Facial-Attribute-Detection-Quantized: 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-Quantized found here.

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

Model Details

Model Type: 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: 47.6MB

Model	Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
Facial-Attribute-Detection-Quantized	Samsung Galaxy S23	Snapdragon® 8 Gen 2	TFLITE	0.498 ms	0 - 9 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	0.515 ms	0 - 19 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.so
Facial-Attribute-Detection-Quantized	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	0.912 ms	0 - 16 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.onnx
Facial-Attribute-Detection-Quantized	Samsung Galaxy S24	Snapdragon® 8 Gen 3	TFLITE	0.376 ms	0 - 29 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	0.38 ms	0 - 26 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.so
Facial-Attribute-Detection-Quantized	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	0.68 ms	0 - 102 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.onnx
Facial-Attribute-Detection-Quantized	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	TFLITE	0.38 ms	0 - 19 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	0.402 ms	0 - 20 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	0.659 ms	0 - 52 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.onnx
Facial-Attribute-Detection-Quantized	RB3 Gen 2 (Proxy)	QCS6490 Proxy	TFLITE	2.656 ms	0 - 32 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	RB3 Gen 2 (Proxy)	QCS6490 Proxy	QNN	1.775 ms	0 - 12 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	RB5 (Proxy)	QCS8250 Proxy	TFLITE	54.45 ms	2 - 5 MB	FP32	CPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	QCS8550 (Proxy)	QCS8550 Proxy	TFLITE	0.504 ms	0 - 9 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	QCS8550 (Proxy)	QCS8550 Proxy	QNN	0.48 ms	0 - 1 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	SA7255P ADP	SA7255P	TFLITE	5.066 ms	0 - 21 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	SA7255P ADP	SA7255P	QNN	5.24 ms	0 - 10 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	SA8255 (Proxy)	SA8255P Proxy	TFLITE	0.502 ms	0 - 9 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	SA8255 (Proxy)	SA8255P Proxy	QNN	0.488 ms	0 - 2 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	SA8295P ADP	SA8295P	TFLITE	1.022 ms	0 - 19 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	SA8295P ADP	SA8295P	QNN	1.07 ms	0 - 6 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	SA8650 (Proxy)	SA8650P Proxy	TFLITE	0.504 ms	0 - 10 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	SA8650 (Proxy)	SA8650P Proxy	QNN	0.484 ms	0 - 1 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	SA8775P ADP	SA8775P	TFLITE	0.919 ms	0 - 23 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	SA8775P ADP	SA8775P	QNN	1.021 ms	0 - 6 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	QCS8450 (Proxy)	QCS8450 Proxy	TFLITE	0.641 ms	0 - 32 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.tflite
Facial-Attribute-Detection-Quantized	QCS8450 (Proxy)	QCS8450 Proxy	QNN	0.637 ms	0 - 26 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	0.628 ms	1 - 1 MB	INT8	NPU	Use Export Script
Facial-Attribute-Detection-Quantized	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	1.026 ms	15 - 15 MB	INT8	NPU	Facial-Attribute-Detection-Quantized.onnx

Installation

This model can be installed as a Python 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_quantized.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_quantized.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_quantized.export

Profiling Results
------------------------------------------------------------
Facial-Attribute-Detection-Quantized
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 0.5                    
Estimated peak memory usage (MB): [0, 9]                 
Total # Ops                     : 170                    
Compute Unit(s)                 : NPU (170 ops)

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.face_attrib_net_quantized.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_quantized.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-Quantized'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-Quantized can be found here.
The license for the compiled assets for on-device deployment can be found here

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.