conv_transpose3d_fft

class deepinv.physics.functional.conv_transpose3d_fft(y: Tensor, filter: Tensor, real_fft: bool = True, padding: str = 'valid')[source]

Bases:

A helper function performing the 3d transposed convolution of y and filter using FFT. The adjoint of this operation is deepinv.physics.functional.conv3d_fft().

If b = 1 or c = 1, then this function applies the same filter for each channel. Otherwise, each channel of each image is convolved with the corresponding kernel.

Padding conditions include 'circular' and 'valid'.

Parameters:

  • y (torch.Tensor) – Image of size (B, C, D, H, W).

  • filter (torch.Tensor) – Filter of size (b, c, d, h, w) where b can be either 1 or B and c can be either 1 or C.

  • real_fft (bool) – for real filters and images choose True (default) to accelerate computation

  • padding (str) – can be 'valid' (default) or 'circular'

Returns:

torch.Tensor : the output of the convolution, which has the same shape as \(y\)