在tensorflow中提供了tf.get_variable函数来创建或者获取变量。
当tf.get_variable用于创建变量时,则与tf.Variable的功能基本相同。
相同点:通过两函数创建变量的过程基本一样,且tf.variable函数调用时提供的维度(shape)信息以及初始化方法(initializer)的参数和tf.Variable函数调用时提供的初始化过程中的参数基本类似。
不同点:两函数指定变量名称的参数不同,对于tf.Variable函数,变量名称是一个可选的参数,通过name="x1"的形式给出;而tf.get_variable函数,变量名称是一个必填的参数,它会根据变量名称去创建或者获取变量。
x1=tf.Variable(tf.constant(1.0,shape=[1],name="x1"))
x1 = tf.get_variable("x2",shape=[1],initializer=tf.constant_initializer(1.0))
tf.variable_scope不同scope可以让变量有相同的命名,包括tf.get_variable得到的变量,还有tf.Variable的变量;
tf.name_scope不同scope可以让变量有相同的命名,只是限于tf.Variable的变量。
1.tf.variable_scope用法
- import tensorflow as tf;
- import numpy as np;
- import matplotlib.pyplot as plt;
- with tf.variable_scope('V1'):
- a1 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))
- a2 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a2')
- with tf.variable_scope('V2'):
- a3 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))
- a4 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a2')
- with tf.Session() as sess:
- sess.run(tf.initialize_all_variables())
- print a1.name
- print a2.name
- print a3.name
- print a4.name
V1/a1:0
V1/a2:0
V2/a1:0
V2/a2:0
2.tf.name_scope用法
- import tensorflow as tf;
- import numpy as np;
- import matplotlib.pyplot as plt;
- with tf.name_scope('V1'):
- a1 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))
- a2 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a2')
- with tf.name_scope('V2'):
- a3 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))
- a4 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a2')
- with tf.Session() as sess:
- sess.run(tf.initialize_all_variables())
- print a1.name
- print a2.name
- print a3.name
- print a4.name
改正:
- import tensorflow as tf;
- import numpy as np;
- import matplotlib.pyplot as plt;
- with tf.name_scope('V1'):
- # a1 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))
- a2 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a2')
- with tf.name_scope('V2'):
- # a3 = tf.get_variable(name='a1', shape=[1], initializer=tf.constant_initializer(1))
- a4 = tf.Variable(tf.random_normal(shape=[2,3], mean=0, stddev=1), name='a2')
- with tf.Session() as sess:
- sess.run(tf.initialize_all_variables())
- # print a1.name
- print a2.name
- # print a3.name
- print a4.name
V1/a2:0
V2/a2:0