crossvit_small(pretrained: bool = False, overrides: object = {})CrossViT-S backbone — embed_dims=(192, 384), depths
((1, 4, 0))×3, 6 heads. ~26.7M params (paper Table 2).
Model Size
Examples
>>> import lucid
>>> from lucid.models.vision.crossvit import crossvit_small
>>> model = crossvit_small()
>>> out = model(lucid.randn(1, 3, 240, 240))
>>> out.last_hidden_state.shape
(1, 576)