saver

保存 import所需的模块, 然后建立神经网络当中的 W 和 b, 并初始化变量. import tensorflow as tf import numpy as np ## Save to file # remember to define the same dtype and shape when restore W = tf.Variable( [[1,2,3],[3,4,5]] , dtype=tf.float32, name= 'weights' ) b = tf.Variable( [[1,2,3]] , dtype=tf.float32, name= 'biases' ) # init= tf.initialize_all_variables() # tf 马上就要废弃这种写法 # 替换成下面的写法: init = tf.global_variables_initializer() 保存时, 首先要建立一个 tf.train.Saver() 用来保存, 提取变量. Saver 的例子： v1 = tf.Variable( ... , name= 'v1' ) v2 = tf.Variable( ... , name= 'v2' ) # dict形式传递 saver = tf.train.Saver({ 'v1' : v1, 'v2' : v2}) #

#保存代码 import tensorflow as tf W=tf.Variable([ 2 , 3 ], dtype =tf.float32, name = "weight" ) #W=[2,3] b=tf.Variable([ 3 ], dtype =tf.float32, name = "biases" ) init=tf.initialize_all_variables() saver=tf.train.Saver() with tf.Session() as sess: sess.run(init) path=saver.save(sess, "path/weights.ckpt" ) print ( "path" ,path) #恢复代码 W=tf.Variable(np.arange( 2 ).reshape(( 1 , 2 )), dtype =tf.float32, name = "weight" ) b=tf.Variable(np.arange( 1 ).reshape(( 1 , 1 )), dtype =tf.float32, name = "biases" ) saver=tf.train.Saver() with tf.Session() as sess: "path/weights.ckpt" ) ( "w,b" ,sess.run(W),sess

1.目前只总结出两条 创建saver实例saver = tf.train.Saver()放在循环外面 不循环初始化变量 sess.run(tf.global_variables_initializer()) 来源： https://www.cnblogs.com/lzq116/p/11313488.html