# 验证码生成库

from captcha.image import ImageCaptcha

import numpy as py

# 处理图像的包

from PIL import Image

import random

import sys

number = ['','','','','','','','','','']

# alphabet = ['a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z']

# ALPHABET = ['A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z']

def random_captcha_text(char_set=number, captcha_size=4):

    # 验证码列表

    captcha_text = []

    for i in range(captcha_size):

        # 随机选择

        c = random.choice(char_set)

        # 加入验证码列表

        captcha_text.append(c)

    return captcha_text

# 生成字符对应的验证码

def gen_captcha_text_and_image():

    image = ImageCaptcha()

    # 获得随机生成的验证码

    captcha_text = random_captcha_text()

    # 把验证码列表转化为字符串

    captcha_text = ''.join(captcha_text)

    # 根据字符串生成验证码

    captcha = image.generate(captcha_text)

    image.write(captcha_text, 'captcha/images/' + captcha_text + '.jpg')  # 写到文件

# 0000~9999总共10000，但是数量少于10000，因为重名

num = 10000

if __name__ == '__main__':

    for i in range(num):

        gen_captcha_text_and_image()

        sys.stdout.write('\r>> Creating image %d/%d' % (i+1, num))

        sys.stdout.flush()

    sys.stdout.write('\n')

    sys.stdout.flush()

    print("生成完毕")

import tensorflow as tf

import os

import random

import math

import sys

from PIL import Image

import numpy as np

# 验证集的数量

_NUM_TEST = 500

# 随机种子

_RANDOM_SEED = 0

# 数据集路径

DATASET_DIR = "F:/PyCharm-projects/第十周/captcha/images/"

# tfrecord文件存放路径

TFRECORD_DIR = "F:/PyCharm-projects/第十周"

# 判断tfrecord文件是否存在

def _dataset_exists(dataset_dir):

    for split_name in ['train', 'name']:

        output_filename = os.path.join(dataset_dir, split_name + '.tfrecords')

        if not tf.gfile.Exists(output_filename):

            return False

    return True

# 获取验证码所有图片

def _get_filenames_and_classes(dataset_dir):

    photo_filenames = []

    for filename in os.listdir(dataset_dir):

        # 获取文件路径

        path = os.path.join(dataset_dir, filename)

        photo_filenames.append(path)

    return photo_filenames

def int64_feature(values):

    if not isinstance(values, (tuple, list)):

        values = [values]

    return tf.train.Feature(int64_list=tf.train.Int64List(value=values))

def bytes_feature(values):

    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[values]))

def image_to_tfexample(image_data, label0, label1, label2, label3):

    return tf.train.Example(features=tf.train.Features(feature={

        'image':bytes_feature(image_data),

        'label0':int64_feature(label0),

        'label1': int64_feature(label1),

        'label2': int64_feature(label2),

        'label3': int64_feature(label3),

    }))

# 把数据转化为tfrecord格式

def _convert_dataset(split_name, filenames,dataset_dir):

    assert split_name in ['train', 'test']

    with tf.Session() as sess:

        # 定义tfrecord问津的路径+名字

        output_filename = os.path.join(TFRECORD_DIR, split_name + '.tfrecords')

        with tf.python_io.TFRecordWriter(output_filename) as tfrecord_writer:

            for i, filename in enumerate(filenames):

                try:

                    sys.stdout.write('\r>> Converting image %d/%d' % (i+1, len(filenames)))

                    sys.stdout.flush()

                    # 读取图片

                    image_data = Image.open(filename)

                    # 根据模型的结构resize

                    image_data = image_data.resize((224, 224))

                    # 由于验证码是彩色的，但是我们识别验证码并不需要彩色，灰度图就可以。这样可以减少计算量

                    image_data = np.array(image_data.convert('L'))

                    # 将图片转化为bytes

                    image_data = image_data.tobytes()

                    # 获取level  验证码的前4位就是它的level

                    labels = filename.split('/')[-1][0:4]

                    num_labels = []

                    for j in range(4):

                        num_labels.append(int(labels[j]))

                    # 生成protocol数据类型

                    example = image_to_tfexample(image_data, num_labels[0], num_labels[1], num_labels[2], num_labels[3])

                    tfrecord_writer.write(example.SerializeToString())

                except IOError as e:

                    print('Cloud not read:', filename)

                    print('Error:', e)

                    print('Skip it\n')

    sys.stdout.write('\n')

    sys.stdout.flush()

# 判断tfrecord文件是否存在

if _dataset_exists(TFRECORD_DIR):

    print('tfrecord文件已存在')

else:

    # 获得所有图片

    photo_filenames = _get_filenames_and_classes(DATASET_DIR)

    # 把数据切分为训练集和测试集，并打乱。我们在后面还是会打乱的。这里不打乱也可以

    random.seed(_RANDOM_SEED)

    random.shuffle(photo_filenames)

    training_filenames = photo_filenames[_NUM_TEST:]

    testing_filenames = photo_filenames[:_NUM_TEST]

    # 数据转换

    _convert_dataset('train', training_filenames, DATASET_DIR)

    _convert_dataset('test', testing_filenames, DATASET_DIR)

    print('生成tfrecord文件')