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.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of device

device

Photo of E2EE

E2EE

Related news:

News photo

Sci-fi inspired antenna adjusts to signal needs

News photo

Indian police demand Starlink reveal buyer of device found in $4.2 billion drug bust | Smugglers were caught with 13,227 pounds of meth

News photo

Xreal’s new One Series AR glasses use USB-C to connect with nearly any device