Pretrained weights for lucid.models.resnest_50_cls.
Single ImageNet-1k checkpoint converted from timm's
resnest50d.in1k (Zhang et al., 2022; ~27.5M params, 81.1%
top-1). Evaluated at 224 crop / 256 resize / bilinear.
Examples
>>> from lucid.models.vision.resnest._weights import ResNeSt50Weights
>>> list(ResNeSt50Weights.__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.
>>> ResNeSt50Weights.DEFAULT is ResNeSt50Weights.IN1K
True
>>> ResNeSt50Weights.IN1K.num_classes
1000