Pretrained weights for lucid.models.cvt_13_cls.
Wu et al. ICCV 2021 13-layer convolutional ViT (20 M params, top-1 81.6%).
Attributes
IN1KWeightEntryImageNet-1k 224x224 finetune (top-1 81.6%), sourced from
transformers/microsoft/cvt-13.DEFAULTWeightEntryAlias for
IN1K.Notes
Reference: Wu, Xiao, Codella, Liu, Dai, Yuan, Zhang, "CvT: Introducing Convolutions to Vision Transformers", ICCV 2021 (arXiv:2103.15808).
Examples
>>> from lucid.models import cvt_13_cls
>>> model = cvt_13_cls(pretrained=True).eval()