mindspore.ops.mish

mindspore.ops.mish(x)[source]

Computes MISH(A Self Regularized Non-Monotonic Neural Activation Function) of input tensors element-wise.

The function is shown as follows:

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

See more details in A Self Regularized Non-Monotonic Neural Activation Function.

Parameters: x (Tensor) – Tensor of shape \((N, *)\), where \(*\) means, any number of additional dimensions, with float16 or float32 data type.
Returns: Tensor, with the same type and shape as the x.

Supported Platforms:: Ascend GPU CPU

Raises: TypeError – If dtype of x is neither float16 nor float32.

Examples

>>> input_x = Tensor(np.array([[-1.0, 4.0, -8.0], [2.0, -5.0, 9.0]]), mindspore.float32)
>>> output = ops.mish(input_x)
>>> print(output)
[[-3.0340147e-01  3.9974129e+00 -2.68311895e-03]
 [ 1.9439590e+00  -3.3576239e-02 8.99999990e+00]]