LeakyReLU

class paddle.nn. LeakyReLU ( negative_slope=0.01, name=None ) [source]

Leaky ReLU Activation.

\[\begin{split}LeakyReLU(x)= \\left\\{ \\begin{aligned} &x, & & if \\ x >= 0 \\\\ &negative\_slope * x, & & otherwise \\\\ \\end{aligned} \\right. \\\\\end{split}\]
Parameters

  • negative_slope (float, optional) – Slope of the activation function at \(x < 0\) . Default is 0.01.

  • 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
import numpy as np

m = paddle.nn.LeakyReLU()
x = paddle.to_tensor(np.array([-2, 0, 1], 'float32'))
out = m(x)  # [-0.02, 0., 1.]
forward ( x )

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