Rate this Page
★★★★★

LeakyReLU#

classtorch.nn.LeakyReLU(negative_slope=0.01,inplace=False)[source]#

Applies the LeakyReLU function element-wise.

LeakyReLU(x)=max⁡(0,x)+negative_slope∗min⁡(0,x)\text{LeakyReLU}(x) = \max(0, x) + \text{negative\_slope} * \min(0, x)

or

LeakyReLU(x)={x, if x≥0negative_slope×x, otherwise \text{LeakyReLU}(x) =\begin{cases}x, & \text{ if } x \geq 0 \\\text{negative\_slope} \times x, & \text{ otherwise }\end{cases}
Parameters

  • negative_slope (float) – Controls the angle of the negative slope (which is used fornegative input values). Default: 1e-2

  • inplace (bool) – can optionally do the operation in-place. Default:False

Shape:

  • Input:(∗)(*) where* means, any number of additionaldimensions

  • Output:(∗)(*), same shape as the input

../_images/LeakyReLU.png

Examples:

>>>m=nn.LeakyReLU(0.1)>>>input=torch.randn(2)>>>output=m(input)
extra_repr()[source]#

Return the extra representation of the module.

Return type

str

forward(input)[source]#

Run forward pass.

Return type

Tensor