TensorFlow 模型的保存与载入

参考学习博客：

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

一、模型保存

 # 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')

输出结果：

Iter ,Testing Accuracy 0.8629
Iter ,Testing Accuracy 0.896
Iter ,Testing Accuracy 0.9028
Iter ,Testing Accuracy 0.9052
Iter ,Testing Accuracy 0.9085
Iter ,Testing Accuracy 0.9099
Iter ,Testing Accuracy 0.9122
Iter ,Testing Accuracy 0.9139
Iter ,Testing Accuracy 0.9148
Iter ,Testing Accuracy 0.9163
Iter ,Testing Accuracy 0.9165

二、模型载入

 # 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}))

未载入识别率 0.098
载入后识别率 0.9178

程序输出如上结果。