mindspore.ops.mean

查看源文件
mindspore.ops.mean(x, axis=None, keep_dims=False)[源代码]

计算tensor在指定轴上的均值。

参数:
  • x (Tensor[Number]) - 输入tensor。

  • axis (Union[int, tuple(int), list(int), Tensor]) - 指定计算轴。如果为 None ,计算 input 中的所有元素。默认 None

  • keep_dims (bool) - 输出tensor是否保留维度。默认 False

返回:

Tensor

支持平台:

Ascend GPU CPU

样例:

>>> import mindspore
>>> input = mindspore.tensor([[9, 3, 4, 5],
...                           [5, 2, 7, 4],
...                           [8, 1, 3, 6]])
>>> # case 1: By default, compute the mean of all elements.
>>> mindspore.ops.mean(input)
Tensor(shape=[], dtype=Int64, value= 4)
>>>
>>> # case 2: Compute the mean along axis 1.
>>> mindspore.ops.mean(input, axis=1)
Tensor(shape=[3], dtype=Int64, value= [5, 4, 4])
>>>
>>> # case 3: If keep_dims=True, the output shape will be same of that of the input.
>>> mindspore.ops.mean(input, axis=1, keep_dims=True)
Tensor(shape=[3, 1], dtype=Int64, value=
[[5],
 [4],
 [4]])