1 # -*- coding: utf-8 -*- 2 """ 3 Created on Mon Oct 22 17:23:49 2018 4  5 @author: zhen 6 """ 7 import tensorflow as tf 8 from tensorflow.examples.tutorials.mnist import input_data 9 import numpy as np10 from tensorflow.contrib.layers import fully_connected11 12 # 构建图阶段13 n_inputs = 28 * 2814 n_hidden1 = 30015 n_hidden2 = 10016 n_outputs = 1017 18 x = tf.placeholder(tf.float32, shape=(None, n_inputs), name='x')19 y = tf.placeholder(tf.int64, shape=(None), name='y')20 21 # 构建神经网络，基于两个隐藏层，激活函数：relu，Softmax22 def neuron_layer(x, n_neurons, name, activation=None):23     with tf.name_scope(name):24         # 取输入矩阵的维度作为层的输入连接个数25         n_inputs = int(x.get_shape()[1])26         stddev = 2 / np.sqrt(n_inputs)27         init = tf.truncated_normal((n_inputs, n_neurons), stddev=stddev)28         w = tf.Variable(init, name='weights')29         b = tf.Variable(tf.zeros([n_neurons]), name='biases')30         z = tf.matmul(x, w) + b31         if activation == 'relu':32             return tf.nn.relu(z)33         else:34             return z35 36 with tf.name_scope("dnn"):37     # 创建输入层到第一层隐藏层的映射38     hidden1 = neuron_layer(x, n_hidden1, "hidden1", activation="relu")39     # 创建第一层隐藏层到第二层隐藏层的映射40     hidden2 = neuron_layer(hidden1, n_hidden2, "hidden2", activation="relu")41     # 创建第二层隐藏层到输出层的映射42     logits = neuron_layer(hidden2, n_outputs, "outputs")43      44 with tf.name_scope("loss"):45     entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y, logits=logits)        46     loss = tf.reduce_mean(entropy, name="loss")47     48 learning_rate = 0.0149 50 with tf.name_scope("train"):51     optimizer = tf.train.GradientDescentOptimizer(learning_rate)52     training_op = optimizer.minimize(loss)53     54 with tf.name_scope("eval"):55     correct = tf.nn.in_top_k(logits, y, 1)56     accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))57     58 init = tf.global_variables_initializer()59 saver = tf.train.Saver()60 61 # 计算图阶段62 mnist = input_data.read_data_sets("C:/Users/zhen/MNIST_data_bak/")63 n_epochs = 2064 batch_size = 5065 66 with tf.Session() as sess:67     init.run()68     for epoch in range(n_epochs):69         for iteration in range(mnist.train.num_examples // batch_size):70             x_batch, y_batch = mnist.train.next_batch(batch_size)71             sess.run(training_op, feed_dict={x:x_batch, y:y_batch})72         acc_train = accuracy.eval(feed_dict={x:x_batch, y:y_batch})73         acc_test = accuracy.eval(feed_dict={x:mnist.test.images, y:mnist.test.labels})74         print(epoch, "train accuracy:", acc_train, "test accuracy", acc_test)75     save_path = saver.save(sess, "./my_dnn_model_final.ckpt")76

结果：

　　

分析：

　　从结果可知：整体训练和测试准确率较高，前期波动较大，后期逐渐趋于稳定，收敛！