>>> import tensorflow as tf
>>> node1 = tf.constant(3.0, dtype=tf.float32)
>>> node2 = tf.constant(4.0)
>>> node3=tf.constant(66)
>>> print(node1,node2,node3)
(<tf.Tensor 'Const:0' shape=() dtype=float32>, <tf.Tensor 'Const_1:0' shape=() dtype=float32>, <tf.Tensor 'Const_2:0' shape=() dtype=int32>)
>>> node4=tf.constant(77,dtype=tf.int32)
>>> print(node1,node2,node3,node4)
(<tf.Tensor 'Const:0' shape=() dtype=float32>, <tf.Tensor 'Const_1:0' shape=() dtype=float32>, <tf.Tensor 'Const_2:0' shape=() dtype=int32>, <tf.Tensor 'Const_3:0' shape=() dtype=int32>)
>>> sess = tf.Session()
2017-07-05 22:24:06.991688: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-07-05 22:24:06.991783: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-07-05 22:24:06.991820: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-07-05 22:24:06.991837: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-07-05 22:24:06.991850: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
>>> print(sess.run([node1, node2]))
[3.0, 4.0]

1、使用tf.constant函数，创建常数

可以指定常数类型，也可以隐式指定。

2、下面的语句输出常数对象

print(node1,node2,node3)

3、创建session，并生成计算图，然后，调用run方法

输出node1和node2的计算

print(sess.run([node1, node2]))

print(sess.run([node1, node2]*(node1+node2)))
[ 21. 28.]