首页 > 其他分享 >验证码模型训练与识别

验证码模型训练与识别

时间:2023-05-28 23:23:01浏览次数:37  
标签:nn text 模型 random 验证码 captcha tf 识别 image

1. 训练模型代码

import numpy as np
import tensorflow as tf 
# import tensorflow.compat.v1 as tf
# tf.disable_v2_behavior()
from captcha.image import ImageCaptcha
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
import random
number = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']

def random_captcha_text(char_set=number, captcha_size=4): captcha_text = [] for i in range(captcha_size): c = random.choice(char_set) captcha_text.append(c) return captcha_text def gen_captcha_text_and_image(): image = ImageCaptcha() captcha_text = random_captcha_text() captcha_text = ''.join(captcha_text) captcha = image.generate(captcha_text) captcha_image = Image.open(captcha) captcha_image = np.array(captcha_image) return captcha_text, captcha_image def convert2gray(img): if len(img.shape) > 2: gray = np.mean(img, -1) # 上面的转法较快,正规转法如下 # r, g, b = img[:,:,0], img[:,:,1], img[:,:,2] # gray = 0.2989 * r + 0.5870 * g + 0.1140 * b return gray else: return img def text2vec(text): text_len = len(text) if text_len > MAX_CAPTCHA: raise ValueError('验证码最长4个字符') vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN) for i, c in enumerate(text): idx = i * CHAR_SET_LEN + int(c) vector[idx] = 1 return vector # 向量转回文本 def vec2text(vec): text = [] char_pos = vec.nonzero()[0]# nunzero函数是找出矩阵中非零元素的位置,返回一个元组,每个元素为列表,前一个列表存放非零行坐标,后一个列表存放非零元素列坐标 for i, c in enumerate(char_pos): number = i % 10 text.append(str(number)) return "".join(text) # 生成一个训练batch def get_next_batch(batch_size=128): batch_x = np.zeros([batch_size, IMAGE_HEIGHT * IMAGE_WIDTH]) batch_y = np.zeros([batch_size, MAX_CAPTCHA * CHAR_SET_LEN]) # 有时生成图像大小不是(60, 160, 3) def wrap_gen_captcha_text_and_image(): while True: text, image = gen_captcha_text_and_image() if image.shape == (60, 160, 3): return text, image for i in range(batch_size): text, image = wrap_gen_captcha_text_and_image() image = convert2gray(image) batch_x[i, :] = image.flatten() / 255 # (image.flatten()-128)/128 mean为0 batch_y[i, :] = text2vec(text) return batch_x, batch_y # 定义CNN def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1): x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1]) # 3 conv layer w_c1 = tf.Variable(w_alpha * tf.random_normal([3, 3, 1, 32]))#卷积核的参数3x3,深度为1(灰度),32个filter生成32个特征图 b_c1 = tf.Variable(b_alpha * tf.random_normal([32])) conv1 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(x, w_c1, strides=[1, 1, 1, 1], padding='SAME'), b_c1)) conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') conv1 = tf.nn.dropout(conv1, keep_prob) w_c2 = tf.Variable(w_alpha * tf.random_normal([3, 3, 32, 64])) b_c2 = tf.Variable(b_alpha * tf.random_normal([64])) conv2 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv1, w_c2, strides=[1, 1, 1, 1], padding='SAME'), b_c2)) conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') conv2 = tf.nn.dropout(conv2, keep_prob) w_c3 = tf.Variable(w_alpha * tf.random_normal([3, 3, 64, 64])) b_c3 = tf.Variable(b_alpha * tf.random_normal([64])) conv3 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv2, w_c3, strides=[1, 1, 1, 1], padding='SAME'), b_c3)) conv3 = tf.nn.max_pool(conv3, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') conv3 = tf.nn.dropout(conv3, keep_prob) # Fully connected layer w_d = tf.Variable(w_alpha * tf.random_normal([8 * 20 * 64, 1024])) b_d = tf.Variable(b_alpha * tf.random_normal([1024])) dense = tf.reshape(conv3, [-1, w_d.get_shape().as_list()[0]]) dense = tf.nn.relu(tf.add(tf.matmul(dense, w_d), b_d)) dense = tf.nn.dropout(dense, keep_prob) w_out = tf.Variable(w_alpha * tf.random_normal([1024, MAX_CAPTCHA * CHAR_SET_LEN])) b_out = tf.Variable(b_alpha * tf.random_normal([MAX_CAPTCHA * CHAR_SET_LEN])) out = tf.add(tf.matmul(dense, w_out), b_out) return out # 训练 def train_crack_captcha_cnn(): output = crack_captcha_cnn() loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y)) optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss) predict = tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]) max_idx_p = tf.argmax(predict, 2) max_idx_l = tf.argmax(tf.reshape(Y, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2) correct_pred = tf.equal(max_idx_p, max_idx_l) accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) saver = tf.train.Saver() with tf.Session() as sess: sess.run(tf.global_variables_initializer()) step = 0 while True: batch_x, batch_y = get_next_batch(64) _, loss_ = sess.run([optimizer, loss], feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.75}) print(step, loss_) # 每100 step计算一次准确率 if step % 10 == 0: batch_x_test, batch_y_test = get_next_batch(100) acc = sess.run(accuracy, feed_dict={X: batch_x_test, Y: batch_y_test, keep_prob: 1.}) print(step, acc) # 如果准确率大于90%,保存模型,完成训练 if acc > 0.90: saver.save(sess, "./model/crack_capcha.model", global_step=step) break step += 1 def crack_captcha(captcha_image): output = crack_captcha_cnn() saver = tf.train.Saver() with tf.Session() as sess: saver.restore(sess, "./model/crack_capcha.model-810") predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2) text_list = sess.run(predict, feed_dict={X: [captcha_image], keep_prob: 1}) text = text_list[0].tolist() return text if __name__ == '__main__': number = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9'] text, image = gen_captcha_text_and_image() print("验证码图像channel:", image.shape) # (60, 160, 3) # 图像大小 IMAGE_HEIGHT = 60 IMAGE_WIDTH = 160 MAX_CAPTCHA = len(text) print("验证码文本最长字符数", MAX_CAPTCHA) char_set = number CHAR_SET_LEN = len(char_set) X = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT * IMAGE_WIDTH]) Y = tf.placeholder(tf.float32, [None, MAX_CAPTCHA * CHAR_SET_LEN]) keep_prob = tf.placeholder(tf.float32) # dropout train_crack_captcha_cnn()

