mindspore.ops.Softplus

class mindspore.ops.Softplus[source]

Softplus activation function.

Softplus is a smooth approximation to the ReLU function. It can be used to constrain the output of a machine to always be positive. The function is shown as follows:

\[\text{output} = \log(1 + \exp(\text{x}))\]

Inputs:

input_x (Tensor) - Tensor of any dimension. Supported dtypes:
- GPU/CPU: float16, float32, float64.
- Ascend: float16, float32.

Outputs:

Tensor, with the same type and shape as the input_x.

Raises

TypeError – If input_x is not a Tensor.
TypeError – If the dtype of input_x is not float16, float32 or float64.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> input_x = Tensor(np.array([1, 2, 3, 4, 5]), mindspore.float32)
>>> softplus = ops.Softplus()
>>> output = softplus(input_x)
>>> print(output)
[1.3132615 2.126928  3.0485873 4.01815   5.0067153]