tf.get_variable 和tf.Variable不同的一点是,前者拥有一个变量检查机制,会检测已经存在的变量是否设置为共享变量,如果已经存在的变量没有设置为共享变量,TensorFlow 运行到第二个拥有相同名字的变量的时候,就会报错。tf.variable_scope() 返回的只是 variable_scope,不管 name_scope.所以以后我们在使用tf.variable_scope().reuse_variables() 时可以无视name_scope运行结果:import tensorflow as tf with tf.name_scope("a_name_scope"): initializer = tf.constant_initializer(value=1) #get_variable对name_scope无效使用 #使用tf.get_variable()的时候,tf.name_scope()就不会给 tf.get_variable()创建出来的Variable加前缀 var1 = tf.get_variable(name='var1', shape=[1], dtype=tf.float32, initializer=initializer) #使用tf.Variable()的时候,tf.name_scope()和tf.variable_scope() 都会给 Variable 和 op 的 name属性加上前缀 var2 = tf.Variable(name='var2', initial_value=[2], dtype=tf.float32) var21 = tf.Variable(name='var2', initial_value=[2.1], dtype=tf.float32) var22 = tf.Variable(name='var2', initial_value=[2.2], dtype=tf.float32) with tf.Session() as sess: sess.run(tf.initialize_all_variables()) print(var1.name) # var1:0 print(sess.run(var1)) # [ 1.] print(var2.name) # a_name_scope/var2:0 print(sess.run(var2)) # [ 2.] print(var21.name) # a_name_scope/var2_1:0 print(sess.run(var21)) # [ 2.0999999] print(var22.name) # a_name_scope/var2_2:0 print(sess.run(var22)) # [ 2.20000005] with tf.variable_scope("a_variable_scope") as scope: initializer = tf.constant_initializer(value=3) var3 = tf.get_variable(name='var3', shape=[1], dtype=tf.float32, initializer=initializer) #用Variable方式就可以一直重复利用变量 var4 = tf.Variable(name='var4', initial_value=[4], dtype=tf.float32) var4_reuse = tf.Variable(name='var4', initial_value=[4], dtype=tf.float32) #用get_variable方式,为了能够重复利用变量 name='var3' scope.reuse_variables() #var3 与var3_reuse是同一个variable,共享变量,用reuse_variable比如RNN中train与test结构有所不同但参数都一致 var3_reuse = tf.get_variable(name='var3',) with tf.Session() as sess: init = tf.global_variables_initializer() sess.run(init) print(var3.name) # a_variable_scope/var3:0 print(sess.run(var3)) # [ 3.] print(var4.name) # a_variable_scope/var4:0 print(sess.run(var4)) # [ 4.] print(var4_reuse.name) # a_variable_scope/var4_1:0 print(sess.run(var4_reuse)) # [ 4.] print(var3_reuse.name) # a_variable_scope/var3:0 print(sess.run(var3_reuse)) # [ 3.]
tensorflow 学习笔记14 scope命名方式
最新推荐文章于 2020-10-16 08:15:46 发布