Main Content

relu

Apply rectified linear unit activation

Description

The rectified linear unit (ReLU) activation operation performs a nonlinear threshold operation, where any input value less than zero is set to zero.

This operation is equivalent to

f(x)={x,x>00,x0.

Note

This function applies the ReLU operation to dlarray data. If you want to apply ReLU activation within a layerGraph object or Layer array, use the following layer:

example

dlY = relu(dlX) computes the ReLU activation of the input dlX by applying a threshold operation. All values in dlX that are less than zero are set to zero.

Examples

collapse all

Use the relu function to set negative values in the input data to zero.

Create the input data as a single observation of random values with a height and width of 12 and 32 channels.

height = 12;
width = 12;
channels = 32;
observations = 1;

X = randn(height,width,channels,observations);
dlX = dlarray(X,'SSCB');

Compute the leaky ReLU activation.

dlY = relu(dlX);

All negative values in dlX are now set to 0.

Input Arguments

collapse all

Input data, specified as a dlarray with or without dimension labels.

Data Types: single | double

Output Arguments

collapse all

ReLU activations, returned as a dlarray. The output dlY has the same underlying data type as the input dlX.

If the input data dlX is a formatted dlarray, dlY has the same dimension labels as dlX. If the input data is not a formatted dlarray, dlY is an unformatted dlarray with the same dimension order as the input data.

Extended Capabilities

Introduced in R2019b