Try the Model

Use the widget below to experiment with MediaPipe. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

MediaPipe is a versatile open source framework made for a variety of tasks. First released in the Google I/O conference in 2023, MediaPipe is able to achieve many tasks from creating a face mesh to 3d object tracking. The development of MediaPipe first began in 2012, with a small team of Google Engineers.

‍

One notorious example of MediaPipes features is its pose estimation. Here, we can visualize the objects it is able to capture.

‍

Additionally, MediaPipe also creates fascinating face meshs. Build your own face mesh using supervision.

MediaPipe License

MediaPipe

is licensed under a

license.

Performance

Deploy a MediaPipe API

You can use Roboflow Inference to deploy a

MediaPipe

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with MediaPipe

You can automatically label a dataset using MediaPipe with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use MediaPipe to train a computer vision model.

No items found.