News for hackers. Stuff that matters.
Re:How to train large deep learning models as a startup by andyxor on Thursday October 07, 2021 @01:34PM (#28789600)
it's more like try different off-the-shelf models on some sample of data until the performance is somewhat acceptable

Unless you're Google, who even trains models from scratch these days, at most you do some fine-tuning

There are no comments on this comment yet.