Pretrained weights for lucid.models.convnext_small_cls.
Currently ships IMAGENET1K_V1 — reference_vision's ImageNet-1k
checkpoint (acc@1 = 83.616 / acc@5 = 96.650).
Examples
>>> from lucid.models.vision.convnext._weights import ConvNeXtSmallWeights
>>> list(ConvNeXtSmallWeights.__members__)
['IMAGENET1K_V1', 'DEFAULT']
DEFAULT is an alias rather than a fourth entry, so a bare
pretrained=True and the tag it resolves to cannot drift apart.
>>> ConvNeXtSmallWeights.DEFAULT is ConvNeXtSmallWeights.IMAGENET1K_V1
True
>>> ConvNeXtSmallWeights.IMAGENET1K_V1.num_classes
1000