Pretrained weights for lucid.models.maxvit_large_cls.
Single ImageNet-1k checkpoint converted from timm's
maxvit_large_tf_224.in1k (Tu et al., 2022; ~211.8M params,
85.17% top-1).
Examples
>>> from lucid.models.vision.maxvit._weights import MaxViTLargeWeights
>>> list(MaxViTLargeWeights.__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.
>>> MaxViTLargeWeights.DEFAULT is MaxViTLargeWeights.IN1K
True
>>> MaxViTLargeWeights.IN1K.num_classes
1000