spyrit.core.recon.UPGD.reconstruct_pinv

UPGD.reconstruct_pinv(x)

Preprocesses and reconstructs raw measurement vectors.

Args:

x: raw measurement vectors

Shape:

x: \((BC,2M)\)

output: \((BC,1,H,W)\)

Example:

>>> B, C, H, M = 10, 1, 64, 64**2
>>> Ord = torch.ones((H,H))
>>> meas = HadamSplit(M, H, Ord)
>>> noise = NoNoise(meas)
>>> prep = SplitPoisson(1.0, M, H**2)
>>> recnet = PinvNet(noise, prep)
>>> x = torch.rand((B*C,2*M), dtype=torch.float)
>>> z = recnet.reconstruct_pinv(x)
>>> print(z.shape)
torch.Size([10, 1, 64, 64])