class
Segmentation
extends
TransformsPresetSegmentation(crop_size: int, resize_size: int = 520, mean: tuple[float, ...] | None = None, std: tuple[float, ...] | None = None, interpolation: str | Interpolation = Interpolation.BILINEAR)Semantic-segmentation preset — image + mask share geometry.
Pipeline: SmallestMaxSize(resize_size) → CenterCrop(crop_size)
→ Normalize applied to the image only. Mask travels through
the geometric stages with nearest-neighbour interpolation (label
preservation guaranteed by every
lucid.utils.transforms._base.GeometricTransform's
_apply_mask hook) and is not normalised.
Parameters
crop_sizeintSquare crop fed to the model.
resize_sizeint= 520Shorter-side length before cropping; canonical for FCN /
DeepLab style recipes.
meantuple of float= NonePer-channel normalization stats; default ImageNet.
stdtuple of float= NonePer-channel normalization stats; default ImageNet.
Image resize interpolation. Masks always use nearest.