mindspore.ops.erfinv

View Source On Gitee
mindspore.ops.erfinv(input)[source]

Returns the result of the inverse error function with input. It is defined in the range (-1, 1) as:

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

where \(x\) is the input.

Parameters

input (Tensor) –

The input tensor to compute with. Supported dtypes:

  • Ascend: float16, float32, int8, int16, int32, int64, uint8, bool.

  • GPU/CPU: float16, float32 or float64.

Returns

Tensor. When the input is int8, int16, int32, int64, uint8, bool, the return value type is float32. Otherwise, the return value type is the same as the input type.

Raises

TypeError –

If dtype of input is not as follows

  • Ascend: float16, float32, int8, int16, int32, int64, uint8, bool.

  • GPU/CPU: float16, float32 or float64.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> input = Tensor(np.array([0, 0.5, -0.9]), mindspore.float32)
>>> output = ops.erfinv(input)
>>> print(output)
[ 0.          0.47693613 -1.1630869 ]