第十四节 验证码识别案列

import tensorflow as tf

FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_string("captcha_dir", "./tfrecords", "验证码数据路径")
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性个数")

# 定义一个随机初始化权重函数
def weight_variables(shape):
    w = tf.Variable(tf.random_normal(shape=shape, mean=0.0, stddev=1.0))
    return w

# 定义一个随机初始化偏置函数
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"""
    # 1.构建文件独立
    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()
    key, value = reader.read(file_queue)

    # tfrecords数据需要解析
    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.解析图片特征值
    image = tf.decode_raw(features["image"], tf.uint8)
    # 2.解析目标值
    label = tf.decode_raw(features["label"], tf.uint8)

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

    # 进行批处理
    image_batch, label_batch = tf.train.batch([image_reshape, label_reshape], batch_size=FLAGS.batch_size, num_threads=2, capacity=10)

    return image_batch, label_batch

def fc_model(image):
    """
    进行预测结果
    image [100, 20, 80, 3]
    """
    with tf.variable_scope("model"):
        # 1。随机初始化权重，偏置
        weights = weight_variables([20*80*3, 4*26])
        bias = bias_variables([4*26])

        # 将图片数据转换成二维
        image_reshape = tf.reshape(image, [-1, 20*80*3])

        # 进行全连接层矩阵运算
        y_predict = tf.matmul(tf.cast(image_reshape, tf.float32), weights) + bias

    return y_predict

def captcharec():
    """验证码识别"""
    # 1.读取验证码数据
    image_batch, label_batch = read_and_decode()

    # 2.通过输入图片的特征数据，建立模型，得出预测结果
    # 一层，全连接层进行预测
    # matrix [100, 20*80*3]*[20*80*3, 4*26] + [104] = [100, 4*26]
    y_predict = fc_model(image_batch)

    # 目标值[100, 4]转换成one-hot编码==>[100, 4, 26]
    y_true = tf.one_hot(label_batch, depth=FLAGS.letter_num, on_value=1.0, axis=2)

    # softmax计算，交叉熵损失计算
    with tf.variable_scope("soft_cross"):
        # 求平均交叉熵损失
        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))

    # 梯度下降优化损失
    with tf.variable_scope("optimizer"):
        # 0.1是学习率，minimize表示求最小损失
        train_op = tf.train.GradientDescentOptimizer(0.0001).minimize(loss)

    # 计算准确率，三维比较 y_predict：[100, 4*26]==>[100, 4, 26]
    with tf.variable_scope("acc"):
        equal_list = tf.equal(tf.argmax(y_true, 2), tf.argmax(tf.reshape(y_predict, [FLAGS.batch_size, FLAGS.label_num, FLAGS.letter_num]), 1))
        # equal_list None个样本 [1, 0, 1, 1, 0, 0.....]
        accuracy = tf.reduce_mean(tf.cast(equal_list, tf.float32))

    # 定义初始化变量op
    init_op = tf.global_variables_initializer()
    # 开启会话
    with tf.Session() as sess:
        sess.run(init_op)

        # 定义线程协调器和开启线程
        coord = tf.train.Coordinator()

        # 开启线程读取文件
        threads = tf.train.start_queue_runners(sess, coord=coord)

        # 训练数据
        for i in range(5000):
            sess.run(train_op)
            print("第{}批次的准确率为：{}".format(i, accuracy.eval()))

        # 回收线程
        coord.request_stop()
        coord.join(threads)
    return None


if __name__ == "__nain__":
    captcharec()