TensorFlow与神经网络_学习记录1（get_variable函数 与 initialize_all_variables函数）

环境 Python_3.5.2 TensorFlow_1.2.1

import tensorflow as tf
g1 = tf.Graph()
with g1.as_default():
    v = tf.get_variable(
        "v", shape=[1], initializer=tf.zeros_initializer
    )

g2 = tf.Graph()
with g2.as_default():
    v = tf.get_variable(
        "v", shape=[1], initializer=tf.ones_initializer
    )

with tf.Session(graph=g1) as sess:
    sess.run(tf.global_variables_initializer())
    with tf.variable_scope("", reuse=True):
        print(sess.run(tf.get_variable("v")))

with tf.Session(graph=g2) as sess:
    sess.run(tf.global_variables_initializer())
    with tf.variable_scope("", reuse=True):
        print(sess.run(tf.get_variable("v")))

函数差异：

1. tf.get_variable:
   旧：tf.get_variable(“varName”, initializer=tf.zeros_initializer(shape=[1]))
   新：tf.get_variable(“varName”, shape=[1]， initializer=tf.zeros_initializer)

2. tf.initialize_all_variables().run()
   旧：tf.initialize_all_variables().run()
   新：sess.run(tf.global_variables_initializer())