Pretrained weights for lucid.models.maxvit_small_cls.
Single ImageNet-1k checkpoint converted from timm's
maxvit_small_tf_224.in1k (Tu et al., 2022; ~68.9M params,
84.45% top-1).
Examples
>>> from lucid.models.vision.maxvit._weights import MaxViTSmallWeights
>>> list(MaxViTSmallWeights.__members__)
['IN1K', 'DEFAULT']
DEFAULT is an alias rather than a fourth entry, so a bare
pretrained=True and the tag it resolves to cannot drift apart.
>>> MaxViTSmallWeights.DEFAULT is MaxViTSmallWeights.IN1K
True
>>> MaxViTSmallWeights.IN1K.num_classes
1000