PReLU¶

class paddle.nn. PReLU ( num_parameters=1, init=0.25, weight_attr=None, data_format='NCHW', name=None ) [source]

PReLU Activation. The calculation formula is follows:

If approximate calculation is used:

\[PReLU(x) = max(0, x) + weight * min(0, x)\]

x is input Tensor.

Parameters

num_parameters (int, optional) – Number of weight to learn. The supported values are: 1 - a single parameter alpha is used for all input channels; Number of channels - a separate alpha is used for each input channel. Default is 1.
init (float, optional) – Init value of learnable weight. Default is 0.25.
weight_attr (ParamAttr, optional) – The parameter attribute for the learnable weight. Default is None. For more information, please refer to ParamAttr.
name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.
data_format (str, optional) – Data format that specifies the layout of input. It may be “NC”, “NCL”, “NCHW”, “NCDHW”, “NLC”, “NHWC” or “NDHWC”. Default: “NCHW”.

Shape:

input: Tensor with any shape. Default dtype is float32.
output: Tensor with the same shape as input.

Examples

           >>> import paddle

>>> data = paddle.to_tensor([[[[-2.0,  3.0, -4.0,  5.0],
...                            [ 3.0, -4.0,  5.0, -6.0],
...                            [-7.0, -8.0,  8.0,  9.0]],
...                           [[ 1.0, -2.0, -3.0,  4.0],
...                            [-5.0,  6.0,  7.0, -8.0],
...                            [ 6.0,  7.0,  8.0,  9.0]]]])
...
>>> m = paddle.nn.PReLU(1, 0.25)
>>> out = m(data)
>>> print(out)
Tensor(shape=[1, 2, 3, 4], dtype=float32, place=Place(cpu), stop_gradient=False,
[[[[-0.50000000,  3.        , -1.        ,  5.        ],
   [ 3.        , -1.        ,  5.        , -1.50000000],
   [-1.75000000, -2.        ,  8.        ,  9.        ]],
  [[ 1.        , -0.50000000, -0.75000000,  4.        ],
   [-1.25000000,  6.        ,  7.        , -2.        ],
   [ 6.        ,  7.        ,  8.        ,  9.        ]]]])

          

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.

PReLU¶

forward¶

extra_repr¶