sigpy.convolve_filter_adjoint

sigpy.convolve_filter_adjoint(output, data, filt_shape, mode='full', strides=None, multi_channel=False)[source]

Adjoint convolution operation with respect to filter.

Note that the cuDNN version only supports inputs with D=1, 2 or 3.

Parameters:
  • output (array) – output array of shape: \([..., p_1, ..., p_D]\) if multi_channel is False, \([..., c_o, p_1, ..., p_D]\) otherwise.
  • data (array) – data array of shape: \([..., m_1, ..., m_D]\) if multi_channel is False, \([..., c_i, m_1, ..., m_D]\) otherwise.
  • mode (str) – {‘full’, ‘valid’}.
  • strides (None or tuple of ints) – convolution strides of length D.
  • multi_channel (bool) – specify if input/output has multiple channels.
Returns:

filter array of shape:

\([n_1, ..., n_D]\) if multi_channel is False \([c_o, c_i, n_1, ..., n_D]\) otherwise.

Return type:

array