torch.var

torch.var(input, dim, unbiased, keepdim=False, *, out=None) → Tensor

If unbiased is True, Bessel’s correction will be used. Otherwise, the sample variance is calculated, without any correction.

Parameters:

• input (Tensor) – the input tensor.
• dim (int or tuple of ints, optional) – the dimension or dimensions to reduce. If None, all dimensions are reduced.

Keyword Arguments:

• unbiased (bool) – whether to use Bessel’s correction ( $\delta N = 1$).
• keepdim (bool) – whether the output tensor has dim retained or not.
• out (Tensor, optional) – the output tensor.

torch.var(input, unbiased) → Tensor

Calculates the variance of all elements in the input tensor.

If unbiased is True, Bessel’s correction will be used. Otherwise, the sample deviation is calculated, without any correction.

Parameters:

• input (Tensor) – the input tensor.
• unbiased (bool) – whether to use Bessel’s correction ( $\delta N = 1$).

Example:

>>> a = torch.tensor([[-0.8166, -1.3802, -0.3560]])
>>> torch.var(a, unbiased=False)
tensor(0.1754)