Hugging Face's logo

qualcomm
/
MediaPipe-Face-Detection

Object Detection
PyTorch
LiteRT
real_time
android
Model card Files Community
2

MediaPipe-Face-Detection: 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 found here.

This repository provides scripts to run MediaPipe-Face-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:
    • Input resolution: 256x256
    • Number of output classes: 6
    • Number of parameters (FaceDetector): 135K
    • Model size (FaceDetector) (w8a8): 260 KB
    • Number of parameters (FaceLandmarkDetector): 603K
    • Model size (FaceLandmarkDetector) (w8a8): 750 KB
    • Model size (FaceDetector) (float): 557 KB
    • Model size (FaceLandmarkDetector) (float): 2.33 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
FaceDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 2.908 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 2.871 ms 1 - 16 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.762 ms 0 - 25 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 0.747 ms 1 - 23 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.545 ms 0 - 6 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 0.533 ms 1 - 7 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 1.058 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 1.022 ms 1 - 18 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float SA7255P ADP Qualcomm® SA7255P TFLITE 2.908 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA7255P ADP Qualcomm® SA7255P QNN_DLC 2.871 ms 1 - 16 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.548 ms 0 - 6 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 0.534 ms 1 - 7 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float SA8295P ADP Qualcomm® SA8295P TFLITE 1.138 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8295P ADP Qualcomm® SA8295P QNN_DLC 1.095 ms 1 - 20 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.55 ms 0 - 7 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 0.535 ms 1 - 6 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float SA8775P ADP Qualcomm® SA8775P TFLITE 1.058 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8775P ADP Qualcomm® SA8775P QNN_DLC 1.022 ms 1 - 18 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.551 ms 0 - 6 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 0.533 ms 1 - 8 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.82 ms 0 - 8 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.395 ms 0 - 26 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 0.376 ms 0 - 29 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.583 ms 0 - 27 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.412 ms 0 - 23 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 0.326 ms 2 - 23 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.594 ms 1 - 20 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 0.69 ms 7 - 7 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.894 ms 2 - 2 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 0.856 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 0.841 ms 0 - 13 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.27 ms 0 - 27 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 0.319 ms 0 - 23 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.195 ms 0 - 10 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 0.214 ms 0 - 9 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.429 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 0.445 ms 0 - 15 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float SA7255P ADP Qualcomm® SA7255P TFLITE 0.856 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA7255P ADP Qualcomm® SA7255P QNN_DLC 0.841 ms 0 - 13 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.196 ms 0 - 9 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 0.214 ms 0 - 9 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float SA8295P ADP Qualcomm® SA8295P TFLITE 0.55 ms 0 - 24 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8295P ADP Qualcomm® SA8295P QNN_DLC 0.608 ms 0 - 17 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.196 ms 0 - 10 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 0.213 ms 0 - 5 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float SA8775P ADP Qualcomm® SA8775P TFLITE 0.429 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8775P ADP Qualcomm® SA8775P QNN_DLC 0.445 ms 0 - 15 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.186 ms 0 - 9 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 0.216 ms 0 - 10 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.383 ms 0 - 8 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.137 ms 0 - 30 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 0.158 ms 0 - 26 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.264 ms 0 - 25 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.186 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 0.134 ms 0 - 18 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.244 ms 0 - 20 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 0.316 ms 5 - 5 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.398 ms 0 - 0 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 0.661 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 0.647 ms 0 - 17 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.276 ms 0 - 33 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 0.278 ms 0 - 30 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.236 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 0.234 ms 0 - 6 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.449 ms 0 - 19 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 0.417 ms 0 - 18 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 0.667 ms 0 - 21 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 0.701 ms 0 - 22 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 5.46 ms 0 - 3 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 0.661 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 0.647 ms 0 - 17 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.234 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 0.236 ms 0 - 11 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 0.576 ms 0 - 19 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 0.572 ms 0 - 20 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.232 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 0.228 ms 0 - 11 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 0.449 ms 0 - 19 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 0.417 ms 0 - 18 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.23 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 0.228 ms 0 - 11 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.367 ms 0 - 11 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.15 ms 0 - 34 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 0.152 ms 0 - 30 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.239 ms 0 - 34 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.158 ms 0 - 24 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 0.176 ms 0 - 24 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.28 ms 0 - 21 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 0.328 ms 2 - 2 MB NPU MediaPipe-Face-Detection.dlc
FaceDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.38 ms 1 - 1 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 0.51 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 0.466 ms 0 - 13 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.188 ms 0 - 23 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 0.196 ms 0 - 30 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.158 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 0.157 ms 0 - 11 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.339 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 0.315 ms 0 - 14 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 0.366 ms 0 - 19 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 0.393 ms 0 - 16 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 2.712 ms 0 - 3 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 0.51 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 0.466 ms 0 - 13 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.151 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 0.153 ms 0 - 11 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 0.455 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 0.441 ms 0 - 23 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.158 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 0.144 ms 0 - 11 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 0.339 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 0.315 ms 0 - 14 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.159 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 0.146 ms 0 - 11 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.294 ms 0 - 11 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.117 ms 0 - 27 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 0.102 ms 0 - 29 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.21 ms 0 - 30 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.118 ms 0 - 21 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 0.126 ms 0 - 19 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.22 ms 0 - 20 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 0.257 ms 5 - 5 MB NPU MediaPipe-Face-Detection.dlc
FaceLandmarkDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.322 ms 0 - 0 MB NPU MediaPipe-Face-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.mediapipe_face.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.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.export

Profiling Results
------------------------------------------------------------
FaceDetector
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 0.7                                  
Estimated peak memory usage (MB): [0, 17]                              
Total # Ops                     : 114                                  
Compute Unit(s)                 : npu (114 ops) gpu (0 ops) cpu (0 ops)

------------------------------------------------------------
FaceLandmarkDetector
Device                          : cs_8275 (ANDROID 14)                 
Runtime                         : TFLITE                               
Estimated inference time (ms)   : 0.5                                  
Estimated peak memory usage (MB): [0, 14]                              
Total # Ops                     : 108                                  
Compute Unit(s)                 : npu (108 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.mediapipe_face 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.

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

References

Community

Downloads last month
218
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support