tf.keras.layers.Activation

Applies an activation function to an output.

Inherits From: Layer, Operation

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

Used in the notebooks

Used in the guide	Used in the tutorials
Mixed precision Ragged tensors	Basic text classification Load text Classifying CIFAR-10 with XLA TFF simulations with accelerators Parametrized Quantum Circuits for Reinforcement Learning

Args
`activation`	Activation function. It could be a callable, or the name of an activation from the `keras.activations` namespace.
`**kwargs`	Base layer keyword arguments, such as `name` and `dtype`.

Example:

layer = keras.layers.Activation('relu')
layer([-3.0, -1.0, 0.0, 2.0])
[0.0, 0.0, 0.0, 2.0]
layer = keras.layers.Activation(keras.activations.relu)
layer([-3.0, -1.0, 0.0, 2.0])
[0.0, 0.0, 0.0, 2.0]

Attributes
`input`	Retrieves the input tensor(s) of a symbolic operation. Only returns the tensor(s) corresponding to the first time the operation was called.
`output`	Retrieves the output tensor(s) of a layer. Only returns the tensor(s) corresponding to the first time the operation was called.

Attributes

input

Retrieves the input tensor(s) of a symbolic operation.

Only returns the tensor(s) corresponding to the first time the operation was called.

output

Retrieves the output tensor(s) of a layer.

Only returns the tensor(s) corresponding to the first time the operation was called.

Methods

`from_config`

View source

@classmethod
from_config(
    config
)

Creates a layer from its config.

This method is the reverse of get_config, capable of instantiating the same layer from the config dictionary. It does not handle layer connectivity (handled by Network), nor weights (handled by set_weights).

Args
`config`	A Python dictionary, typically the output of get_config.

Returns
A layer instance.

`symbolic_call`