Pretrained weights for lucid.models.se_resnet_152_cls.
SE-ResNet-152 (Hu et al. CVPR 2018; 66.8 M params, top-1 78.66%).
Attributes
IN1KWeightEntryImageNet-1k checkpoint (top-1 78.66%), sourced from
timm/legacy_seresnet152.in1k.DEFAULTWeightEntryAlias for
IN1K.Notes
Reference: Hu, Shen, Sun, "Squeeze-and-Excitation Networks", CVPR 2018 (arXiv:1709.01507).
Examples
>>> from lucid.models import se_resnet_152_cls
>>> model = se_resnet_152_cls(pretrained=True).eval()