Thanks to @matthen2, I got to test out my new candidate DeOldify model on a use case that I think will be quite appealing for many people: wedding photos! Thanks Matt!pic.twitter.com/OEscz5XhiW
Show this thread
-
No question, many, many. I suppose this happens as well in, say, NLP where inbound language could be any language.
Yes that’s actually a great example where training in many languages benefits performance in all said languages in a mutually beneficial way. More correct generalizations can be modeled, I gather.
-
-
I think it’s also true in humans that learning multiple languages makes learning the incremental language easier. But whether or not it makes -accents- easier or harder to pronounce, I’m not sure. In other words general rules can be picked up, but maybe nuance comes w/specialz’n
-
I would think a pure wedding photo model that’s learned only from wedding portraits would outperform a general photo learner, but again I’m in preschool on this compared to your work. Totally spitballing, and believe you when you say it’s not actually true in practice.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.