How to use facebook/PE-Spatial-B16-512 with PerceptionEncoder:
# Use any PE model as a vision encoder import core.vision_encoder.pe as pe model = pe.VisionTransformer.from_config("facebook/PE-Spatial-B16-512", pretrained=True)
6798ebf b8dd9d0 6798ebf
1
2
3
4
version https://git-lfs.github.com/spec/v1 oid sha256:86217607f0bb28c0adb5ac3f9b0608ae22f6fb634bf1c16b2316847e8148a2a5 size 345783707
