Hugging Face's logo

qualcomm
/
MediaPipe-Face-Detection-Quantized

Object Detection
PyTorch
LiteRT
ONNX
real_time
quantized
android
Model card Files Community
MediaPipe-Face-Detection-Quantized / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
082b11d verified
preview code
|
raw
history blame
14.7 kB
metadata
library_name: pytorch
license: apache-2.0
tags:
  - real_time
  - quantized
  - android
pipeline_tag: object-detection

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 0.267 ms 0 - 11 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 0.789 ms 0 - 10 MB FP16 NPU MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceDetector Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 0.171 ms 0 - 28 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 0.507 ms 0 - 31 MB FP16 NPU MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceDetector Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 0.185 ms 0 - 23 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 0.533 ms 0 - 27 MB FP16 NPU MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceDetector SA8255 (Proxy) SA8255P Proxy TFLITE 0.269 ms 0 - 11 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector SA8295P ADP SA8295P TFLITE 0.629 ms 0 - 22 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector SA8650 (Proxy) SA8650P Proxy TFLITE 0.27 ms 0 - 5 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector SA8775P ADP SA8775P TFLITE 0.556 ms 0 - 17 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector RB3 Gen 2 (Proxy) QCS6490 Proxy TFLITE 0.701 ms 0 - 22 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector RB5 (Proxy) QCS8250 Proxy TFLITE 5.335 ms 0 - 3 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector QCS8550 (Proxy) QCS8550 Proxy TFLITE 0.268 ms 0 - 12 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector QCS9075 (Proxy) QCS9075 Proxy TFLITE 0.556 ms 0 - 17 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector QCS8450 (Proxy) QCS8450 Proxy TFLITE 0.306 ms 0 - 22 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceDetector Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.759 ms 1 - 1 MB FP16 NPU MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceLandmarkDetector Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 0.183 ms 0 - 10 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 0.481 ms 0 - 10 MB FP16 NPU MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceLandmarkDetector Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 0.133 ms 0 - 21 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 0.365 ms 0 - 28 MB FP16 NPU MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceLandmarkDetector Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 0.116 ms 0 - 19 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 0.364 ms 0 - 26 MB FP16 NPU MediaPipe-Face-Detection-Quantized.onnx
MediaPipeFaceLandmarkDetector SA7255P ADP SA7255P TFLITE 0.855 ms 0 - 11 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector SA8255 (Proxy) SA8255P Proxy TFLITE 0.183 ms 0 - 11 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector SA8295P ADP SA8295P TFLITE 0.498 ms 0 - 18 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector SA8650 (Proxy) SA8650P Proxy TFLITE 0.187 ms 0 - 11 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector SA8775P ADP SA8775P TFLITE 0.437 ms 0 - 13 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector RB3 Gen 2 (Proxy) QCS6490 Proxy TFLITE 0.418 ms 0 - 16 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector RB5 (Proxy) QCS8250 Proxy TFLITE 3.457 ms 0 - 3 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector QCS8275 (Proxy) QCS8275 Proxy TFLITE 0.855 ms 0 - 11 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector QCS8550 (Proxy) QCS8550 Proxy TFLITE 0.186 ms 0 - 11 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector QCS9075 (Proxy) QCS9075 Proxy TFLITE 0.437 ms 0 - 13 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector QCS8450 (Proxy) QCS8450 Proxy TFLITE 0.244 ms 0 - 19 MB FP16 NPU MediaPipe-Face-Detection-Quantized.tflite
MediaPipeFaceLandmarkDetector Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.486 ms 0 - 0 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, 10]                
Total # Ops                     : 116                    
Compute Unit(s)                 : NPU (116 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