CoAtNet-4 backbone (Dai et al., 2021).
Even deeper variant: blocks_per_stage=(2, 12, 28, 2),
dims=(192, 384, 768, 1536), stem_width=192,
attn_heads=(24, 48). Approximately 275M parameters, 85.0%
ImageNet-1k top-1 at 224×224 (Table 5). Paper headline with
JFT-3B pretrain reaches 88.4% at 512x512.
Model Size
Examples
>>> import lucid
>>> from lucid.models.vision.coatnet import coatnet_4
>>> model = coatnet_4()
>>> out = model(lucid.randn(1, 3, 224, 224))
>>> out.last_hidden_state.shape
(1, 1536, 7, 7)