TensorFlow variable用法

TensorFlow中可以使用tf.Variable创建变量

import tensorflow as tf 

state  = tf.Variable(0,name = 'zzh')
print(state.name)

输出为 zzh:0

用一个小例子实现计数功能。

import tensorflow as tf 

state  = tf.Variable(0,name = 'zzh')
print(state.name)
#方法1
#one = tf.Variable(1)
#new_value = tf.add(state,one)
#update = tf.assign(state,new_value)

#方法2
one = tf.constant(1)
update = tf.assign_add(state,one)

init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    for _ in range(4):
        sess.run(update)
        print(sess.run(state))

tf.assign是将new_value赋值给state.

tf.assign_add将tf.add 和tf.assign结合起来。