Pretrained weights for lucid.models.resnest_101_cls.
Single ImageNet-1k checkpoint converted from timm's
resnest101e.in1k (Zhang et al., 2022; ~48.3M params, 82.8%
top-1). Evaluated at 256 crop / 293 resize / bilinear.
Examples
>>> from lucid.models.vision.resnest._weights import ResNeSt101Weights
>>> list(ResNeSt101Weights.__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.
>>> ResNeSt101Weights.DEFAULT is ResNeSt101Weights.IN1K
True
>>> ResNeSt101Weights.IN1K.num_classes
1000