deepmr.fft.apply_sparse_fft_selfadj

deepmr.fft.apply_sparse_fft_selfadj(image, toeplitz_kern, device=None, threadsperblock=128)

Apply self-adjoint Fast Fourier Transform via Toeplitz convolution.

Parameters:

• image (torch.Tensor) – Input image of shape (..., ncontrasts, ny, nx) (2D) or (..., ncontrasts, nz, ny, nx) (3D).

• toeplitz_kern (GramMatrix) – Pre-calculated Toeplitz kernel.

• device (str, optional) – Computational device (cpu or cuda:n, with n=0, 1,...nGPUs). The default is ``None ``(same as interpolator).

• threadsperblock (int) – CUDA blocks size (for GPU only). The default is 128.

Returns:

image – Output image of shape (..., ncontrasts, ny, nx) (2D) or (..., ncontrasts, nz, ny, nx) (3D).

Return type:

torch.Tensor