News for hackers. Stuff that matters.

A comment on Researchers unveil a pruning algorithm to shrink deep learning models. Parent comment

Re: Researchers unveil a pruning algorithm to shrink deep le... by yalok on Saturday May 09, 2020 @04:06AM (#23123037)
The trick is to combine these 2 approaches. Quantizing to bytes helps a lot, but forces you to use much larger pruning group size to see any speed up from pruning.
[ Parent | on HN ]

There are no comments on this comment yet.