MaxViT-Small backbone (Tu et al., 2022).
Builds the canonical MaxViT-Small configuration: same depths
as MaxViT-Tiny (depths=(2, 2, 5, 2)) but wider —
dims=(96, 192, 384, 768). Approximately 55.8M parameters.
Model Size
Parameters
pretrainedbool= FalseIf
True, loads ImageNet-1k pretrained weights when
available. Defaults to False.**overridesobject= {}Keyword overrides on top of the canonical MaxViT-Small config.
Returns
MaxViTA MaxViT backbone returning a flat
feature.
Notes
MaxViT-Small reaches 84.5% top-1 on ImageNet-1k at 224x224 (Tu et al., 2022, Table 6).
Examples
>>> import lucid
>>> from lucid.models.vision.maxvit import maxvit_small
>>> model = maxvit_small()
>>> x = lucid.randn(1, 3, 224, 224)
>>> model.forward_features(x).shape
(1, 768)