`numpy.fft:irfft2`

Signature

   def     irfft2 (    a    ,    s    =  None   ,    axes    =  (-2, -1)   ,    norm    =  None   ,    out    =  None     )

Computes the inverse of rfft2.

a : array_like: The input array
s : sequence of ints, optional: Shape of the real output to the inverse FFT.
versionchanged 2.0
If it is -1, the whole input is used (no padding/trimming).
deprecated 2.0
If s is not None, axes must not be None either.
deprecated 2.0
s must contain only int s, not None values. None values currently mean that the default value for n is used in the corresponding 1-D transform, but this behaviour is deprecated.
axes : sequence of ints, optional: The axes over which to compute the inverse fft. Default: (-2, -1), the last two axes.
deprecated 2.0
If s is specified, the corresponding axes to be transformed must not be None.
norm : {"backward", "ortho", "forward"}, optional: Normalization mode (see numpy.fft). Default is "backward". Indicates which direction of the forward/backward pair of transforms is scaled and with what normalization factor.
versionadded 1.20.0
The "backward", "forward" values were added.
out : ndarray, optional: If provided, the result will be placed in this array. It should be of the appropriate shape and dtype for the last transformation.
versionadded 2.0.0

This is really irfftn with different defaults. For more details see irfftn.

import numpy as np
a = np.mgrid[:5, :5][0]
A = np.fft.rfft2(a)
np.fft.irfft2(A, s=a.shape)