采用TensorFlow支持通過tf.Graph函數來生成新的向量圖，代碼如下：
import tensorflow as tf g1 = tf.Graph() with g1.as_default(): v = tf.get_variable( "v",initializer=tf.zeros_initializer(shape = [1])) g2 = tf.Graph() with g2.as_default(): v = tf.get_variable( "v",initializer=tf.ones_initializer(shape = [1])) with tf.Session(graph=g1) as sess: tf.initialize_all_variables().run() with tf.variable_scope("",reuse=True): print(sess.run(tf.get_variable("v"))) with tf.Session(graph=g2) as sess: tf.initialize_all_variables().run() with tf.variable_scope("",reuse=True): print(sess.run(tf.get_variable("v")))
執行后發生如下錯誤：
解決辦法：因為上述代碼寫法是TensorFlow舊版本的寫法，將Line6 和Line10 改如下如下可以實現代碼的正常運行：
v = tf.get_variable("v",initializer=tf.zeros_initializer()(shape = [1]))
v = tf.get_variable( "v",initializer=tf.ones_initializer()(shape = [1]))
輸出結果如下圖：
明顯有一個更新提示，表示該初始化的語句也需要進行更新：
tf.initialize_all_variables().run() 變成 tf.global_variables_initializer().run()
最后輸出結果：
源於博客：https://blog.csdn.net/li_haiyu/article/category/7625657