mindspore.mint.nn.functional.elu

mindspore.mint.nn.functional.elu(input, alpha=1.0)[source]

Exponential Linear Unit activation function.

Applies the exponential linear unit function element-wise. The activation function is defined as:

\[\begin{split}\text{ELU}(x)= \left\{ \begin{array}{align} \alpha(e^{x} - 1) & \text{if } x \le 0\\ x & \text{if } x \gt 0\\ \end{array}\right.\end{split}\]

Where \(x\) is the element of input Tensor input, \(\alpha\) is param alpha, it determines the smoothness of ELU.

ELU function graph:

Parameters

input (Tensor) – The input of ELU is a Tensor of any dimension.
alpha (float, optional) – The alpha value of ELU, the data type is float. Default: 1.0 .

Returns

Tensor, has the same shape and data type as input.

Raises

TypeError – If alpha is not a float.

Supported Platforms:: Ascend

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, mint
>>> x = Tensor(np.array([[-1.0, 4.0, -8.0], [2.0, -5.0, 9.0]]), mindspore.float32)
>>> output = mint.nn.functional.elu(x)
>>> print(output)
[[-0.63212055  4.         -0.99966455]
 [ 2.         -0.99326205  9.        ]]