响应式相册网站,汕头网络推广,免费手机网站建站平台,高端建造https://blog.csdn.net/UESTC_C2_403/article/details/72328815
tf.variable_scope可以让变量有相同的命名#xff0c;包括tf.get_variable得到的变量#xff0c;还有tf.Variable的变量
tf.name_scope可以让变量有相同的命名#xff0c;只是限于tf.Variable的变量
例如包括tf.get_variable得到的变量还有tf.Variable的变量
tf.name_scope可以让变量有相同的命名只是限于tf.Variable的变量
例如
import tensorflow as tf; import numpy as np; import matplotlib.pyplot as plt; with tf.variable_scope(V1): a1 tf.get_variable(namea1, shape[1], initializertf.constant_initializer(1)) a2 tf.Variable(tf.random_normal(shape[2,3], mean0, stddev1), namea2) with tf.variable_scope(V2): a3 tf.get_variable(namea1, shape[1], initializertf.constant_initializer(1)) a4 tf.Variable(tf.random_normal(shape[2,3], mean0, stddev1), namea2) with tf.Session() as sess: sess.run(tf.initialize_all_variables()) print a1.name print a2.name print a3.name print a4.name 输出 V1/a1:0 V1/a2:0 V2/a1:0 V2/a2:0 例子2
import tensorflow as tf; import numpy as np; import matplotlib.pyplot as plt; with tf.name_scope(V1): a1 tf.get_variable(namea1, shape[1], initializertf.constant_initializer(1)) a2 tf.Variable(tf.random_normal(shape[2,3], mean0, stddev1), namea2) with tf.name_scope(V2): a3 tf.get_variable(namea1, shape[1], initializertf.constant_initializer(1)) a4 tf.Variable(tf.random_normal(shape[2,3], mean0, stddev1), namea2) with tf.Session() as sess: sess.run(tf.initialize_all_variables()) print a1.name print a2.name print a3.name print a4.name 报错Variable a1 already exists, disallowed. Did you mean to set reuseTrue in VarScope? Originally defined at: 换成下面的代码就可以执行
import tensorflow as tf; import numpy as np; import matplotlib.pyplot as plt; with tf.name_scope(V1): # a1 tf.get_variable(namea1, shape[1], initializertf.constant_initializer(1)) a2 tf.Variable(tf.random_normal(shape[2,3], mean0, stddev1), namea2) with tf.name_scope(V2): # a3 tf.get_variable(namea1, shape[1], initializertf.constant_initializer(1)) a4 tf.Variable(tf.random_normal(shape[2,3], mean0, stddev1), namea2) with tf.Session() as sess: sess.run(tf.initialize_all_variables()) # print a1.name print a2.name # print a3.name print a4.name 输出 V1/a2:0 V2/a2:0
