Pretrained weights for lucid.models.resnext_101_32x8d_cls.
ResNeXt-101 (32 groups × 8d width, 88.8 M params, top-1 82.83%).
Attributes
IMAGENET1K_V2WeightEntryImageNet-1k V2 checkpoint (top-1 82.834% / top-5 96.228%),
sourced from
torchvision/ResNeXt101_32X8D_Weights.IMAGENET1K_V2.DEFAULTWeightEntryAlias for
IMAGENET1K_V2.Notes
Reference: Xie, Girshick, Dollár, Tu, He, "Aggregated Residual Transformations for Deep Neural Networks", CVPR 2017 (arXiv:1611.05431).
Examples
>>> from lucid.models import resnext_101_32x8d_cls
>>> model = resnext_101_32x8d_cls(pretrained=True).eval()