crossvit_base(pretrained: bool = False, overrides: object = {})CrossViT-B backbone — embed_dims=(384, 768), depths
((1, 4, 0))×3, 12 heads. ~105M params (paper Table 2).
crossvit_base(pretrained: bool = False, overrides: object = {})CrossViT-B backbone — embed_dims=(384, 768), depths
((1, 4, 0))×3, 12 heads. ~105M params (paper Table 2).