Thomas MacaulaySenior reporter
Thomas is a senior reporter at TNW. He covers European tech, with a focus on deeptech, startups, and government policy. Thomas is a senior reporter at TNW. He covers European tech, with a focus on deeptech, startups, and government policy.
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.
You can also review the model’s performance through real-time visual results, offer feedback on its predictions, and correct inaccurate labels.
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.