tensorflow中Variable和Placeholder的学习

今天根据莫烦python学习了tensorflow中的变量对象Varible

通过下列代码来具体讨论

import tensorflow as tf

创建一个Variable对象

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

one = tf.constant(1)
new_value = tf.add(state,one)
update = tf.assign(state,new_value)

以上是Varible的修改

接下来我将要对Variable进行初始化

init = tf.global_variables_initializer()

最后用Session对象执行输出，不同的Session会各自独立的维护Vairiable

with tf.Session() as sess:
    sess.run(init)
    for _ in range(3):
        sess.run(update)
        sess.run(state.assign_add(4))
        print(sess.run(state))#输出为5 10 15
with tf.Session() as sess2:
    sess2.run(init)
    sess2.run(state.assign_add(6))
    print(sess2.run(state))#输出为6

Placeholder

input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
output= tf.multiply(input1,input2)
with tf.Session() as sess:
    print(sess.run(output,feed_dict={input1:[2,4],input2:[1,2]}))#输出结果为[2.8.]，可见是分别相乘的