View source on GitHub |
ND fast real Fourier transform.
tf.signal.rfftnd(
input_tensor, fft_length=None, axes=None, norm=None, name=None
)
Computes the n-dimensional real discrete Fourier transform over designated
dimensions of input
. The designated dimensions of input
are assumed to be
the result of RFFTND
. The length of the last axis transformed will be
fft_length[-1]//2+1.
If fft_length[i]
Axes mean the dimensions to perform the transform on. Default is to perform on all axes.
Returns | |
---|---|
A Tensor of type Tcomplex .
|