convnext_large_cls(pretrained: bool | str = False, weights: ConvNeXtLargeWeights | None = None, overrides: object = {})ConvNeXt-Large image classifier (Liu et al., 2022).
Combines the convnext_large backbone (depths=(3, 3, 27, 3),
dims=(192, 384, 768, 1536)) with a global average pool +
LayerNorm + linear classification head. ~198M parameters.
Model Size
Parameters
pretrainedbool= FalseIf
True, loads ImageNet-22k pretrained weights when
available. Defaults to False.Explicit weights enum member; takes precedence over
pretrained.**overridesobject= {}Keyword overrides on top of the canonical ConvNeXt-L config.
Returns
ConvNeXtForImageClassificationClassifier whose logits has shape (B, num_classes).
Notes
ConvNeXt-L reaches 84.3% top-1 on ImageNet-1k (224x224) and 86.6% top-1 at 384x384 after ImageNet-22k pretraining (Liu et al., 2022, Tables 1 and 11).
Examples
>>> import lucid
>>> from lucid.models.vision.convnext import convnext_large_cls
>>> model = convnext_large_cls(num_classes=1000)
>>> x = lucid.randn(1, 3, 224, 224)
>>> model(x).logits.shape
(1, 1000)
Load ImageNet-pretrained weights:
>>> model = convnext_large_cls(pretrained=True)
>>> from lucid.models.weights import ConvNeXtLargeWeights
>>> model = convnext_large_cls(weights=ConvNeXtLargeWeights.IMAGENET1K_V1)