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

I recommend looking into "transfer learning".

That's where you start with an existing large model, and train a new model on top of it by feeding in new images.

What's fascinating about transfer learning is that you don't need to give it a lot of new images, at all. Just a few hundred extras can create a model that's frighteningly accurate for tasks like image labeling.

This is pretty much how all AI models work today. Take a look at the Stable Diffusion model card: https://github.com/CompVis/stable-diffusion/blob/main/Stable...

They ran multiple training sessions with progressively smaller (and higher quality) images to get the final result.



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

Search: