Pretrained weights for lucid.models.maxvit_tiny_cls.
Single ImageNet-1k checkpoint converted from timm's
maxvit_tiny_tf_224.in1k (Tu et al., 2022; ~30.9M params,
83.62% top-1).
Examples
>>> from lucid.models.vision.maxvit._weights import MaxViTTinyWeights
>>> list(MaxViTTinyWeights.__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.
>>> MaxViTTinyWeights.DEFAULT is MaxViTTinyWeights.IN1K
True
>>> MaxViTTinyWeights.IN1K.num_classes
1000