Pretrained weights for lucid.models.resnest_269_cls.
Single ImageNet-1k checkpoint converted from timm's
resnest269e.in1k (Zhang et al., 2022; ~110.9M params, 84.5%
top-1) — the deepest paper-cited variant. Evaluated at 416 crop /
448 resize / bicubic.
Examples
>>> from lucid.models.vision.resnest._weights import ResNeSt269Weights
>>> list(ResNeSt269Weights.__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.
>>> ResNeSt269Weights.DEFAULT is ResNeSt269Weights.IN1K
True
>>> ResNeSt269Weights.IN1K.num_classes
1000