Re:iOS 12 Core ML Benchmarks
by gok on Thursday September 27, 2018 @10:21PM
(#18090498)
Honestly I'm kind of surprised how little buzz there is about the A12's neural engine. ~5 tera-ops in your pocket, and it can run your models. For this particular set of math, that's comparable to a top-of-the-line desktop GPU from 3 years ago.
[ Parent
| on HN ]
There are no comments on this comment yet.