《深度学习之Tensorflow》学习笔记二

共享变量

import tensorflow as tf

# get_variable和variable的区别
# var1 = tf.Variable(1.,name='firstvar')
# print(var1.name)
#
# var1 = tf.Variable(2.,name='first')
# print(var1.name)
#
# var2 = tf.Variable(3.)
# print(var2.name)
#
# var2 = tf.Variable(4.)
# print(var2.name)
#
# get_var1 = tf.get_variable('firstvar',[1],initializer=tf.constant_initializer(0.3))
# print(get_var1.name)
#
# get_var1 = tf.get_variable('firstvar1',[1],initializer=tf.constant_initializer(0.4))
# print(get_var1.name)

# 在特定作用域下获取变量
# with tf.variable_scope('test1',):
#     var1 = tf.get_variable('firstvar',shape=[2],dtype=tf.float32)
#
#     with tf.variable_scope('test2',):
#         var2 = tf.get_variable('firstvar',shape=[2],dtype=tf.float32)
#

# 共享变量功能的实现
# with tf.variable_scope('test1',reuse=True):
#     var3 = tf.get_variable('firstvar',shape=[2],dtype=tf.float32)
#
#     with tf.variable_scope('test2',):
#         var4 = tf.get_variable('firstvar',shape=[2],dtype=tf.float32)


# print(var1.name)
# print(var2.name)
# print(var3.name)
# print(var4.name)

# with tf.variable_scope('test1',initializer=tf.constant_initializer(0.4)):
#     var1 = tf.get_variable('firstvar',shape=[2],dtype=tf.float32)
#     with tf.variable_scope('test2'):
#         var2 = tf.get_variable('firstvar',shape=[2],dtype=tf.float32)
#         var3 = tf.get_variable('var3',shape=[2],initializer=tf.constant_initializer(0.3))


with tf.variable_scope('scope1') as sp:
    var1 = tf.get_variable('v',[1])

print(sp.name)
print(var1.name)

with tf.variable_scope('scope2'):
    var2 = tf.get_variable('v',[1])

    with tf.variable_scope(sp) as sp1:
        var3 = tf.get_variable('v3',[1])

print(sp1.name)
print(var2.name)
print(var3.name)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    # print(var1.eval())
    # print(var2.eval())
    # print(get_var1.eval())
    # print(var1.eval())
    # print(var2.eval())
    # print(var3.eval())