Pretrained weights for lucid.models.se_resnet_34_cls.
SE-ResNet-34 (Hu et al. CVPR 2018; 22.0 M params, top-1 73.31%).
Attributes
IN1KWeightEntryImageNet-1k checkpoint (top-1 73.31%), sourced from
timm/legacy_seresnet34.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_34_cls
>>> model = se_resnet_34_cls(pretrained=True).eval()