tensorflow::ops::Selu

#include <nn_ops.h>

Computes scaled exponential linear: scale * alpha * (exp(features) - 1)

Summary

if < 0, scale * features otherwise.

To be used together with `initializer = tf.variance_scaling_initializer(factor=1.0, mode='FAN_IN'). For correct dropout, usetf.contrib.nn.alpha_dropout`.

See Self-Normalizing Neural Networks

Args:

• scope: A Scope object

Returns:

• Output: The activations tensor.

Constructors and Destructors
Selu(const ::tensorflow::Scope & scope, ::tensorflow::Input features)

Public attributes
activations	::tensorflow::Output
operation	Operation

Public functions
node() const	::tensorflow::Node *
operator::tensorflow::Input() const
operator::tensorflow::Output() const

Public attributes

activations

::tensorflow::Output activations

operation

Operation operation

Public functions

Selu

 Selu(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input features
)

node

::tensorflow::Node * node() const 

operator::tensorflow::Input

 operator::tensorflow::Input() const 

operator::tensorflow::Output

 operator::tensorflow::Output() const