Mish¶

class paddle.nn. Mish ( name=None ) [source]

Mish Activation.

\[ \begin{align}\begin{aligned}\begin{split}softplus(x) = \begin{cases} x, \text{if } x > \text{threshold} \\ \ln(1 + e^{x}), \text{otherwise} \end{cases}\end{split}\\Mish(x) = x * \tanh(softplus(x))\end{aligned}\end{align} \]

Parameters

name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Shape:

• input: Tensor with any shape.

• output: Tensor with the same shape as input.

Examples

>>> import paddle

>>> x = paddle.to_tensor([-5., 0., 5.])
>>> m = paddle.nn.Mish()
>>> out = m(x)
>>> print(out)
Tensor(shape=[3], dtype=float32, place=Place(cpu), stop_gradient=True,
[-0.03357624,  0.        ,  4.99955177])

forward ( x )

forward¶

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

• *inputs (tuple) – unpacked tuple arguments

• **kwargs (dict) – unpacked dict arguments

extra_repr ( )

extra_repr¶

Extra representation of this layer, you can have custom implementation of your own layer.