tf.constant
tf.constant
tf.constant(
value,
dtype=None,
shape=None,
name='Const',
verify_shape=False
)
Creates a constant tensor.
The resulting tensor is populated with values of type dtype
, as specified by arguments value
and (optionally) shape
(see examples below).
The argument value
can be a constant value, or a list of values of type dtype
. If value
is a list, then the length of the list must be less than or equal to the number of elements implied by the shape
argument (if specified). In the case where the list length is less than the number of elements specified by shape
, the last element in the list will be used to fill the remaining entries.
The argument shape
is optional. If present, it specifies the dimensions of the resulting tensor. If not present, the shape of value
is used.
If the argument dtype
is not specified, then the type is inferred from the type of value
.
Args:
-
value
: A constant value (or list) of output typedtype
. -
dtype
: The type of the elements of the resulting tensor. -
shape
: Optional dimensions of resulting tensor. -
name
: Optional name for the tensor. -
verify_shape
: Boolean that enables verification of a shape of values.
Returns:
A Constant Tensor.
Raises:
TypeError
: if shape is incorrectly specified or unsupported.
1 #!/usr/bin/env python3 2 #-*- coding:utf-8 -*- 3 ############################ 4 #File Name: tensor_constant.py 5 #Author: frank 6 #Mail: frank0903@aliyun.com 7 #Created Time:2018-05-30 23:02:38 8 ############################ 9 import tensorflow as tf 10 11 ct = tf.constant([1.,2.,3]) 12 print(ct) 13 print(ct.shape) 14 print(ct.name) 15 16 ct2 = tf.constant([1,2,3], shape=(2, 3)) 17 print(ct2) 18 19 with tf.Session() as sess: 20 sess.run(ct) 21 print(ct.eval()) 22 print(ct2.eval())
![](https://images2018.cnblogs.com/blog/593387/201805/593387-20180530233136362-508047258.png)
0 表示 节点名
1 表示 一维数组
2 表示 数据类型,同时可以看出是根据数据的值来推断数据类型
3 表示 2行3列的矩阵
6 表示 当元素的个数 少于 shape定义的个数时,由最后一个元素的值初始化其他空位元素