# https://www.cnblogs.com/felixwang2/p/9190692.html

 # TensorFlow(十三)：模型的保存与载入

 import tensorflow as tf

 from tensorflow.examples.tutorials.mnist import input_data

 # 载入数据集

 mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

 # 每个批次100张照片

 batch_size =

 # 计算一共有多少个批次

 n_batch = mnist.train.num_examples // batch_size

 # 定义两个placeholder

 x = tf.placeholder(tf.float32, [None, ])

 y = tf.placeholder(tf.float32, [None, ])

 # 创建一个简单的神经网络，输入层784个神经元，输出层10个神经元

 W = tf.Variable(tf.zeros([, ]))

 b = tf.Variable(tf.zeros([]))

 prediction = tf.nn.softmax(tf.matmul(x, W) + b)

 # 二次代价函数

 # loss = tf.reduce_mean(tf.square(y-prediction))

 loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y, logits=prediction))

 # 使用梯度下降法

 train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

 # 初始化变量

 init = tf.global_variables_initializer()

 # 结果存放在一个布尔型列表中

 correct_prediction = tf.equal(tf.argmax(y, ), tf.argmax(prediction, ))  # argmax返回一维张量中最大的值所在的位置

 # 求准确率

 accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

 saver = tf.train.Saver()

 gpu_options = tf.GPUOptions(allow_growth=True)

 with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:

     sess.run(init)

     for epoch in range():

         for batch in range(n_batch):

             batch_xs, batch_ys = mnist.train.next_batch(batch_size)

             sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys})

         acc = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})

         print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))

     # 保存模型

     saver.save(sess, 'net/my_net.ckpt')

 # https://www.cnblogs.com/felixwang2/p/9190692.html

 # TensorFlow(十三)：模型的保存与载入

 import tensorflow as tf

 from tensorflow.examples.tutorials.mnist import input_data

 # 载入数据集

 mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

 # 每个批次100张照片

 batch_size = 100

 # 计算一共有多少批次

 n_batch = mnist.train.num_examples // batch_size

 # 定义两个placeholder

 x = tf.placeholder(tf.float32, [None, 784])

 y = tf.placeholder(tf.float32, [None, 10])

 # 创建一个简单的神经网络，输入层784个神经单元，输出层10个神经单元

 W = tf.Variable(tf.zeros([784, 10]))

 b = tf.Variable(tf.zeros([10]))

 prediction = tf.nn.softmax(tf.matmul(x, W) + b)

 # 二次代价函数

 # loss = tf.reduce_mean(tf.square(y-prediction))

 loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y, logits=prediction))

 # 使用梯度下降法

 train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

 # 初始化变量

 init = tf.global_variables_initializer()

 # 结果存放在一个布尔值列表中

 correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(prediction, 1)) # argmax返回一维张量中最大的值所在的位置

 # 求准确率

 accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

 saver = tf.train.Saver()

 gpu_options = tf.GPUOptions(allow_growth=True)

 with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:

     sess.run(init)

     # 未载入模型时的识别率

     print('未载入识别率', sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels}))

     saver.restore(sess, 'net/my_net.ckpt')

     # 载入模型后的识别率

     print('载入后识别率', sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels}))