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

Methods

from_config

View source

@classmethod
from_config(
    config
)

Creates an operation from its config.

This method is the reverse of get_config, capable of instantiating the same operation from the config dictionary.

Note: If you override this method, you might receive a serialized dtype config, which is a dict. You can deserialize it as follows:

if "dtype" in config and isinstance(config["dtype"], dict):
    policy = dtype_policies.deserialize(config["dtype"])

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

Returns
An operation instance.