megengine.functional.var¶
- var(inp, axis=None, keepdims=False)[源代码]¶
Calculates the variance of tensor elements over a given axis (or axes).
- 参数
inp (
Tensor
) – input tensor. Should have a numeric data type.axis (
Union
[int
,Sequence
[int
],None
]) – axis or axes along which variances must be computed. By default, the variance must be computed over the entire tensor. If a sequence of integers, variances must be computed over multiple axes.keepdims (
bool
) – ifTrue
, the reduced axes (dimensions) must be included in the result as singleton dimensions, and, accordingly, the result must be compatible with the input tensor (see 广播机制与规则). Otherwise, ifFalse
, the reduced axes (dimensions) must not be included in the result.
- 返回类型
- 返回
if the variance was computed over the entire tensor, a zero-dimensional tensor containing the variance; otherwise, a non-zero-dimensional tensor containing the variances. The returned tensor must have a data type determined by 类型提升规则.
注解
The variance is the average of the squared deviations from the mean, i.e.,
var = mean(x)
, wherex = abs(a - a.mean())**2
.实际案例
>>> x = Tensor([[1, 2], [3, 4]]) >>> F.var(x) Tensor(1.25, device=xpux:0)
>>> x = Tensor([[14, 8, 11, 10], [7, 9, 10, 11], [10, 15, 5, 10]]) >>> F.var(x) Tensor(6.8333335, device=xpux:0)