Help Understanding the use of clip

[IamShubhamGupto]

Hello!

Thank you for the amazing repository. I am trying to understand the role of CLIP in this project. Owl-ViT seems to have its own Text encodings, why do we need clip as well?

Helping me understand this loop would be great !

nanoowl/nanoowl/tree_predictor.py

Line 113 in 9ae3d83

while queue:

Thank you!