Microsoft releases Lobe, an intuitive open-source platform for developing end-to-end machine learning models. Using Lobe, you can build image classification models and export it into a wide range of formats such as Local API, TensorFlow Lite, TensorFlow, and CoreML to integrate with mobile and web apps. Lobe fills a sweet spot for customers looking for a simple and quick way to get started with machine learning using their PCs or Macs without requiring any dependency on the cloud, says Microsoft.
Lobe was acquired by Microsoft in 2018 to democratize machine learning with a no-code platform. The current release, however, can only be used for image classification. But, Microsoft is committed to expanding its capabilities for handling other data types. The next major iteration would be object detection to locate an object inside of an image and data classification to label data in a table based on its content.
The application — Microsoft Lobe — is currently available for Windows and iOS platforms and can work without the Internet or login credentials, thereby ensuring the privacy of the data you use for training the machine learning models.
You can import images or use your device camera to take pictures and label it to train the model. And after the automatic training, it displays the accuracy, which can be further improved by checking and relabeling the inaccurate classification of images. After evaluating the model, you can export and leverage it with applications; these models can also run on small Raspberry Pi.
Also Read: Microsoft & Netflix Launches 3 Free Data Science Modules
However, the final machine learning models are not limited to small projects. Many organizations are using Microsoft Lobe in real-world use cases to automate their business operations. For one, using Microsoft Lobe, The Nature Conservancy is Mapping Ocen Wealth project to evaluate how and where tourism, fishing, and other activities may be affecting essential ocean resources. This is helping five Caribbean countries make conservation and economic decisions.
