tensorflow变量初始化问题？ 如图，在代码中我已经初始化了变量，为啥还提示未初始化变量

Posted 2023-03-22

如何使用tensorflow内置的参数导出和导入方法：基本用法
如果你还在纠结如何保存tensorflow训练好的模型参数，用这个方法就对了
The Saver class adds ops to save and restore variables to and from checkpoints. It also provides convenience methods to run these ops.来自官网的介绍。
import tensorflow as tf
"""
变量声明，运算声明 例：w = tf.get_variable(name="vari_name", shape=[], dtype=tf.float32)
初始化op声明
"""
#创建saver对象，它添加了一些op用来save和restore模型参数
saver = tf.train.Saver()

with tf.Session() as sess:
sess.run(init_op)
#训练模型。。。
#使用saver提供的简便方法去调用 save op
saver.save(sess, "save_path/file_name.ckpt") #file_name.ckpt如果不存在的话，会自动创建
#后缀可加可不加 参考技术A The Saver class adds ops to save and restore variables to and from checkpoints. It also provides convenience methods to run these ops.来自官网的介绍。The Saver class adds ops to save and restore variables to and from checkpoints. It also provides convenience methods to run these ops.来自官网的介绍。The Saver class adds ops to save and restore variables to and from checkpoints. It also provides convenience methods to run these ops.来自官网的介绍。