Pretrained weights for lucid.models.resnext_50_32x4d_cls.
ResNeXt-50 (32 groups × 4d width, 25.0 M params, top-1 81.20%).
Attributes
IMAGENET1K_V2WeightEntryImageNet-1k V2 checkpoint (top-1 81.198% / top-5 95.340%),
sourced from
torchvision/ResNeXt50_32X4D_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_50_32x4d_cls
>>> model = resnext_50_32x4d_cls(pretrained=True).eval()