mindspore.ops.erf

mindspore.ops.erf(input)

逐元素计算输入tensor的高斯误差。

$$\text{erf}(x)=\frac{2}{\sqrt{\pi }}\underset{0}{\overset{x}{\int }}{e}^{-t^2}dt$$

参数：

• input (Tensor) - 输入tensor。

返回：

Tensor

支持平台：

Ascend GPU CPU

样例：

>>> import mindspore
>>> # The dtype of output is float32 when dtype of input is int64.
>>> input = mindspore.tensor([-1, 0, 1, 2, 3], mindspore.int64)
>>> mindspore.ops.erf(input)
Tensor(shape=[5], dtype=Float32, value= [-8.42700793e-01,  0.00000000e+00,  8.42700793e-01,  9.95322265e-01,  9.99977910e-01])
>>>
>>> # Otherwise output has the same dtype as the input.
>>> input = mindspore.tensor([-1, 0, 1, 2, 3], mindspore.float64)
>>> mindspore.ops.erf(input)
Tensor(shape=[5], dtype=Float64, value= [-8.42700793e-01,  0.00000000e+00,  8.42700793e-01,  9.95322265e-01,  9.99977910e-01])