TensorFlow——深入MNIST

程序（有些不甚明白的地方改日修订）：

# _*_coding:utf-8_*_

import inputdata
mnist = inputdata.read_data_sets('MNIST_data', one_hot=True)    # mnist是一个以numpy数组形式存储训练、验证和测试数据的轻量级类

import tensorflow as tf
sess = tf.InteractiveSession()


x = tf.placeholder("float",shape=[None, 784])
y_ = tf.placeholder("float", shape=[None, 10])

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

sess.run(tf.initialize_all_variables())

y = tf.nn.softmax(tf.matmul(x,W)+b)     # nn:neural network

# 代价函数
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))

# 最优化算法
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)    # 会更新权值

for i in range(1000):
    batch = mnist.train.next_batch(50)
    train_step.run(feed_dict={x:batch[0], y_:batch[1]})    # 可以用feed_dict来替代任何张量，并不仅限于替换placeholder

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_, 1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

print accuracy.eval(feed_dict={x:mnist.test.images, y_:mnist.test.labels})

# 构建多层卷积网络模型

# 初始化W,b的函数
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)    # truncated_normal表示的是截断的正态分布
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

# 卷积和池化
def conv2d(x, W):    # 卷积用原版，1步长0边距
    return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')

def max_pool_2x2(x):    # 池化用传统的2*2模板做max polling
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

# 第一层卷积
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])

x_image = tf.reshape(x, [-1,28,28,1])

h_conv1= tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

# 第二层卷积
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

# 密集连接层
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

# dropout
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# 输出层
W_fc2= weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv= tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

# 训练和评估模型
cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run(tf.initialize_all_variables())
for i in range(20000):
    batch = mnist.train.next_batch(50)
    if i%100 == 0:
        train_accuracy = accuracy.eval(feed_dict={ x:batch[0], y_: batch[1], keep_prob: 1.0})
        print "step %d, training accuracy %g" %(i, train_accuracy)
    train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob:0.5})

print "test accuracy %g" % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})

运行结果：

0.9092
step 0, training accuracy 0.08
step 100, training accuracy 0.9
step 200, training accuracy 0.94
step 300, training accuracy 0.98
step 400, training accuracy 0.98
step 500, training accuracy 0.9
step 600, training accuracy 0.96
step 700, training accuracy 0.96
step 800, training accuracy 0.96
step 900, training accuracy 0.94
step 1000, training accuracy 0.98
step 1100, training accuracy 1
step 1200, training accuracy 0.92
step 1300, training accuracy 0.96
step 1400, training accuracy 0.92
step 1500, training accuracy 0.98
...明天早上跑出来再贴