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA8775P 34.24 ms 0 - 6 MB CPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA8650P 34.24 ms 0 - 6 MB CPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA8255P 34.24 ms 0 - 6 MB CPU
Facial-Attribute-Detection TFLITE float Qualcomm® QCS8450 1.298 ms 0 - 94 MB NPU
Facial-Attribute-Detection TFLITE float Snapdragon® 8 Elite Mobile 0.491 ms 0 - 64 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA8295P 1.551 ms 0 - 60 MB NPU
Facial-Attribute-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.418 ms 0 - 65 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® SA7255P 4.234 ms 0 - 67 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® QCS9075 1.206 ms 0 - 24 MB NPU
Facial-Attribute-Detection TFLITE float Qualcomm® QCS8750 0.491 ms 0 - 64 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.289 ms 0 - 62 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.615 ms 0 - 71 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCS6490 1.168 ms 0 - 13 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCS8275 1.086 ms 0 - 46 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.382 ms 0 - 2 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA8775P 45.726 ms 2 - 8 MB CPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA8650P 45.726 ms 2 - 8 MB CPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA8255P 45.726 ms 2 - 8 MB CPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCS8450 0.615 ms 0 - 71 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.207 ms 0 - 47 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.486 ms 0 - 41 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCM6690 2.971 ms 0 - 43 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCS9075 0.495 ms 0 - 13 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA7255P 1.086 ms 0 - 46 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.243 ms 0 - 42 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® SA8295P 0.884 ms 0 - 43 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCS7790 0.486 ms 0 - 41 MB NPU
Facial-Attribute-Detection TFLITE w8a8 Qualcomm® QCS8750 0.243 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