MediaPipe Iris Demo

This guide shows how to implement MediaPipe graph using OVMS.

Example usage of graph that accepts Mediapipe::ImageFrame as a input:

The demo is based on the Mediapipe Iris demo

Prepare the server deployment

Clone the repository and enter mediapipe object_detection directory

git clone
cd model_server/demos/mediapipe/iris_tracking


Pull the Latest Model Server Image

Pull the latest version of OpenVINO™ Model Server from Docker Hub:

docker pull openvino/model_server:latest

Run OpenVINO Model Server

docker run -d -v $PWD/mediapipe:/mediapipe -v $PWD/ovms:/models -p 9000:9000 openvino/model_server:latest --config_path /models/config_iris.json --port 9000

Run client application for iris tracking

pip install -r requirements.txt
# download a sample image for analysis
echo "people2.jpeg" > input_images.txt
# launch the client
python --grpc_port 9000 --images_list input_images.txt
Running demo application.
Start processing:
        Graph name: irisTracking
(800, 1200, 3)
Iteration 0; Processing time: 44.73 ms; speed 22.36 fps
Results saved to :image_0.jpg

Output image