Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

For multi-modal check out OpenAI CLIP: https://www.pinecone.io/learn/clip/


Exactly what I'm looking for, thank you.

EDIT: I am immediately struck that I need vastly more data and compute than I can afford for my experiment.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: