mirtorch.linear.mri.FFTCn

class mirtorch.linear.mri.FFTCn(size_in: Sequence[int], size_out: Sequence[int], dims: Union[int, Sequence[int]], norm: str = 'ortho')

FFT operators with FFTshift and iFFTshift for multidimensional data. Pytorch provides three modes in FFT: ‘ortho’, ‘forward’, ‘backward’. Each pair of FFT and iFFT with same mode is the inverse, but not necessarily the adjoint to each other.

norm

normalization of the fft (‘ortho’, ‘forward’ or ‘backward’)

dims

the dimensions to apply the fft

__init__(size_in: Sequence[int], size_out: Sequence[int], dims: Union[int, Sequence[int]], norm: str = 'ortho')

Initiate the linear operator.

Methods

__init__(size_in, size_out, dims[, norm])	Initiate the linear operator.
adjoint(x)	Apply the adjoint operator
apply(x)	Apply the forward operator
to(*args, **kwargs)	Copy to different devices

Attributes

H	Apply the (Hermitian) transpose