tensorflow constant

首先我们载入tensorflow模块，如果需要，可以查看一下当前tf的版本
import tensorflow as tf
print(tf.__version__)
tensorflow是一种图计算框架，所有的计算操作被声明为图（graph）中的节点（Node）
即使只是声明一个变量或者常量，也并不执行实际的操作，而是向图中增加节点


a = tf.constant(5)
b = tf.constant(7)
print(a)
print(a)

c = tf.add(a, b)
print(c)

d = a + b
e = a*b
print(d)
print(e)

sess = tf.Session()
a,b,c,d,e = sess.run([a,b,c,d,e])
print("a=",a," b=",b," c=",c," d=",d," e=",e)

mat_a = tf.constant([[1,1,1],[3,3,3]])
mat_b = tf.constant([[2,2,2],[5,5,5]],name='mat_b')

mul_a_b = mat_a * mat_b
tf_mul_a_b = tf.multiply(mat_a, mat_b)
tf_matmul_a_b = tf.matmul(mat_a, tf.transpose(mat_b),name='matmul_with_name')

sess2 = tf.Session()
mul_a_b,tf_mul_a_b,tf_matmul_a_b = sess2.run([mul_a_b,tf_mul_a_b,tf_matmul_a_b])

print(" mul_a_b=",mul_a_b)
print(" tf_mul_a_b=",tf_mul_a_b)
print(" tf_matmul_a_b=",tf_matmul_a_b)

graph是一张有向无环图，在tensorflow中，通常用protobuf进行持久化
this_graph = tf.get_default_graph()
this_graph_def = this_graph.as_graph_def()
print(this_graph_def)