TensorFlow 利用卷积神经网络辨别MNIST数据集

卷积操作padding详解：https://blog.csdn.net/jiandanjinxin/article/details/77519629

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf


mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()


def weight_variable(shape):
    return tf.Variable(tf.truncated_normal(shape, stddev=0.1))


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


def conv2d(x, W):
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')


def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')


x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
x_image = tf.reshape(x, [-1, 28, 28, 1])

# 第一层卷积
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)  # output size:28x28x32
h_pool1 = max_pool_2x2(h_conv1)                           # output size:14x14x32

# 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)  # output size:14x14x64
h_pool2 = max_pool_2x2(h_conv2)                           # output size:7x7x64

# 全连接层,1024个隐含结点
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
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)

#误差函数
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y *tf.log(y_conv), axis=1))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

#准确率
correct_prediction = tf.equal(tf.argmax(y, axis=1), tf.argmax(y_conv, axis=1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

#开始训练
tf.global_variables_initializer().run()
for _ in range(20000):
    batch = mnist.train.next_batch(50)
    train_step.run({x: batch[0], y: batch[1], keep_prob: 0.5})
    if _ % 100 == 0:
        train_accuracy = accuracy.eval({x: batch[0], y: batch[1], keep_prob: 1.0})
        print(train_accuracy)