torchcell.transforms.regression_to_classification.LabelNormalizationTransform

class LabelNormalizationTransform(dataset: Neo4jCellDataset, label_configs: dict[str, dict[str, Any]], eps: float = 1e-08)[source]

Bases: BaseTransform

Transform for normalizing labels with different strategies.

normalize(values: Tensor, label: str) → Tensor[source]: Normalize values based on specified strategy.

denormalize(values: Tensor, label: str) → Tensor[source]: Denormalize values based on specified strategy.

forward(data: HeteroData) → HeteroData[source]: Transform the data by normalizing specified labels.

inverse(data: HeteroData) → HeteroData[source]: Inverse transform to recover original scale.