nn_prelu: PReLU module

Description Usage Arguments Details Shape Attributes Note Examples

Description

Applies the element-wise function:

\mbox{PReLU}(x) = \max(0,x) + a * \min(0,x)

or

\mbox{PReLU}(x) = ≤ft\{ \begin{array}{ll} x, & \mbox{ if } x ≥q 0 \\ ax, & \mbox{ otherwise } \end{array} \right.

Usage

1
nn_prelu(num_parameters = 1, init = 0.25)

Arguments

num_parameters

(int): number of a to learn. Although it takes an int as input, there is only two values are legitimate: 1, or the number of channels at input. Default: 1

init

(float): the initial value of a. Default: 0.25

Details

Here a is a learnable parameter. When called without arguments, nn.prelu() uses a single parameter a across all input channels. If called with nn_prelu(nChannels), a separate a is used for each input channel.

Shape

Attributes

Note

weight decay should not be used when learning a for good performance.

Channel dim is the 2nd dim of input. When input has dims < 2, then there is no channel dim and the number of channels = 1.

Examples

1
2
3
4
5
6
if (torch_is_installed()) {
m <- nn_prelu()
input <- torch_randn(2)
output <- m(input)

}

torch documentation built on Oct. 7, 2021, 9:22 a.m.