spyrit.core.recon.TikhoNet.reconstruct

TikhoNet.reconstruct(y)

Reconstruct an image from measurements.

This method sucessively applies the preprocessing operator prep, the Tikhonov regularization operator tikho, and the denoising operator denoi to the input measurement vectors x.

Important

The measurements passed as input must NOT be preprocessed.

Args:

y: raw measurement vectors. Have shape \((b, c, m)\)

Returns:

torch.tensor: Reconstructed images. Have shape \((b,c,h,w)\) if reshape_output is True in the kwargs dictionary (default) or \((b,c,hw)\) otherwise.

Example:

>>> import spyrit
>>> acqu = spyrit.core.meas.HadamSplit2d(8)
>>> prep = spyrit.core.prep.UnsplitRescale()
>>> sigma = torch.ones(64, 64)
>>> tikho = TikhoNet(acqu, prep, sigma)
>>> x = torch.rand(10, 1, 8, 8)
>>> y = acqu(x)
>>> z = tikho.reconstruct(y)
>>> print(z.shape)
torch.Size([10, 1, 8, 8])