torch_geometric.transforms.Cartesian

class Cartesian(norm: bool = True, max_value: Optional[float] = None, cat: bool = True, interval: Tuple[float, float] = (0.0, 1.0))[source]

Bases: BaseTransform

Saves the relative Cartesian coordinates of linked nodes in its edge attributes (functional name: cartesian). Each coordinate gets globally normalized to a specified interval (\([0, 1]\) by default).

Parameters:

  • norm (bool, optional) – If set to False, the output will not be normalized. (default: True)

  • max_value (float, optional) – If set and norm=True, normalization will be performed based on this value instead of the maximum value found in the data. (default: None)

  • cat (bool, optional) – If set to False, all existing edge attributes will be replaced. (default: True)

  • interval ((float, float), optional) – A tuple specifying the lower and upper bound for normalization. (default: (0.0, 1.0))