Early bird prices are coming to an end soon... ⏰ Grab your tickets before January 17

This article was published on October 27, 2020

Microsoft unveils FREE app to create AI models without writing any code

Lobe automatically trains machine learning models on images you upload


Microsoft unveils FREE app to create AI models without writing any code

Microsoft has released a public preview of a free app lets helps people train machine learning models without writing any code.

The Lobe desktop app for Windows and Mac currently only supports image classification, but Microsoft plans to expand it to other models and data types in the future.

“Just show it examples of what you want it to learn, and it automatically trains a custom machine learning model that can be shipped in your app,” the Lobe website explains.

Users first need to import and label images of what they want Lobe to recognize. The app will then select a suitable open-source machine learning architecture for the dataset and start training the model on the user’s device.

The 💜 of EU tech

The latest rumblings from the EU tech scene, a story from our wise ol' founder Boris, and some questionable AI art. It's free, every week, in your inbox. Sign up now!

[Read: What audience intelligence data tells us about the 2020 US presidential election]

You can also review the model’s performance through real-time visual results, offer feedback on its predictions, and correct inaccurate labels.

Credit: Mike Matas, Microsoft
Microsoft acquired Lobe in 2018 to make AI development more accessible.

After training, the models can be exported to a variety of industry-standard formats and shipped on a platform of the user’s choice.

Microsoft says early customers have used Lobe to build apps that identify harmful plants, detect beehive invaders such as wasps, or send people alerts when they’ve accidentally left their garage door open.

If you want to join them, you can download Lobe here and view a video tutorial for the app here.

Get the TNW newsletter

Get the most important tech news in your inbox each week.

Also tagged with