tensorflow实现验证码识别案例

1、知识点

"""
验证码分析：
    对图片进行分析：
                1、分割识别
                2、整体识别
输出：[3,5,7]  -->softmax转为概率[0.04,0.16,0.8] ---> 交叉熵计算损失值 (目标值和预测值的对数)
tf.argmax(预测值，2)
验证码样例：[NAZP] [XCVB] [WEFW] ，都是字母的
"""

2、将数据写入TFRecords

import tensorflow as tf
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = ''

FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string("tfrecords_dir", "./tfrecords/captcha.tfrecords", "验证码tfrecords文件")
tf.app.flags.DEFINE_string("captcha_dir", "../data/Genpics/", "验证码图片路径")
tf.app.flags.DEFINE_string("letter", "ABCDEFGHIJKLMNOPQRSTUVWXYZ", "验证码字符的种类")

def dealwithlabel(label_str):

    # 构建字符索引 {0：'A', 1:'B'......}
    num_letter = dict(enumerate(list(FLAGS.letter)))

    # 键值对反转 {'A':0, 'B':1......}
    letter_num = dict(zip(num_letter.values(), num_letter.keys()))

    print(letter_num)

    # 构建标签的列表
    array = []

    # 给标签数据进行处理[[b"NZPP"]......]
    for string in label_str:

        letter_list = []# [1,2,3,4]

        # 修改编码，b'FVQJ'到字符串，并且循环找到每张验证码的字符对应的数字标记
        for letter in string.decode('utf-8'):
            letter_list.append(letter_num[letter])

        array.append(letter_list)

    # [[13, 25, 15, 15], [22, 10, 7, 10], [22, 15, 18, 9], [16, 6, 13, 10], [1, 0, 8, 17], [0, 9, 24, 14].....]
    print(array)

    # 将array转换成tensor类型
    label = tf.constant(array)

    return label

def get_captcha_image():
    """
    获取验证码图片数据
    :param file_list: 路径+文件名列表
    :return: image
    """
    # 构造文件名
    filename = []

    for i in range(6000):
        string = str(i) + ".jpg"
        filename.append(string)

    # 构造路径+文件
    file_list = [os.path.join(FLAGS.captcha_dir, file) for file in filename]

    # 构造文件队列
    file_queue = tf.train.string_input_producer(file_list, shuffle=False)

    # 构造阅读器
    reader = tf.WholeFileReader()

    # 读取图片数据内容
    key, value = reader.read(file_queue)

    # 解码图片数据
    image = tf.image.decode_jpeg(value)

    image.set_shape([20, 80, 3])

    # 批处理数据 [6000, 20, 80, 3]
    image_batch = tf.train.batch([image], batch_size=6000, num_threads=1, capacity=6000)

    return image_batch

def get_captcha_label():
    """
    读取验证码图片标签数据
    :return: label
    """
    file_queue = tf.train.string_input_producer(["../data/Genpics/labels.csv"], shuffle=False)

    reader = tf.TextLineReader()

    key, value = reader.read(file_queue)

    records = [[1], ["None"]]

    number, label = tf.decode_csv(value, record_defaults=records)

    # [["NZPP"], ["WKHK"], ["ASDY"]]
    label_batch = tf.train.batch([label], batch_size=6000, num_threads=1, capacity=6000)

    return label_batch

def write_to_tfrecords(image_batch, label_batch):
    """
    将图片内容和标签写入到tfrecords文件当中
    :param image_batch: 特征值
    :param label_batch: 标签纸
    :return: None
    """
    # 转换类型
    label_batch = tf.cast(label_batch, tf.uint8)

    print(label_batch)

    # 建立TFRecords 存储器
    writer = tf.python_io.TFRecordWriter(FLAGS.tfrecords_dir)

    # 循环将每一个图片上的数据构造example协议块，序列化后写入
    for i in range(6000):
        # 取出第i个图片数据，转换相应类型,图片的特征值要转换成字符串形式
        image_string = image_batch[i].eval().tostring()

