Get the latest tech news
Machine Learning at Ente – On-Device, E2EE
Overview of Ente's on-device Machine Learning
Image processing methods can make or break any computer vision experience, as artifacts such as aliasing can have significant negative effects on the model output. We've become very comfortable rewriting existing data science (Python) packages for our specific platforms, be it in Dart, Javascript, Kotlin, Swift or Rust. While all of these ML frameworks come with their own perks and quirks, we have grown to love ORT for its reliability across many devices and its interoperability to accommodate all kinds of different models.
Or read this on Hacker News