Microsoft just added 3 interesting new Features to Lobe
Microsoft just released a new version of its tool that lets you train AI models without writing a single line of code
Microsoft released a brand new version of Lobe that will open a new range of possibilities and projects that can be built using machine learning.
Lobe is a Windows or Mac desktop software program that allows everyone to create machine-learning models for image classification.
It lets you build machine learning models with the help of a simple drag-and-drop interface.
This new update introduces four significant improvements — the ability to select which camera you want to use in Lobe, new export formats, accelerated GPU training, and increased app performance.
Input from any connected camera
Now Lobe’s Data collection happens in more places than just in front of your computer.
This new update adds the ability to select any connected camera right inside Lobe, for example, a USB camera, that makes data collection more seamless than ever.
Export your models
Another exciting update is that Lobe introduced ONNX and TensorFlow.js support to export your model universally or use it specifically on the web. And worths noting that TensorFlow Lite export now works with Android, and this is a breaking change for existing exported models.
Training models with GPU Acceleration
But maybe the most exciting update is that Lobe now supports GPU acceleration, which will make training faster and more efficient.
This will allow training to recede to the background, even more, making the overall experience of building a model more enjoyable.
Accelerated GPU training is available on Windows today, and Microsoft says that macOS support will come soon.
As a first impression, in this new release, Lobe is faster and runs smoother in scrolling and reacting to my interactions. You must try it yourself!
Lobe is an exciting software that can bring AI and Computer Vision to the masses since the first release. You can download it for free to get started on your machine learning models and join the community to share your feedback and see what others are building.
Now, by making Lobe faster, more performant, and expanding its capabilities with more export formats and camera sources, Microsoft is opening a whole new range of possibilities for easy, powerful, and portable machine learning projects. For everyone!
Further related content
If you want to read more about Lobe, Artificial Intelligence, and Data Science, here you have some other articles I’ve written about it: