Hacker News new | past | comments | ask | show | jobs | submit login

According to the ViperGPT paper their "ImagePatch.find()" uses GLIP.

According to the GLIP paper,† accuracy on a test-set not seen during training is around 60% so... neat demos but whether it'll be reliable enough depends on your application.

https://arxiv.org/abs/2206.05836




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

Search: