Pretrained weight tags for lucid.models.resnet_152_cls.
152-layer bottleneck ResNet (60.2 M params, top-1 78.31% / top-5 94.05%).
Attributes
IMAGENET1K_V1WeightEntryImageNet-1k V1 checkpoint (top-1 78.312% / top-5 94.046%),
sourced from
torchvision/ResNet152_Weights.IMAGENET1K_V1.DEFAULTWeightEntryAlias for
IMAGENET1K_V1.Notes
Reference: He, Zhang, Ren, Sun, "Deep Residual Learning for Image Recognition", CVPR 2016 (arXiv:1512.03385).
Examples
>>> from lucid.models import resnet_152_cls
>>> model = resnet_152_cls(pretrained=True).eval()