Hugging Face's logo

qualcomm
/
Facial-Attribute-Detection

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

Facial-Attribute-Detection: Optimized for Mobile Deployment

Comprehensive facial analysis by extracting face features

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 provides scripts to run Facial-Attribute-Detection on Qualcomm® devices. More details on model performance across various devices, can be found here.

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
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
Facial-Attribute-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 4.255 ms 0 - 156 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 4.28 ms 0 - 144 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 1.297 ms 0 - 184 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 1.335 ms 0 - 169 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.836 ms 0 - 3 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 0.853 ms 0 - 3 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 1.086 ms 0 - 26 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 1.383 ms 0 - 158 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 1.403 ms 0 - 143 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float SA7255P ADP Qualcomm® SA7255P TFLITE 4.255 ms 0 - 156 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float SA7255P ADP Qualcomm® SA7255P QNN_DLC 4.28 ms 0 - 144 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float SA8295P ADP Qualcomm® SA8295P TFLITE 1.521 ms 0 - 163 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float SA8295P ADP Qualcomm® SA8295P QNN_DLC 1.515 ms 0 - 147 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float SA8775P ADP Qualcomm® SA8775P TFLITE 1.383 ms 0 - 158 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float SA8775P ADP Qualcomm® SA8775P QNN_DLC 1.403 ms 0 - 143 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.621 ms 0 - 191 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 0.652 ms 0 - 176 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.782 ms 0 - 149 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 0.493 ms 0 - 160 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 0.505 ms 0 - 150 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 0.624 ms 0 - 120 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen 5 Mobile TFLITE 0.413 ms 0 - 160 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen 5 Mobile QNN_DLC 0.42 ms 0 - 146 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen 5 Mobile ONNX 0.575 ms 0 - 119 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 0.995 ms 0 - 0 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.987 ms 22 - 22 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection w8a8 Dragonwing Q-6690 MTP Qualcomm® QCM6690 TFLITE 2.995 ms 0 - 140 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Dragonwing Q-6690 MTP Qualcomm® QCM6690 QNN_DLC 2.983 ms 0 - 144 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 Dragonwing Q-6690 MTP Qualcomm® QCM6690 ONNX 16.643 ms 20 - 34 MB CPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection w8a8 Dragonwing RB3 Gen 2 Vision Kit Qualcomm® QCS6490 TFLITE 1.304 ms 0 - 13 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Dragonwing RB3 Gen 2 Vision Kit Qualcomm® QCS6490 QNN_DLC 1.32 ms 0 - 2 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 Dragonwing RB3 Gen 2 Vision Kit Qualcomm® QCS6490 ONNX 35.117 ms 21 - 28 MB CPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 1.09 ms 0 - 139 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 1.053 ms 0 - 139 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.628 ms 0 - 169 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 0.621 ms 0 - 160 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.379 ms 0 - 2 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 0.382 ms 0 - 2 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 0.659 ms 0 - 15 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.622 ms 0 - 140 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 0.594 ms 0 - 139 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 1.09 ms 0 - 139 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 1.053 ms 0 - 139 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 0.813 ms 0 - 147 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 0.798 ms 0 - 146 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 0.622 ms 0 - 140 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 0.594 ms 0 - 139 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.28 ms 0 - 166 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 0.281 ms 0 - 163 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.417 ms 0 - 154 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 0.242 ms 0 - 144 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 0.239 ms 0 - 140 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 0.356 ms 0 - 126 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile TFLITE 0.497 ms 0 - 140 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 0.498 ms 0 - 145 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile ONNX 15.496 ms 18 - 35 MB CPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen 5 Mobile TFLITE 0.203 ms 0 - 141 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen 5 Mobile QNN_DLC 0.209 ms 0 - 142 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen 5 Mobile ONNX 0.331 ms 0 - 128 MB NPU Facial-Attribute-Detection.onnx.zip
Facial-Attribute-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 0.528 ms 0 - 0 MB NPU Facial-Attribute-Detection.dlc
Facial-Attribute-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.525 ms 11 - 11 MB NPU Facial-Attribute-Detection.onnx.zip

Installation

Install the package via pip:

pip install qai-hub-models

Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub Workbench with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Demo off target

The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.

python -m qai_hub_models.models.face_attrib_net.demo

The above demo runs a reference implementation of pre-processing, model inference, and post processing.

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.face_attrib_net.demo

Run model on a cloud-hosted device

In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:

  • Performance check on-device on a cloud-hosted device
  • Downloads compiled assets that can be deployed on-device for Android.
  • Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.face_attrib_net.export

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Compile model for on-device deployment

To compile a PyTorch model for on-device deployment, we first trace the model in memory using the jit.trace and then call the submit_compile_job API.

import torch

import qai_hub as hub
from qai_hub_models.models.face_attrib_net import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S25")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on-device
target_model = compile_job.get_target_model()

Step 2: Performance profiling on cloud-hosted device

After compiling models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.

profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.

input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)
    on_device_output = inference_job.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

Note: This on-device profiling and inference requires access to Qualcomm® AI Hub Workbench. Sign up for access.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.face_attrib_net.demo --eval-mode on-device

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.face_attrib_net.demo -- --eval-mode on-device

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on Facial-Attribute-Detection's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

Community

Downloads last month
437
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support