ConvNeXt-Small backbone (Liu et al., 2022).
Builds the canonical ConvNeXt-S configuration: depths=(3, 3, 27, 3)
(3x deeper stage 3 than ConvNeXt-T), dims=(96, 192, 384, 768).
Approximately 50M parameters — Swin-S equivalent.
Model Size
Parameters
pretrainedbool= FalseIf
True, loads ImageNet-1k pretrained weights when available.
Defaults to False.**overridesobject= {}Keyword overrides on top of the canonical ConvNeXt-S config.
Returns
ConvNeXtA ConvNeXt backbone returning a flat
feature.
Notes
ConvNeXt-S reaches 83.1% top-1 on ImageNet-1k (Liu et al., 2022, Table 1).
Examples
>>> import lucid
>>> from lucid.models.vision.convnext import convnext_small
>>> model = convnext_small()
>>> x = lucid.randn(1, 3, 224, 224)
>>> model.forward_features(x).shape
(1, 768)