torch.view_as_complex

torch.view_as_complex(input) → Tensor

Returns a view of input as a complex tensor. For an input complex tensor of size $m1, m2, \dots, mi, 2$, this function returns a new complex tensor of size $m1, m2, \dots, mi$ where the last dimension of the input tensor is expected to represent the real and imaginary components of complex numbers.

Warning

view_as_complex() is only supported for tensors with torch.dtype torch.float64 and torch.float32. The input is expected to have the last dimension of size 2. In addition, the tensor must have a stride of 1 for its last dimension. The strides of all other dimensions must be even numbers.

Parameters:

input (Tensor) – the input tensor.

Example:

>>> x=torch.randn(4, 2)
>>> x
tensor([[ 1.6116, -0.5772],
        [-1.4606, -0.9120],
        [ 0.0786, -1.7497],
        [-0.6561, -1.6623]])
>>> torch.view_as_complex(x)
tensor([(1.6116-0.5772j), (-1.4606-0.9120j), (0.0786-1.7497j), (-0.6561-1.6623j)])