Pretrained weights for lucid.models.maxvit_base_cls.
Single ImageNet-1k checkpoint converted from timm's
maxvit_base_tf_224.in1k (Tu et al., 2022; ~119.5M params,
84.95% top-1).
Examples
>>> from lucid.models.vision.maxvit._weights import MaxViTBaseWeights
>>> list(MaxViTBaseWeights.__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.
>>> MaxViTBaseWeights.DEFAULT is MaxViTBaseWeights.IN1K
True
>>> MaxViTBaseWeights.IN1K.num_classes
1000