Rate this Page

Function torch::fft::ihfftn#

Function Documentation#

inline Tensor torch::fft::ihfftn(const Tensor &self, at::OptionalIntArrayRef s = std::nullopt, IntArrayRef dim = {-2, -1}, std::optional<std::string_view> norm = std::nullopt)#

Computes the N-dimensional IFFT of a real input signal.

The output is a onesided representation of the Hermitian symmetric time domain signal. See https://pytorch.org/docs/main/fft.html#torch.fft.ihfftn.

Example:

auto T = torch::randn({128, 128}, torch::kDouble);
auto t = torch::fft::hfft2(T);
assert(t.is_complex() && t.size(1) == 65);