mindspore.mint.nn.LogSigmoid

View Source On Gitee
class mindspore.mint.nn.LogSigmoid[source]

Applies logsigmoid activation element-wise. The input is a Tensor with any valid shape.

Logsigmoid is defined as:

\[\text{logsigmoid}(x_{i}) = \log(\frac{1}{1 + \exp(-x_i)}),\]

where \(x_{i}\) is the element of the input.

LogSigmoid Activation Function Graph:

../../_images/LogSigmoid.png

Warning

This is an experimental API that is subject to change or deletion.

Inputs:

  • input (Tensor) - The input of LogSigmoid with data type of bfloat16, float16 or float32. The shape is \((*)\) where \(*\) means, any number of additional dimensions.

Outputs:

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

Raises

  • TypeError – If dtype of input is not bfloat16, float16 and float32.

  • TypeError – If input is not a Tensor.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> from mindspore import Tensor
>>> net = mint.nn.LogSigmoid()
>>> input = Tensor([1.0, 2.0, 3.0], mindspore.float32)
>>> output = net(input)
>>> print(output)
[-0.31326166 -0.12692806 -0.04858734]