mindspore.ops.Erfinv

class mindspore.ops.Erfinv[source]

Computes the inverse error function of input. The inverse error function is defined in the range (-1, 1).

The formula is defined as:

\[erfinv(erf(x)) = x\]

Inputs:

input_x (Tensor) - The input tensor to compute to, with data type float32, float16 or float64.

Outputs:

Tensor, has the same shape and dtype as input_x.

Raises: TypeError – If dtype of input_x is not float16, float32 or float64.

Supported Platforms:: Ascend GPU CPU

Examples

>>> x = Tensor(np.array([0, 0.5, -0.9]), mindspore.float32)
>>> erfinv = ops.Erfinv()
>>> output = erfinv(x)
>>> print(output)
[ 0.          0.47695306 -1.1630805 ]