        # 标签值，转换成整型
        label_string = label_batch[i].eval().tostring()

        # 构造协议块
        example = tf.train.Example(features=tf.train.Features(feature={
            "image": tf.train.Feature(bytes_list=tf.train.BytesList(value=[image_string])),
            "label": tf.train.Feature(bytes_list=tf.train.BytesList(value=[label_string]))
        }))

        writer.write(example.SerializeToString())

    # 关闭文件
    writer.close()

    return None

if __name__ == "__main__":

    # 获取验证码文件当中的图片
    image_batch = get_captcha_image()

    # 获取验证码文件当中的标签数据
    label = get_captcha_label()

    print(image_batch, label)

    with tf.Session() as sess:

        coord = tf.train.Coordinator()

        threads = tf.train.start_queue_runners(sess=sess, coord=coord)

        # [b'NZPP' b'WKHK' b'WPSJ' ..., b'FVQJ' b'BQYA' b'BCHR']
        label_str = sess.run(label)

        print(label_str)

        # 处理字符串标签到数字张量
        label_batch = dealwithlabel(label_str)

        print(label_batch)

        # 将图片数据和内容写入到tfrecords文件当中
        write_to_tfrecords(image_batch, label_batch)

        coord.request_stop()

        coord.join(threads)

3、数据存在百度云(小白号)

4、标准代码

import tensorflow as tf

FLAGS = tf.app.flags.FLAGS

tf.app.flags.DEFINE_string("captcha_dir", "./tfrecords/captcha.tfrecords", "验证码数据的路径")
tf.app.flags.DEFINE_integer("batch_size", 100, "每批次训练的样本数")
tf.app.flags.DEFINE_integer("label_num", 4, "每个样本的目标值数量")
tf.app.flags.DEFINE_integer("letter_num", 26, "每个目标值取的字母的可能心个数")

# 定义一个初始化权重的函数
def weight_variables(shape):
    w = tf.Variable(tf.random_normal(shape=shape, mean=0.0, stddev=1.0))
    return w

# 定义一个初始化偏置的函数
def bias_variables(shape):
    b = tf.Variable(tf.constant(0.0, shape=shape))
    return b

def read_and_decode():
    """
    读取验证码数据API
    :return: image_batch, label_batch
    """
    # 1、构建文件队列
    file_queue = tf.train.string_input_producer([FLAGS.captcha_dir])

    # 2、构建阅读器，读取文件内容，默认一个样本
    reader = tf.TFRecordReader()

    # 读取内容
    key, value = reader.read(file_queue)

    # tfrecords格式example,需要解析
    features = tf.parse_single_example(value, features={
        "image": tf.FixedLenFeature([], tf.string),
        "label": tf.FixedLenFeature([], tf.string),
    })

    # 解码内容，字符串内容
    # 1、先解析图片的特征值
    image = tf.decode_raw(features["image"], tf.uint8)
    # 1、先解析图片的目标值
    label = tf.decode_raw(features["label"], tf.uint8)

    # print(image, label)

    # 改变形状
    image_reshape = tf.reshape(image, [20, 80, 3])

    label_reshape = tf.reshape(label, [4])

    print(image_reshape, label_reshape)

    # 进行批处理,每批次读取的样本数 100, 也就是每次训练时候的样本
    image_batch, label_btach = tf.train.batch([image_reshape, label_reshape], batch_size=FLAGS.batch_size, num_threads=1, capacity=FLAGS.batch_size)

    print(image_batch, label_btach)
    return image_batch, label_btach

def fc_model(image):
    """
    进行预测结果
    :param image: 100图片特征值[100, 20, 80, 3]
    :return: y_predict预测值[100, 4 * 26]
    """
    with tf.variable_scope("model"):
        # 将图片数据形状转换成二维的形状
        image_reshape = tf.reshape(image, [-1, 20 * 80 * 3])

        # 1、随机初始化权重偏置
        # matrix[100, 20 * 80 * 3] * [20 * 80 * 3, 4 * 26] + [104] = [100, 4 * 26]
        weights = weight_variables([20 * 80 * 3, 4 * 26])
        bias = bias_variables([4 * 26])

        # 进行全连接层计算[100, 4 * 26]
        y_predict = tf.matmul(tf.cast(image_reshape, tf.float32), weights) + bias

    return y_predict

def predict_to_onehot(label):
    """
    将读取文件当中的目标值转换成one-hot编码
    :param label: [100, 4]      [[13, 25, 15, 15], [19, 23, 20, 16]......]
    :return: one-hot
    """
    # 进行one_hot编码转换，提供给交叉熵损失计算，准确率计算[100, 4, 26]
    label_onehot = tf.one_hot(label, depth=FLAGS.letter_num, on_value=1.0, axis=2)

    print(label_onehot)

    return label_onehot

def captcharec():
    """
    验证码识别程序
    :return:
    """
    # 1、读取验证码的数据文件 label_btch [100 ,4]
    image_batch, label_batch = read_and_decode()

    # 2、通过输入图片特征数据，建立模型，得出预测结果
    # 一层，全连接神经网络进行预测
    # matrix [100, 20 * 80 * 3] * [20 * 80 * 3, 4 * 26] + [104] = [100, 4 * 26]
    y_predict = fc_model(image_batch)

    #  [100, 4 * 26]
    print(y_predict)

    # 3、先把目标值转换成one-hot编码 [100, 4, 26]
    y_true = predict_to_onehot(label_batch)

    # 4、softmax计算, 交叉熵损失计算
    with tf.variable_scope("soft_cross"):
        # 求平均交叉熵损失 ,y_true [100, 4, 26]--->[100, 4*26]
        loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
            labels=tf.reshape(y_true, [FLAGS.batch_size, FLAGS.label_num * FLAGS.letter_num]),
            logits=y_predict))
    # 5、梯度下降优化损失
    with tf.variable_scope("optimizer"):

        train_op = tf.train.GradientDescentOptimizer(0.01).minimize(loss)

    # 6、求出样本的每批次预测的准确率是多少 三维比较
    with tf.variable_scope("acc"):

        # 比较每个预测值和目标值是否位置(4)一样    y_predict [100, 4 * 26]---->[100, 4, 26]
        equal_list = tf.equal(tf.argmax(y_true, 2), tf.argmax(tf.reshape(y_predict, [FLAGS.batch_size, FLAGS.label_num, FLAGS.letter_num]), 2))

        # equal_list  100个样本   [1, 0, 1, 0, 1, 1,..........]
        accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))

    # 定义一个初始化变量的op
    init_op = tf.global_variables_initializer()

    # 开启会话训练
    with tf.Session() as sess:
        sess.run(init_op)

        # 定义线程协调器和开启线程（有数据在文件当中读取提供给模型）
        coord = tf.train.Coordinator()

        # 开启线程去运行读取文件操作
        threads = tf.train.start_queue_runners(sess, coord=coord)

        # 训练识别程序
        for i in range(5000):

            sess.run(train_op)

            print("第%d批次的准确率为：%f" % (i, accuracy.eval()))

        # 回收线程
        coord.request_stop()

        coord.join(threads)

    return None

if __name__ == "__main__":
    captcharec()

5、自写代码

# coding = utf-8

import tensorflow as tf
from tensorflow.contrib.slim.python.slim.nets.inception_v3 import inception_v3_base
import  os
"""
验证码分析：
    对图片进行分析：
                1、分割识别
                2、整体识别
输出：[3,5,7]  -->softmax转为概率[0.04,0.16,0.8] ---> 交叉熵计算损失值 (目标值和预测值的对数)
tf.argmax(预测值，2)
"""
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string("captcha_dir","./tfrecords/captcha.tfrecords","验证码数据路径")
tf.app.flags.DEFINE_integer("batch_size",100,"读取批次")
tf.app.flags.DEFINE_integer("label_num", 4, "每个样本的目标值数量")
tf.app.flags.DEFINE_integer("letter_num", 26, "每个目标值取的字母的可能心个数")

def weight_variable(shape):
    w = tf.Variable(tf.random_normal(shape=shape,mean=0.0,stddev=1.0,))
    return w
def bias_variable(shape):
    b = tf.Variable(tf.random_normal(shape=shape,mean=0.0,stddev=1.0))
    return b

def captcharec():
    """
    验证码识别
    :return:
    """
    #1、读取验证码的数据文件
    file_queue = tf.train.string_input_producer([FLAGS.captcha_dir])

    #2、创建阅读器,解析example
    reader = tf.TFRecordReader()
    key ,value = reader.read(file_queue)
    features = tf.parse_single_example(value,features={
        "image":tf.FixedLenFeature([],tf.string),
        "label": tf.FixedLenFeature([], tf.string)
    })
    #解码操作
    image = tf.decode_raw(features["image"],tf.uint8)
    label = tf.decode_raw(features["label"],tf.uint8)
    print(image,label)

    #修改形状
    image_reshape = tf.reshape(image,[20,80,3])
    label_reshape = tf.reshape(label, [4])

    #进行批处理，每次读取100个样本
    image_batch,label_batch = tf.train.batch([image_reshape,label_reshape],batch_size=100,num_threads=1,capacity=20)
    print(image_batch, label_batch)
    return image_batch,label_batch

def fc_model(image_batch):
    #1、初始化权重和偏置
    w = weight_variable([20*80*3,4*26])
    b = bias_variable([4*26])

    #模型 x [100,20*80*3]  w [20*80*3,4]          y_true [100,4]
    #对输入进行矩阵转换
    image = tf.reshape(image_batch,[-1,20*80*3])
    y_predict = tf.matmul(tf.cast(image,tf.float32),w) + b

    ############收集变量########
    tf.summary.histogram("w",w)
    tf.summary.histogram("b",b)
    merged = tf.summary.merge_all()
    return y_predict,merged

#[100,4]
def predict_to_onehot(label_batch):
    y_true = tf.one_hot(label_batch,on_value=1.0,depth=26,axis=2)
    return y_true

if __name__ == '__main__':
    image_batch, label_batch = captcharec()
    y_predict,merged_his =fc_model(image_batch)
    y_true = predict_to_onehot(label_batch)

    #计算交叉熵
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=tf.reshape(y_true,[100,4*26]),logits=y_predict))

    #梯度下降优化
    train_op = tf.train.GradientDescentOptimizer(0.001).minimize(loss)

    #准确率
    equal_list = tf.equal(tf.argmax(y_true,2),tf.argmax(tf.reshape(y_predict,[100,4,26]),2))
    accuracy = tf.reduce_mean(tf.cast(equal_list,tf.float32))

    #####收集变量###############
    tf.summary.scalar("losses",loss)
    tf.summary.scalar("accuracy",accuracy)
    merged_scalar = tf.summary.merge_all()

    ############保存模型####
    saver = tf.train.Saver()

    init_op = tf.global_variables_initializer()
    with tf.Session() as sess:
        sess.run(init_op)

        fileWriter = tf.summary.FileWriter("./vc",graph=sess.graph)
        #创建线程协调器
        coord = tf.train.Coordinator()

        #开启线程
        threads = tf.train.start_queue_runners(sess,coord=coord)
        IS_TRAIN =1

        # if os.path.exists("./vertifycode/checkpoint"):
        #     IS_TRAIN = 0

        if IS_TRAIN==1:
            #######训练模型###############
            # if os.path.exists("./vertifycode/checkpoint"):
            #     saver.restore(sess, "./vertifycode/vertifycode_model")

            for i in range(2000):
                sess.run(train_op)
                summary_his = sess.run(merged_his)
                summary_scalar = sess.run(merged_scalar)
                fileWriter.add_summary(summary_scalar,i)
                fileWriter.add_summary(summary_his,i)
                print("训练第%d次的准确率为：%f" %(i,accuracy.eval()))

            #######保存模型#############
            saver.save(sess,"./vertifycode/vertifycode_model")
        else:
            ##########测试模型##################
            for i in range(10):
                saver.restore(sess, "./vertifycode/vertifycode_model")
                # print("第%d张图片的准确率为：%f" % (
                #     i,
                #     tf.argmax(y_test, 2).eval(),
                #     tf.argmax(y_predict,2).eval()
                #                           ))

        #停止线程
        coord.request_stop()
        coord.join(threads)