How to use facebook/PE-Core-B16-224 with PerceptionEncoder:
# Use PE-Core models as CLIP models import core.vision_encoder.pe as pe model = pe.CLIP.from_config("facebook/PE-Core-B16-224", pretrained=True)
# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("facebook/PE-Core-B16-224", pretrained=True)
Adds project page URL.
Hi @nielsr , the commit contains "There was an HTTP error fetching the Github README content". Can you take a look?
Hi that looks like a mistake, sorry for the inconvenience.
· Sign up or log in to comment
