Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library

Comment by jerpint

2 months ago

Batching can lead to variance with things like batchnorm but most transformers use layer norm to avoid this problem

1 comment

jerpint

Reply

amelius  2 months ago

Batchnorm can only have an effect between batches during training, not inference.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities