deepmr.linops.NUFFTGramOp

deepmr.linops.NUFFTGramOp#

class deepmr.linops.NUFFTGramOp(*args: Any, **kwargs: Any)[source]#

Self-adjoint Non-Uniform Fast Fourier Transform operator.

K-space sampling trajectory are expected to be shaped (ncontrasts, nviews, nsamples, ndims).

Input and output data are expected to be shaped (nslices, nsets, ncoils, ncontrasts, nviews, nsamples), where nsets represents multiple sets of coil sensitivity estimation for soft-SENSE implementations (e.g., ESPIRIT), equal to 1 for conventional SENSE and ncoils represents the number of receiver channels in the coil array.

__init__(coord, shape, basis=None, weight=None, device='cpu', threadsperblock=128, width=6, **kwargs)[source]#

Initiate the linear operator.

Methods

__init__(coord, shape[, basis, weight, ...])

Initiate the linear operator.

forward(x)

Apply Toeplitz convolution (NUFFT.H * NUFFT).

to(*args, **kwargs)

Copy to different devices

Attributes

H

Return adjoint linear operator.