Sigmoid

class paddle.nn. Sigmoid ( name: Optional[str] = None ) [source]

this interface is used to construct a callable object of the Sigmoid class. This layer calculate the sigmoid of input x.

\[sigmoid(x) = \frac{1}{1 + e^{-x}}\]

Parameters: name (str|None, optional) – For details, please refer to api_guide_Name. Generally, no setting is required. Default: None.

Shape:: x: N-D tensor, available dtype is float16, float32, float64.

Returns: A callable object of Sigmoid.

Examples

           >>> import paddle

>>> m = paddle.nn.Sigmoid()
>>> x = paddle.to_tensor([1.0, 2.0, 3.0, 4.0])
>>> out = m(x)
>>> print(out)
Tensor(shape=[4], dtype=float32, place=Place(cpu), stop_gradient=True,
[0.73105860, 0.88079703, 0.95257413, 0.98201376])

          

forward ( x: Tensor ) → Tensor 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 ( ) → str extra_repr¶: Extra representation of this layer, you can have custom implementation of your own layer.

Sigmoid

forward¶

extra_repr¶