bartorch.tools.nlinv

Contents

bartorch.tools.nlinv#

bartorch.tools.nlinv(kspace, *, maxiter=None, maps=None, traj=None, pattern=None, basis=None, initial=None, alpha=None, real=False, normalize=True, return_sensitivities=False, **extra)#

Nonlinear inversion: the image and the sensitivities together.

Parameters:

  • kspace (torch.Tensor) – Under-sampled k-space, C order.

  • maxiter (int, optional) – Gauss-Newton steps (-i).

  • maps (int, optional) – How many sets of sensitivities to estimate (-m).

  • traj (tensor, optional) – Non-Cartesian trajectory (-t).

  • pattern (tensor, optional) – Sampling pattern (-p).

  • basis (tensor, optional) – Subspace basis (-B).

  • initial (tensor, optional) – Warm start (-I).

  • alpha (float, optional) – Initial regularization weight (-a).

  • real (bool) – Constrain the image to be real (-c).

  • normalize (bool) – Divide the image by the root sum of squares of the sensitivities, which is what nlinv does unless told not to. BART spells this the other way round, as -N for “do not normalize”.

  • return_sensitivities (bool) – Also return the sensitivities, which BART writes as a second array.

  • **extra – Further BART nlinv options, by name. s, the axes the sensitivities are constant along, takes axes of kspace.

Returns:

The image, and the sensitivities when asked for.

Return type:

torch.Tensor or tuple of torch.Tensor

Contents