使用混合精度amp训练 报错 xf = torch.fft.rfft(x, dim=1) RuntimeError: cuFFT only supports dimensions whose sizes are powers of two when computing in half precision, but got a signal size of[192] #761
Description
xf = torch.fft.rfft(x, dim=1)
RuntimeError: cuFFT only supports dimensions whose sizes are powers of two when computing in half precision, but got a signal size of[192]