spyrit.core.recon.LearnedPGD.reconstruct

LearnedPGD.reconstruct(x)

Reconstruction step of a reconstruction network

Args:

x: raw measurement vectors

Shape:

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

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

Example:

>>> from spyrit.core.meas import HadamSplit2d
>>> from spyrit.core.prep import UnsplitRescale
>>> from spyrit.core.recon import LearnedPGD

>>> import torch
>>> acqu = HadamSplit2d(32, M=400)
>>> prep = UnsplitRescale()
>>> recnet = LearnedPGD(acqu, prep)
>>> y = torch.randn(10, 1, 800)
>>> z = recnet.reconstruct(y)
>>> print(z.shape)
torch.Size([10, 1, 32, 32])