coatnet_5_cls(pretrained: bool = False, overrides: object = {})CoAtNet-5 image classifier (Dai et al., 2021).
Widest paper-cited variant — dims=(256, 512, 1280, 2048) — with
the standard CoAtNet head. Approximately 688M parameters,
85.8% ImageNet-1k top-1 at 224x224 (Table 5).
Model Size
Examples
>>> import lucid
>>> from lucid.models.vision.coatnet import coatnet_5_cls
>>> model = coatnet_5_cls()
>>> out = model(lucid.randn(1, 3, 224, 224))
>>> out.logits.shape
(1, 1000)