卷积神经网络(CNN)实现手写体识别

 本博客将建立一个简单的卷积神经网络，可以把MNIST手写字符的识别准确率提高到99%。具体如下：

程序的开头是导入TensorFlow

import tensorflow as tf
import numpy as np
import os 

os.environ["CUDA_VISIBLE_DEVICES"] = "0"#指定GPU

#从tensorflow.examples.tutorials.mnist引入模块
from tensorflow.examples.tutorials.mnist import input_data

 查看训练集、验证集、测试集的数据大小

#查看训练数据的大小
print(mnist.train.images.shape)  # (55000, 784)
print(mnist.train.labels.shape)  # (55000, 10)

#查看验证数据的大小
print(mnist.validation.images.shape)  # (5000, 784)
print(mnist.validation.labels.shape)  # (5000, 10)

#查看测试数据的大小
print(mnist.test.images.shape)  # (10000, 784)
print(mnist.test.labels.shape)  # (10000, 10)

#打印出第0幅图片的向量表示
print(mnist.train.images[0, :])

#打印出第0幅图片的标签
print(mnist.train.labels[0, :])

#查看前20张训练图片的label
for i in range(20):
    
    #得到one-hot表示，形如(0, 1, 0, 0, 0, 0, 0, 0, 0, 0)
    one_hot_label = mnist.train.labels[i, :]
    # 通过np.argmax我们可以直接获得原始的label
    # 因为只有1位为1，其他都是0
    label = np.argmax(one_hot_label)
    print('mnist_train_%d.jpg label: %d' % (i, label))

 完整代码为

import tensorflow as tf
import numpy as np
import os 

os.environ["CUDA_VISIBLE_DEVICES"] = "0"#指定GPU

#从tensorflow.examples.tutorials.mnist引入模块
from tensorflow.examples.tutorials.mnist import input_data


#从MNIST_data/中读取MNIST数据,当数据不存在时，会自动执行下载
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

#查看训练数据的大小
print(mnist.train.images.shape)  # (55000, 784)
print(mnist.train.labels.shape)  # (55000, 10)

#查看验证数据的大小
print(mnist.validation.images.shape)  # (5000, 784)
print(mnist.validation.labels.shape)  # (5000, 10)

#查看测试数据的大小
print(mnist.test.images.shape)  # (10000, 784)
print(mnist.test.labels.shape)  # (10000, 10)

#打印出第0幅图片的向量表示
print(mnist.train.images[0, :])

#打印出第0幅图片的标签
print(mnist.train.labels[0, :])

#查看前20张训练图片的label
for i in range(20):
    
    #得到one-hot表示，形如(0, 1, 0, 0, 0, 0, 0, 0, 0, 0)
    one_hot_label = mnist.train.labels[i, :]
    # 通过np.argmax我们可以直接获得原始的label
    # 因为只有1位为1，其他都是0
    label = np.argmax(one_hot_label)
    print('mnist_train_%d.jpg label: %d' % (i, label))


#定义权重
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

#定义偏置
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

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

#最大池化层，步长为2
def max_pool_2x2(x):
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')


if __name__ == '__main__':
    
    #x为训练图像的占位符，输入图像是28*28=784
    x = tf.placeholder(tf.float32, [None, 784])
    #y_为训练图像标签的占位符，输出类别是10类
    y_ = tf.placeholder(tf.float32, [None, 10])

    #将单张图片从784维向量重新还原为28x28的矩阵图片
    x_image = tf.reshape(x, [-1, 28, 28, 1])
    
    with tf.variable_scope("conv1"):
        
        #第一层卷积层和池化层，卷积核大小为5*5，卷积核个数为32，
        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)
        h_pool1 = max_pool_2x2(h_conv1)
    
    with tf.variable_scope("conv2"):
        #第二层卷积层和池化层，卷积核大小为5*5，卷积核个数为64
        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)
    
    with tf.variable_scope("fc1"):
        #全连接层，输出为1024维的向量
        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)
    
    #使用Dropout，keep_prob是一个占位符，训练时为0.5，测试时为1
    keep_prob = tf.placeholder(tf.float32)
    h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

    #把1024维的向量转换成10维，对应10个类别
    W_fc2 = weight_variable([1024, 10])
    b_fc2 = bias_variable([10])
    y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
    
    with tf.variable_scope("loss"):
        #不采用先Softmax再计算交叉熵的方法，而是直接用tf.nn.softmax_cross_entropy_with_logits直接计算
        loss = tf.reduce_mean(
                tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
        
        
    with tf.variable_scope("optimizer"):
        #同样定义train_step
        train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)
        
    with tf.variable_scope("acc"):
        #定义测试的准确率，tf.argmax（y，1）、tf.argmax（y_，1）的功能是取出数组中最大值的下标
        correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        #收集变量，单个数字值收集
    
    #记录loss，accuracy变化曲线
    tf.summary.scalar("losses",loss)
    tf.summary.scalar("acc",accuracy)
    
    #高纬度变量收集
    tf.summary.histogram('weightes',W_conv1)
    tf.summary.histogram('biases',b_conv1)

    #创建Session和变量初始化
    init_op = tf.global_variables_initializer()
    
    #定义一个合并变量的op
    merged = tf.summary.merge_all()
    
    with tf.Session() as sess:
        #初始化所有变量
        sess.run(init_op)
        
        #建立events文件，然后写入
        filewriter = tf.summary.FileWriter('./tensorboard/',graph=sess.graph)
        
        #训练20000步
        for i in range(20000):
            batch = mnist.train.next_batch(64)
            train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
            
            #写入每步训练的值
            summary = sess.run(merged,feed_dict={x:batch[0], y_:batch[1], keep_prob: 0.5})
            filewriter.add_summary(summary,i)
            
            #每100步显示一次在验证集上的准确度
            if i % 100 == 0:
                #显示训练时的准确率
                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))
        
                #在验证集上的准确度
                print("validation accuracy %g" % accuracy.eval(feed_dict={
                        x: mnist.validation.images, y_: mnist.validation.labels, keep_prob: 1.0}))
    
        #训练结束后报告在测试集上的准确度
        print("test accuracy %g" % accuracy.eval(feed_dict={
                x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

 运行结果如下图所示

图

 损失函数变化曲线

准确率变化曲线