MediaPipe-Face-Detection-Quantized: Optimized for Mobile Deployment

Detect faces and locate facial features in real-time video and image streams

Designed for sub-millisecond processing, this model predicts bounding boxes and pose skeletons (left eye, right eye, nose tip, mouth, left eye tragion, and right eye tragion) of faces in an image.

This model is an implementation of MediaPipe-Face-Detection-Quantized found here.

This repository provides scripts to run MediaPipe-Face-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:
- Input resolution: 256x256
- Number of output classes: 6
- Number of parameters (MediaPipeFaceDetector): 135K
- Model size (MediaPipeFaceDetector): 255 KB
- Number of parameters (MediaPipeFaceLandmarkDetector): 603K
- Model size (MediaPipeFaceLandmarkDetector): 746 KB

Model	Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
MediaPipeFaceDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	TFLITE	0.281 ms	0 - 11 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	0.3 ms	0 - 12 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.so
MediaPipeFaceDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	1.056 ms	0 - 9 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	TFLITE	0.189 ms	0 - 24 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	0.207 ms	0 - 24 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.so
MediaPipeFaceDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	0.75 ms	0 - 30 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	TFLITE	0.2 ms	0 - 22 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	0.258 ms	0 - 22 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	0.662 ms	0 - 27 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceDetector	RB3 Gen 2 (Proxy)	QCS6490 Proxy	TFLITE	0.703 ms	0 - 21 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	RB3 Gen 2 (Proxy)	QCS6490 Proxy	QNN	0.764 ms	0 - 11 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	RB5 (Proxy)	QCS8250 Proxy	TFLITE	5.182 ms	0 - 3 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	QCS8550 (Proxy)	QCS8550 Proxy	TFLITE	0.276 ms	0 - 12 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	QCS8550 (Proxy)	QCS8550 Proxy	QNN	0.304 ms	0 - 2 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	SA7255P ADP	SA7255P	TFLITE	1.999 ms	0 - 16 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	SA7255P ADP	SA7255P	QNN	2.192 ms	0 - 10 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	SA8255 (Proxy)	SA8255P Proxy	TFLITE	0.272 ms	0 - 11 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	SA8255 (Proxy)	SA8255P Proxy	QNN	0.306 ms	0 - 2 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	SA8295P ADP	SA8295P	TFLITE	0.683 ms	0 - 21 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	SA8295P ADP	SA8295P	QNN	0.964 ms	0 - 14 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	SA8650 (Proxy)	SA8650P Proxy	TFLITE	0.274 ms	0 - 12 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	SA8650 (Proxy)	SA8650P Proxy	QNN	0.306 ms	0 - 2 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	SA8775P ADP	SA8775P	TFLITE	0.61 ms	0 - 16 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	SA8775P ADP	SA8775P	QNN	0.8 ms	0 - 10 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	QCS8450 (Proxy)	QCS8450 Proxy	TFLITE	0.328 ms	0 - 27 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector	QCS8450 (Proxy)	QCS8450 Proxy	QNN	0.385 ms	0 - 27 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	0.41 ms	0 - 0 MB	FP16	NPU	Use Export Script
MediaPipeFaceDetector	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	1.066 ms	3 - 3 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceLandmarkDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	TFLITE	0.185 ms	0 - 4 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	0.222 ms	0 - 10 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.so
MediaPipeFaceLandmarkDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	0.741 ms	0 - 11 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceLandmarkDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	TFLITE	0.138 ms	0 - 25 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	0.162 ms	0 - 23 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.so
MediaPipeFaceLandmarkDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	0.612 ms	0 - 25 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceLandmarkDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	TFLITE	0.145 ms	0 - 17 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	0.143 ms	0 - 18 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	0.517 ms	0 - 20 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceLandmarkDetector	RB3 Gen 2 (Proxy)	QCS6490 Proxy	TFLITE	0.42 ms	0 - 15 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	RB3 Gen 2 (Proxy)	QCS6490 Proxy	QNN	0.484 ms	0 - 11 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	RB5 (Proxy)	QCS8250 Proxy	TFLITE	3.362 ms	0 - 3 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	QCS8550 (Proxy)	QCS8550 Proxy	TFLITE	0.185 ms	0 - 11 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	QCS8550 (Proxy)	QCS8550 Proxy	QNN	0.22 ms	0 - 3 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	SA7255P ADP	SA7255P	TFLITE	0.867 ms	0 - 11 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	SA7255P ADP	SA7255P	QNN	1.006 ms	0 - 9 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	SA8255 (Proxy)	SA8255P Proxy	TFLITE	0.18 ms	0 - 10 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	SA8255 (Proxy)	SA8255P Proxy	QNN	0.223 ms	0 - 3 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	SA8295P ADP	SA8295P	TFLITE	0.506 ms	0 - 16 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	SA8295P ADP	SA8295P	QNN	0.775 ms	0 - 14 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	SA8650 (Proxy)	SA8650P Proxy	TFLITE	0.184 ms	0 - 3 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	SA8650 (Proxy)	SA8650P Proxy	QNN	0.223 ms	0 - 2 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	SA8775P ADP	SA8775P	TFLITE	0.435 ms	0 - 11 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	SA8775P ADP	SA8775P	QNN	0.624 ms	0 - 10 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	QCS8450 (Proxy)	QCS8450 Proxy	TFLITE	0.228 ms	0 - 16 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector	QCS8450 (Proxy)	QCS8450 Proxy	QNN	0.254 ms	0 - 18 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	0.332 ms	0 - 0 MB	FP16	NPU	Use Export Script
MediaPipeFaceLandmarkDetector	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	0.76 ms	1 - 1 MB	FP16	NPU	MediaPipe-Face-Detection-Quantized.onnx

Installation

Install the package via pip:

pip install "qai-hub-models[mediapipe-face-quantized]"

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.mediapipe_face_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.mediapipe_face_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.mediapipe_face_quantized.export

Profiling Results
------------------------------------------------------------
MediaPipeFaceDetector
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 0.3                    
Estimated peak memory usage (MB): [0, 11]                
Total # Ops                     : 121                    
Compute Unit(s)                 : NPU (121 ops)          

------------------------------------------------------------
MediaPipeFaceLandmarkDetector
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 0.2                    
Estimated peak memory usage (MB): [0, 4]                 
Total # Ops                     : 117                    
Compute Unit(s)                 : NPU (117 ops)

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 MediaPipe-Face-Detection-Quantized's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

The license for the original implementation of MediaPipe-Face-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.