tf.ones_like()函数用法详解（附代码理解）

tf.ones_like 函数
ones_like(
    tensor,
    dtype=None,
    name=None,
    optimize=True
)

函数目的是创建一个和输入参数（tensor）维度一样，元素都为1的张量。

• tensor:输入参数
• dtype:返回的 Tensor 类型.必须是：float32,float64,int8,int16,int32,int64,uint8,complex64,complex128或bool.
• name：操作的名称(可选).
• optimize：如果为 true,则尝试静态确定 “张量” 的形状并将其编码为常量.

import tensorflow as tf
sess=tf.InteractiveSession( )

a = tf.constant([1,2,3,4,5,6])
b = tf.constant([1,2,3,4,5,6], shape=[2, 3])
c=tf.constant([1,2,3,4,5,6], shape=[2, 2, 3])

d=tf.ones_like(a)
e=tf.ones_like(b)
f=tf.ones_like(c)

print(sess.run(a))
print(sess.run(tf.shape(a)),"\n")

print(sess.run(b))
print(sess.run(tf.shape(b)),"\n")

print(sess.run(c))
print(sess.run(tf.shape(c)),"\n")

print(sess.run(d))
print(sess.run(tf.shape(d)),"\n")

print(sess.run(e))
print(sess.run(tf.shape(e)),"\n")

print(sess.run(f))
print(sess.run(tf.shape(f)),"\n")



输出结果：
[1 2 3 4 5 6]
[6] 

[[1 2 3]
 [4 5 6]]
[2 3] 

[[[1 2 3]
  [4 5 6]]

 [[6 6 6]
  [6 6 6]]]
[2 2 3] 

[1 1 1 1 1 1]
[6] 

[[1 1 1]
 [1 1 1]]
[2 3] 

[[[1 1 1]
  [1 1 1]]

 [[1 1 1]
  [1 1 1]]]
[2 2 3]