Function torch::fft::irfft

• Defined in File fft.h

Function Documentation

inline Tensor torch::fft::irfft(const Tensor &self, c10::optional<SymInt> n = c10::nullopt, int64_t dim = -1, c10::optional<c10::string_view> norm = c10::nullopt)

Computes the inverse of torch.fft.rfft.

The input is a onesided Hermitian Fourier domain signal, with real-valued output. See https://pytorch.org/docs/main/fft.html#torch.fft.irfft

Example:

auto T = torch::randn(128 / 2 + 1, torch::kComplexDouble);
auto t = torch::fft::irfft(t, /*n=*‍/128);
assert(t.is_floating_point() && T.numel() == 128);