mindspore.mint.nn.Tanh

class mindspore.mint.nn.Tanh

Apply the Tanh function element-wise.

Tanh function is defined as:

\[tanh(x_i) = \frac{\exp(x_i) - \exp(-x_i)}{\exp(x_i) + \exp(-x_i)} = \frac{\exp(2x_i) - 1}{\exp(2x_i) + 1},\]

where \(x_i\) is an element of the input tensor.

Tanh Activation Function Graph:

Inputs:

• input (Tensor) - The input tensor. Data type must be mindspore.float16 or mindspore.float32.

Outputs:

Tensor.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> input = mindspore.tensor([1, 2, 3, 2, 1], mindspore.float16)
>>> tanh = mindspore.mint.nn.Tanh()
>>> output = tanh(input)
>>> print(output)
[0.7617 0.964  0.995  0.964  0.7617]