Some of the AI functions promised by all this code includs tools for image classification, depth segmentation, text analysis, translation, and more.
What, who, why?
They cover a wide range of applications, including FastViT for image classification, DepthAnything for monocular depth estimation, and DETR for semantic segmentation.
The models are not intended for mass market use and are aimed at developers, who can download them, convert them to CoreML format, and then deploy them in their own code. The process for this was explained at WWDC 2024 in a presentation that details how the models can be deployed once converted. It is also worth noting CoreML is much, much faster in iOS 18, as Apple said.