If you haven’t heard of the Universal Data Tool, it’s an open-source web or desktop program to collaborate, build and edit text, image, video and audio datasets with labels and annotations. You can get started with the Universal Data Tool at universaldatatool.com
This is our first community update! We’re hoping by releasing these we can better engage the community and encourage new contributors. Let’s get started...
New Feature: Automatic Pixel Segmentation (Autoseg)
It can take hours to accurately annotate every pixel of a large image. That’s why we created autoseg, autoseg is a new engine that takes a bunch of points or shapes and automatically creates a pixel mask super fast. What this means is you can now quickly do pixel segmentations directly in the Universal Data Tool!
Automatic pixel segmentation can be found in the “Pixel Segmentation” interface when you’re starting a new project. In the Setup page, just click on “autoseg” under “Automatic Segementation Engine”. Try it out!
For more information about the autoseg engine check out it’s github repo and our image annotation react component.
New Feature: Translation Support
The Universal Data Tool is now available in English, French and Chinese! Big thanks to @puskuruk for putting it together. You can change your language using the dropdown on the landing page.
Adding or fixing translations is also now very easy! All the files you need to edit are in the locales directory.
New Feature: Docker Container Support
For running on servers or quickly testing out the UDT, it can be much faster too
The Universal Data Tool can now run in a docker container! If you have docker installed, you can now run:
docker run -it -p 3000:3000
universaldatatool/universaldatatoolThe Universal Data Tool is now running on http://localhost:3000
That’s it for our first community update, be sure to follow us on Twitter, or join our Slack to hear more!
Previously published at https://universaldatatool.substack.com/p/community-update-1