erf

paddle. erf ( x: Tensor, name: str | None = None, *, out: Tensor | None = None ) → Tensor [source]

The error function.

For more details, see Error function.

\[out = \frac{2}{\sqrt{\pi}} \int_{0}^{x}e^{- \eta^{2}}d\eta\]

Parameters

• x (Tensor) – The input tensor, it’s data type should be float32, float64, uint8, int8, int16, int32, int64. Alias: input.

• name (str|None, optional) – Name for the operation (optional, default is None). For more information, please refer to api_guide_Name.

Keyword Arguments

out (Tensor, optional) – The output tensor that has the computed result.

Returns

float32 or float64 (integer types are autocasted into float32), shape: same as input.

Return type

Tensor. The output of Erf, dtype

Examples

>>> import paddle

>>> x = paddle.to_tensor([-0.4, -0.2, 0.1, 0.3])
>>> out = paddle.erf(x)
>>> print(out)
Tensor(shape=[4], dtype=float32, place=Place(cpu), stop_gradient=True,
[-0.42839241, -0.22270259,  0.11246292,  0.32862678])