multiplier

class deepinv.physics.functional.multiplier(x: Tensor, mult: Tensor)[source]

Bases:

Implements diagonal matrices or multipliers \(x\) and mult. The adjoint of this operation is deepinv.physics.functional.multiplier_adjoint()

Parameters:
  • x (torch.Tensor) – Image of size (B, C, …).

  • filter (torch.Tensor) – Filter of size (b, c, …) where b can be either 1 or B and c can be either 1 or C.

If b = 1 or c = 1, then this function supports broadcasting as the same as numpy.

:return torch.Tensor : the output of the multiplier, same shape as \(x\)