TensorFlow实战2——TensorFlow实现多层感知机

#coding = utf-8
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

mnist = input_data.read_data_sets("MNIST_data/", one_hot = True)
#创建一个IntercativeSession，这样后面的操作就无需指定Session
sess = tf.InteractiveSession()

#隐含层输出节点设置为300，（在此模型中隐含节点数设在200~1000结果区别不大）
in_units = 784
h1_units = 300
#利用tf.truncated_normal实现截断的正态分布，其标准差为0.1 [-1, 784]x[784, 300]
w1 = tf.Variable(tf.truncated_normal([in_units, h1_units], stddev=0.1))
b1 = tf.Variable(tf.zeros([h1_units]))
#[784, 300]x[300, 10]
w2 = tf.Variable(tf.zeros([h1_units, 10]))
b2 = tf.Variable(tf.zeros([10]))

#定义输入x，Dropout的比率keep_prob(通常在训练时小于1，而预测时等于1)
x = tf.placeholder(tf.float32, [None, in_units])
y_ = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)

#hidden1:隐含层 y = relu(W1*x+b1)
hidden1 = tf.nn.relu(tf.matmul(x, w1) + b1)
'''调用tf.nn.dropout实现Dropout，keep_prob在训练时小于1，用于制造随机性，防止过拟合；
在预测时等于1，即使用全部特征来预测样本类别'''
hidden1_drop = tf.nn.dropout(hidden1, keep_prob)

#prediction
y = tf.nn.softmax(tf.matmul(hidden1_drop, w2)+b2)

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y), reduction_indices=[1]))
trian_step = tf.train.AdagradOptimizer(0.3).minimize(cross_entropy)

tf.global_variables_initializer().run()

for i in range(3000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    trian_step.run({x: batch_xs, y_: batch_ys, keep_prob: 0.75})
    #out correct prediction
    correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    if i % 500 == 0:
        print(accuracy.eval({x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

0.2318
0.9584
0.9709
0.9761
0.9778
0.9782