TensorFlow入门基础知识（五）tf.add_n()的用法

tensorflow api中描述如下

A Tensor. Has the same type as inputs.

tf.add_n(inputs, name=None)

Add all input tensors element wise.

Args:

inputs: A list of at least 1 Tensor objects of the same type in: float32, float64, int64, int32, uint8, int16, int8, complex64, qint8, quint8, qint32. Must all be the same size and shape.

name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as inputs.

添加所有张量元素

自己实验：

import tensorflow as tf;  
import numpy as np;  
input1 = tf.constant([1.0, 2.0, 3.0])  
input2 = tf.Variable(tf.random_uniform([3]))  
output = tf.add_n([input1, input2])  
init_op = tf.global_variables_initializer() 
with tf.Session() as sess:  
  sess.run(init_op)
  print(sess.run(input1))
  print(sess.run(input2))
  print(sess.run(output))

结果：

[1. 2. 3.]
[0.6231705  0.50447917 0.28593874]
[1.6231705 2.5044792 3.2859387]