Pretrained weights for lucid.models.resnest_200_cls.
Single ImageNet-1k checkpoint converted from timm's
resnest200e.in1k (Zhang et al., 2022; ~70.2M params, 83.9%
top-1). Evaluated at 320 crop / 352 resize / bicubic.
Examples
>>> from lucid.models.vision.resnest._weights import ResNeSt200Weights
>>> list(ResNeSt200Weights.__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.
>>> ResNeSt200Weights.DEFAULT is ResNeSt200Weights.IN1K
True
>>> ResNeSt200Weights.IN1K.num_classes
1000