tensorflow::ops::Relu

#include <nn_ops.h>

Вычисляет выпрямленную линейную функцию: max(features, 0).

Краткое описание

См.: https://en.wikipedia.org/wiki/Rectifier_(neural_networks) Пример использования: tf.nn.relu([-2., 0., -0., 3.]).numpy() array([ 0., 0., -0., 3.], dtype=float32)

Аргументы:

Возвращает:

Конструкторы и деструкторы
`Relu(const ::tensorflow::Scope & scope, ::tensorflow::Input features)`

Общедоступные атрибуты
`activations`	`::tensorflow::Output`
`operation`	`Operation`

Общедоступные функции
`node() const`	`::tensorflow::Node *`
`operator::tensorflow::Input() const`
`operator::tensorflow::Output() const`

::tensorflow::Output activations

Operation operation

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

::tensorflow::Node * node() const

operator::tensorflow::Input() const

operator::tensorflow::Output() const

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.3/api_docs/cc/class/tensorflow/ops/relu