ToComplex

class deepinv.datasets.utils.ToComplex(*args, **kwargs)

Bases: Module

Torchvision-style transform to add empty imaginary dimension to image.

Expects tensor of shape (…, H, W) and returns tensor of shape (…, 2, H, W).

forward(x)

Convert real image to complex image.

Parameters:

x (torch.Tensor) – image tensor of shape (…, H, W)