Tensorflow学习：Variable变量

本文注意：
1. 变量设置千万一定要初始化，代码r0.12推荐 init = tf.global_variables_initializer()
2. 赋值函数assign()和add()函数类似，直到session的run()之后才会执行操作。与之类似的，一般我们会将神经网络模型中的参数表示为一系列的变量，在模型的训练过程中对变量进行更新操作。

# -*- coding: utf-8 -*-
"""
Created on Wed May  3 10:41:08 2017
E-mail：Eric2014_Lv@sjtu.edu.cn
@author: DidiLv
"""

import tensorflow as tf

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

one = tf.constant(1)

new_value = tf.add(state, one)

update = tf.assign(state, new_value)

init = tf.global_variables_initializer()  # very important

with tf.Session() as sess:
    sess.run(init)
    for _ in range(10):
        print(sess.run(state))
        sess.run(update)