Hugging Face's logo

qualcomm
/
MediaPipe-Face-Detection

Object Detection
PyTorch
LiteRT
ONNX
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 parameters (MediaPipeFaceDetector): 135K
    • Model size (MediaPipeFaceDetector): 565 KB
    • Number of parameters (MediaPipeFaceLandmarkDetector): 603K
    • Model size (MediaPipeFaceLandmarkDetector): 2.34 MB
    • Number of output classes: 6
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 18.746 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 18.656 ms 1 - 10 MB NPU Use Export Script
FaceDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.764 ms 0 - 28 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.733 ms 1 - 29 MB NPU Use Export Script
FaceDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.546 ms 0 - 6 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.532 ms 1 - 4 MB NPU Use Export Script
FaceDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 1.075 ms 0 - 18 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 1.013 ms 1 - 13 MB NPU Use Export Script
FaceDetector float SA7255P ADP Qualcomm® SA7255P TFLITE 18.746 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA7255P ADP Qualcomm® SA7255P QNN 18.656 ms 1 - 10 MB NPU Use Export Script
FaceDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.546 ms 0 - 6 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.535 ms 1 - 4 MB NPU Use Export Script
FaceDetector float SA8295P ADP Qualcomm® SA8295P TFLITE 1.129 ms 0 - 17 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8295P ADP Qualcomm® SA8295P QNN 1.061 ms 0 - 18 MB NPU Use Export Script
FaceDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.552 ms 0 - 7 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.531 ms 0 - 2 MB NPU Use Export Script
FaceDetector float SA8775P ADP Qualcomm® SA8775P TFLITE 1.075 ms 0 - 18 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float SA8775P ADP Qualcomm® SA8775P QNN 1.013 ms 1 - 13 MB NPU Use Export Script
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.547 ms 0 - 7 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.535 ms 1 - 7 MB NPU Use Export Script
FaceDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.84 ms 1 - 7 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.399 ms 0 - 27 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.385 ms 1 - 26 MB NPU Use Export Script
FaceDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.575 ms 1 - 29 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.415 ms 0 - 19 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.325 ms 0 - 21 MB NPU Use Export Script
FaceDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.603 ms 1 - 22 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector float Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.673 ms 1 - 1 MB NPU Use Export Script
FaceDetector float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.862 ms 2 - 2 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 3.564 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 3.562 ms 0 - 10 MB NPU Use Export Script
FaceLandmarkDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.274 ms 0 - 21 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.333 ms 0 - 21 MB NPU Use Export Script
FaceLandmarkDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.198 ms 0 - 10 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.216 ms 0 - 3 MB NPU Use Export Script
FaceLandmarkDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.438 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 0.436 ms 0 - 13 MB NPU Use Export Script
FaceLandmarkDetector float SA7255P ADP Qualcomm® SA7255P TFLITE 3.564 ms 0 - 14 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA7255P ADP Qualcomm® SA7255P QNN 3.562 ms 0 - 10 MB NPU Use Export Script
FaceLandmarkDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.193 ms 0 - 10 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.214 ms 0 - 2 MB NPU Use Export Script
FaceLandmarkDetector float SA8295P ADP Qualcomm® SA8295P TFLITE 0.555 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8295P ADP Qualcomm® SA8295P QNN 0.598 ms 0 - 18 MB NPU Use Export Script
FaceLandmarkDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.196 ms 0 - 9 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.215 ms 0 - 3 MB NPU Use Export Script
FaceLandmarkDetector float SA8775P ADP Qualcomm® SA8775P TFLITE 0.438 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float SA8775P ADP Qualcomm® SA8775P QNN 0.436 ms 0 - 13 MB NPU Use Export Script
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.19 ms 0 - 10 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.215 ms 0 - 9 MB NPU Use Export Script
FaceLandmarkDetector float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.373 ms 0 - 8 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.144 ms 0 - 25 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.145 ms 0 - 24 MB NPU Use Export Script
FaceLandmarkDetector float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.278 ms 0 - 27 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.123 ms 0 - 23 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.19 ms 0 - 23 MB NPU Use Export Script
FaceLandmarkDetector float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.324 ms 0 - 15 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector float Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.309 ms 0 - 0 MB NPU Use Export Script
FaceLandmarkDetector float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.373 ms 0 - 0 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 1.856 ms 0 - 18 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 1.824 ms 0 - 10 MB NPU Use Export Script
FaceDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.275 ms 0 - 28 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.277 ms 0 - 26 MB NPU Use Export Script
FaceDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.231 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.221 ms 0 - 2 MB NPU Use Export Script
FaceDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.436 ms 0 - 20 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 0.419 ms 0 - 12 MB NPU Use Export Script
FaceDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 0.625 ms 0 - 20 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 0.638 ms 0 - 11 MB NPU Use Export Script
FaceDetector w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 4.95 ms 0 - 3 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 1.856 ms 0 - 18 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA7255P ADP Qualcomm® SA7255P QNN 1.824 ms 0 - 10 MB NPU Use Export Script
FaceDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.226 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.225 ms 0 - 3 MB NPU Use Export Script
FaceDetector w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 0.552 ms 0 - 25 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8295P ADP Qualcomm® SA8295P QNN 0.544 ms 0 - 17 MB NPU Use Export Script
FaceDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.232 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.234 ms 0 - 3 MB NPU Use Export Script
FaceDetector w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 0.436 ms 0 - 20 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 SA8775P ADP Qualcomm® SA8775P QNN 0.419 ms 0 - 12 MB NPU Use Export Script
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.236 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.234 ms 0 - 11 MB NPU Use Export Script
FaceDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.361 ms 0 - 11 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.16 ms 0 - 32 MB NPU MediaPipe-Face-Detection.tflite
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.146 ms 0 - 31 MB NPU Use Export Script
FaceDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.241 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 0.149 ms 0 - 23 MB NPU Use Export Script
FaceDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.262 ms 0 - 21 MB NPU MediaPipe-Face-Detection.onnx
FaceDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.318 ms 0 - 0 MB NPU Use Export Script
FaceDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.363 ms 1 - 1 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 0.803 ms 0 - 13 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 0.785 ms 0 - 10 MB NPU Use Export Script
FaceLandmarkDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 0.188 ms 0 - 24 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 0.195 ms 0 - 23 MB NPU Use Export Script
FaceLandmarkDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 0.151 ms 0 - 11 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 0.153 ms 0 - 2 MB NPU Use Export Script
FaceLandmarkDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 0.342 ms 0 - 15 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 0.323 ms 0 - 13 MB NPU Use Export Script
FaceLandmarkDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 0.415 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 0.422 ms 0 - 12 MB NPU Use Export Script
FaceLandmarkDetector w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 2.783 ms 0 - 3 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 0.803 ms 0 - 13 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA7255P ADP Qualcomm® SA7255P QNN 0.785 ms 0 - 10 MB NPU Use Export Script
FaceLandmarkDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 0.16 ms 0 - 5 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN 0.151 ms 0 - 2 MB NPU Use Export Script
FaceLandmarkDetector w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 0.457 ms 0 - 16 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8295P ADP Qualcomm® SA8295P QNN 0.439 ms 0 - 17 MB NPU Use Export Script
FaceLandmarkDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 0.144 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN 0.151 ms 0 - 2 MB NPU Use Export Script
FaceLandmarkDetector w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 0.342 ms 0 - 15 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 SA8775P ADP Qualcomm® SA8775P QNN 0.323 ms 0 - 13 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 0.15 ms 0 - 12 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 0.146 ms 0 - 11 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 0.289 ms 0 - 12 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 0.117 ms 0 - 28 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 0.109 ms 0 - 24 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 0.225 ms 0 - 30 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 0.117 ms 0 - 21 MB NPU MediaPipe-Face-Detection.tflite
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 0.111 ms 0 - 20 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 0.275 ms 0 - 19 MB NPU MediaPipe-Face-Detection.onnx
FaceLandmarkDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN 0.224 ms 0 - 0 MB NPU Use Export Script
FaceLandmarkDetector w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 0.288 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)   : 1.9                                  
Estimated peak memory usage (MB): [0, 18]                              
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)   : 0.8                                  
Estimated peak memory usage (MB): [0, 13]                              
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
754
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support