Abdelilah Hicham

CLIP by OpenAI — A neural network for connecting text and images

3
CLIP efficiently learns visual concepts from natural language supervision; it can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the “zero-shot” capabilities of GPT-2 and 3.

Add a comment

Replies
Best
Moritz
It's on github! 🥳🥳
Max Prilutskiy
Sounds great! 💯
Jim Engine
For me it's a bit too basic but I think that a lot of people will get the courage to learn about neural networks and classification and find out how to build their own object recognition app.