Hugging Face's logo

qualcomm
/
Facial-Attribute-Detection

Object Detection
PyTorch
LiteRT
ONNX
real_time
android
Model card Files Community
1

Facial-Attribute-Detection: Optimized for Mobile Deployment

Comprehensive facial analysis by extracting face features

Facial feature extraction and additional attributes including liveness, eyeclose, mask and glasses detection for face recognition.

This model is an implementation of Facial-Attribute-Detection found here.

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
    • Input channel number: 1
    • Number of parameters: 11.6M
    • Model size (float): 47.6MB
    • Model size (w8a8): 47.6MB
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 29.713 ms 0 - 33 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 4.399 ms 0 - 10 MB NPU Use Export Script
Facial-Attribute-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 1.27 ms 0 - 41 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 1.517 ms 0 - 29 MB NPU Use Export Script
Facial-Attribute-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.899 ms 0 - 118 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.912 ms 0 - 3 MB NPU Use Export Script
Facial-Attribute-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 1.401 ms 0 - 35 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 1.433 ms 0 - 15 MB NPU Use Export Script
Facial-Attribute-Detection float SA7255P ADP Qualcomm® SA7255P TFLITE 29.713 ms 0 - 33 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float SA7255P ADP Qualcomm® SA7255P QNN 4.399 ms 0 - 10 MB NPU Use Export Script
Facial-Attribute-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.882 ms 0 - 115 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.922 ms 0 - 2 MB NPU Use Export Script
Facial-Attribute-Detection float SA8295P ADP Qualcomm® SA8295P TFLITE 1.55 ms 0 - 33 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float SA8295P ADP Qualcomm® SA8295P QNN 1.555 ms 0 - 18 MB NPU Use Export Script
Facial-Attribute-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.882 ms 0 - 116 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.918 ms 0 - 2 MB NPU Use Export Script
Facial-Attribute-Detection float SA8775P ADP Qualcomm® SA8775P TFLITE 1.401 ms 0 - 35 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float SA8775P ADP Qualcomm® SA8775P QNN 1.433 ms 0 - 15 MB NPU Use Export Script
Facial-Attribute-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.884 ms 0 - 114 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.929 ms 0 - 17 MB NPU Use Export Script
Facial-Attribute-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 1.069 ms 0 - 98 MB NPU Facial-Attribute-Detection.onnx
Facial-Attribute-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.678 ms 0 - 40 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.699 ms 0 - 27 MB NPU Use Export Script
Facial-Attribute-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.787 ms 0 - 33 MB NPU Facial-Attribute-Detection.onnx
Facial-Attribute-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.595 ms 0 - 37 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.564 ms 0 - 25 MB NPU Use Export Script
Facial-Attribute-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.694 ms 0 - 25 MB NPU Facial-Attribute-Detection.onnx
Facial-Attribute-Detection float Snapdragon X Elite CRD Snapdragon® X Elite QNN 1.024 ms 0 - 0 MB NPU Use Export Script
Facial-Attribute-Detection float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 1.038 ms 25 - 25 MB NPU Facial-Attribute-Detection.onnx
Facial-Attribute-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 1.195 ms 0 - 31 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 1.121 ms 0 - 10 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.674 ms 0 - 44 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.779 ms 0 - 44 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.434 ms 0 - 50 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.414 ms 0 - 9 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.651 ms 0 - 33 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 0.602 ms 0 - 14 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 1.444 ms 0 - 40 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 1.585 ms 0 - 14 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 55.106 ms 2 - 5 MB CPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 1.195 ms 0 - 31 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA7255P ADP Qualcomm® SA7255P QNN 1.121 ms 0 - 10 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.427 ms 0 - 50 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.407 ms 0 - 2 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 0.878 ms 0 - 34 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA8295P ADP Qualcomm® SA8295P QNN 0.849 ms 0 - 18 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.426 ms 0 - 8 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.414 ms 0 - 2 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 0.651 ms 0 - 33 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 SA8775P ADP Qualcomm® SA8775P QNN 0.602 ms 0 - 14 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.43 ms 0 - 51 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.412 ms 0 - 38 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.605 ms 0 - 47 MB NPU Facial-Attribute-Detection.onnx
Facial-Attribute-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.319 ms 0 - 49 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.296 ms 0 - 45 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.4 ms 0 - 58 MB NPU Facial-Attribute-Detection.onnx
Facial-Attribute-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.272 ms 0 - 38 MB NPU Facial-Attribute-Detection.tflite
Facial-Attribute-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.257 ms 0 - 38 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.464 ms 0 - 40 MB NPU Facial-Attribute-Detection.onnx
Facial-Attribute-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.51 ms 1 - 1 MB NPU Use Export Script
Facial-Attribute-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.59 ms 13 - 13 MB NPU Facial-Attribute-Detection.onnx

Installation

Install the package via pip:

pip install qai-hub-models

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

Sign-in to Qualcomm® AI Hub 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

Profiling Results
------------------------------------------------------------
Facial-Attribute-Detection
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 29.7                                 
Estimated peak memory usage (MB): [0, 33]                              
Total # Ops                     : 158                                  
Compute Unit(s)                 : npu (158 ops) gpu (0 ops) cpu (0 ops)

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 S24")

# 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. 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 --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 -- --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.
  • The license for the compiled assets for on-device deployment can be found here

References

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