9.MNIST 手写数字识别

手写数字识别思路

1.导入手写数字图片数据库
2.分析图片的特点, 定义变量
3.搭建模型
4.训练模型
5.测试模型
6.保存模型
7.读取、使用模型

准备(ssl防止证书过期报错)

import ssl
ssl._create_default_https_context = ssl._create_unverified_context

1.导入手写数字图片数据库

from tensorflow.examples.tutorials.mnist import input_data
# 1.加载手写数字数据库
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

print("输入数据：\n", mnist.train.images)
print("输入数据的shape：", mnist.train.images.shape)

说明：

2.分析图片的特点, 定义变量

x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

3.搭建模型

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

prediction = tf.nn.softmax(tf.matmul(x, W) + b)

# 损失函数
cost = tf.reduce_mean(-tf.reduce_sum(y * tf.log(prediction), reduction_indices=1))

# 定义参数
learning_rate = 0.01

# 使用梯度下降优化器
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)

4.训练模型

training_epoch = 25
batch_size = 100
display_step = 1

saver = tf.train.Saver()
model_path = "log/mnist_model.ckpt"

with tf.Session() as sess:
    # 初始化所有变量
    sess.run(tf.global_variables_initializer())

    for epoch in range(training_epoch):

        total_batch = int(mnist.train.num_examples/batch_size)
        avg_cost = 0

        for i in range(total_batch):

            batch_xs, batch_ys = mnist.train.next_batch(batch_size)

            _, c = sess.run([optimizer, cost], feed_dict={x: batch_xs, y: batch_ys})

            avg_cost += c / total_batch

        if(epoch + 1) % display_step == 0:
            print("epoch:", "%04d" % (epoch + 1), "cost = ", "{:.9f}".format(avg_cost))

    print("Train Finished!")

5.测试模型

 # 测试模型
    correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print("正确率：", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

6.保存模型

 # 保存模型
    save_path = saver.save(sess, model_path)
    print("Model保存路径：", save_path)

7.读取、使用模型

with tf.Session() as sess:
    # 初始化全局变量
    sess.run(tf.global_variables_initializer())

    saver.restore(sess, model_path)

    # 测试model
    output = tf.argmax(prediction, 1)
    batch_xs, batch_ys = mnist.train.next_batch(2)
    output_value, prediction_value = sess.run([output, prediction], feed_dict={x: batch_xs})
    print("识别结果：", output_value, "\n", prediction_value, "\n", batch_ys)

    # 打印图片
    im = batch_xs[0]
    im = im.reshape(-1, 28)
    pylab.imshow(im)
    pylab.show()

    im = batch_xs[1]
    im = im.reshape(-1, 28)
    pylab.imshow(im)
    pylab.show()