conv_filter_transpose2d_fft#
- deepinv.physics.functional.conv_filter_transpose2d_fft(x, y, filter_size, real_fft=True, padding='circular', correlation=False)[source]#
Apply the adjoint of 2D convolution with respect to its filter using FFTs.
This function gives the same result as
deepinv.physics.functional.conv_filter_transpose2d(). It is generally faster for large filter supports, while the non-fft version is faster for small filters.- Parameters:
x (torch.Tensor) – Input tensor of shape
(B, C, H, W).y (torch.Tensor) – Adjoint input. Its spatial shape must match the output of
deepinv.physics.functional.conv2d()applied tox.real_fft (bool) – Use real FFTs for real-valued inputs.
padding (str) – One of
"valid","circular","replicate","reflect","constant"or"zeros".correlation (bool) – If
True, return the filter adjoint of cross-correlation rather than convolution.
- Returns:
Per-channel filter adjoint of shape
(B, C, H_f, W_f).- Return type: