tf.Variable()函数的使用

tf.Variable(initializer,name),参数initializer是初始化参数，name是可自定义的变量名称，用法如下：

import tensorflow as tf
v1=tf.Variable(tf.random_normal(shape=[4,3],mean=0,stddev=1),name='v1')
v2=tf.Variable(tf.constant(2),name='v2')
v3=tf.Variable(tf.ones([4,3]),name='v3')
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print(sess.run(v1))
    print(sess.run(v2))
    print(sess.run(v3))

结果如下：

[[-1.2115501   1.0484737   0.55210656]
 [-1.5301195   0.9060654  -2.6766613 ]
 [ 0.27101386 -0.32336152  0.44544214]
 [-0.0120788  -0.3409422  -0.48505628]]
2
[[1. 1. 1.]
 [1. 1. 1.]
 [1. 1. 1.]
 [1. 1. 1.]]