torchcvnn.transforms.RandomPhase

class torchcvnn.transforms.RandomPhase(dtype: str, centering: bool = False)

Randomly phase-shifts complex-valued input data. This transform applies a random phase shift to complex-valued input tensors/arrays by multiplying the input with exp(j*phi), where phi is uniformly distributed in [0, 2π] or [-π, π] if centering is enabled. :param dtype: str

Data type for the output. Must be one of the supported complex dtypes.

Parameters:

centering – bool, optional. If True, centers the random phase distribution around 0 by subtracting π from the generated phases. Default is False.

Returns

torch.Tensor or numpy.ndarray

Phase-shifted complex-valued data with the same shape as input.

Examples

>>> transform = RandomPhase(dtype='complex64')
>>> x = torch.ones(3,3, dtype=torch.complex64)
>>> output = transform(x)  # Applies random phase shifts

Notes

• Input data must be complex-valued

• The output maintains the same shape and complex dtype as input

• Phase shifts are uniformly distributed in:

  • [0, 2π] when centering=False

  • [-π, π] when centering=True

__init__(dtype: str, centering: bool = False) → None

Methods

__init__(dtype[, centering])