Pretrained weights for lucid.models.cspresnext_50_cls.
Wang et al. CVPRW 2020 CSP-ResNeXt-50 (20.6 M params, top-1 80.04%).
Attributes
RA_IN1KWeightEntryImageNet-1k RandAugment recipe checkpoint (top-1 80.04%),
sourced from
timm/cspresnext50.ra_in1k.DEFAULTWeightEntryAlias for
RA_IN1K.Notes
Reference: Wang, Liao, Wu, Chen, Hsieh, Yeh, "CSPNet: A New Backbone that can Enhance Learning Capability of CNN", CVPRW 2020 (arXiv:1911.11929).
Examples
>>> from lucid.models import cspresnext_50_cls
>>> model = cspresnext_50_cls(pretrained=True).eval()