tf.keras.layers.Activation

TensorFlow 1 version View source on GitHub

Applies an activation function to an output.

Inherits From: Layer

tf.keras.layers.Activation(
    activation, **kwargs
)

Used in the notebooks

Used in the guide

Arguments:

  • activation: Activation function, such as tf.nn.relu, or string name of built-in activation function, such as "relu".

Usage:

layer = tf.keras.layers.Activation('relu') 
output = layer([-3.0, -1.0, 0.0, 2.0]) 
list(output.numpy()) 
[0.0, 0.0, 0.0, 2.0] 
layer = tf.keras.layers.Activation(tf.nn.relu) 
output = layer([-3.0, -1.0, 0.0, 2.0]) 
list(output.numpy()) 
[0.0, 0.0, 0.0, 2.0] 

Input shape:

Arbitrary. Use the keyword argument input_shape (tuple of integers, does not include the batch axis) when using this layer as the first layer in a model.

Output shape:

Same shape as input.