spyrit.core.recon.PseudoInverse

class spyrit.core.recon.PseudoInverse[source]

Bases: Module

Moore-Penrose pseudoinverse.

Considering linear measurements \(y = Hx\), where \(H\) is the measurement matrix and \(x\) is a vectorized image, it estimates \(x\) from \(y\) by computing \(\hat{x} = H^\dagger y\), where \(H\) is the Moore-Penrose pseudo inverse of \(H\).

Example:

>>> H = torch.rand([400,32*32])
>>> Perm = torch.rand([32*32,32*32])
>>> meas_op =  HadamSplit(H, Perm, 32, 32)
>>> y = torch.rand([85,400], dtype=torch.float)
>>> pinv_op = PseudoInverse()
>>> x = pinv_op(y, meas_op)
>>> print(x.shape)
torch.Size([85, 1024])

Methods

forward(x, meas_op, **kwargs)

Computes pseudo-inverse of measurements.