tf.keras.layers.Softmax

Softmax activation layer.

Inherits From: Layer, Operation

tf.keras.layers.Softmax( axis=-1, **kwargs )

Used in the notebooks

Used in the tutorials

Formula:

exp_x = exp(x - max(x)) f(x) = exp_x / sum(exp_x)

Example:

oftmax_layer = keras.layers.activations.Softmax() nput = np.array([1.0, 2.0, 1.0]) esult = softmax_layer(input) [0.21194157, 0.5761169, 0.21194157]

axis Integer, or list of Integers, axis along which the softmax normalization is applied.
**kwargs Base layer keyword arguments, such as name and dtype.

inputs The inputs (logits) to the softmax layer.
mask A boolean mask of the same shape as inputs. The mask specifies 1 to keep and 0 to mask. Defaults to None.

Softmaxed output with the same shape as inputs.

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

View source

symbolic_call( *args, **kwargs )