 

2.  测试代码

import numpy as np
import tensorflow as tf
# import tensorflow.compat.v1 as tf
# tf.disable_v2_behavior()
from captcha.image import ImageCaptcha
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
import random
import cv2
number = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']


def random_captcha_text(char_set=number, captcha_size=4):
    captcha_text = []
    for i in range(captcha_size):
        c = random.choice(char_set)
        captcha_text.append(c)
    return captcha_text


def gen_captcha_text_and_image():
    image = ImageCaptcha()

    captcha_text = random_captcha_text()
    captcha_text = ''.join(captcha_text)

    captcha = image.generate(captcha_text)
    # image.write(captcha_text, captcha_text + '.jpg')

    captcha_image = Image.open(captcha)
    captcha_image = np.array(captcha_image)
    return captcha_text, captcha_image


def convert2gray(img):
    if len(img.shape) > 2:
        gray = np.mean(img, -1)
        # 上面的转法较快,正规转法如下
        # r, g, b = img[:,:,0], img[:,:,1], img[:,:,2]
        # gray = 0.2989 * r + 0.5870 * g + 0.1140 * b
        return gray
    else:
        return img


def text2vec(text):
    text_len = len(text)
    if text_len > MAX_CAPTCHA:
        raise ValueError('验证码最长4个字符')

    vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)

    for i, c in enumerate(text):
        idx = i * CHAR_SET_LEN + int(c)
        vector[idx] = 1
    return vector


# 向量转回文本
def vec2text(vec):
    text = []
    char_pos = vec.nonzero()[0]# nunzero函数是找出矩阵中非零元素的位置,返回一个元组,每个元素为列表,前一个列表存放非零行坐标,后一个列表存放非零元素列坐标
    for i, c in enumerate(char_pos):
        number = i % 10
        text.append(str(number))

    return "".join(text)

# 定义CNN
def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1):
    x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])
    # 3 conv layer
    w_c1 = tf.Variable(w_alpha * tf.random_normal([3, 3, 1, 32]))#卷积核的参数3x3,深度为1(灰度),32个filter生成32个特征图
    b_c1 = tf.Variable(b_alpha * tf.random_normal([32]))
    conv1 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(x, w_c1, strides=[1, 1, 1, 1], padding='SAME'), b_c1))
    conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    conv1 = tf.nn.dropout(conv1, keep_prob)

    w_c2 = tf.Variable(w_alpha * tf.random_normal([3, 3, 32, 64]))
    b_c2 = tf.Variable(b_alpha * tf.random_normal([64]))
    conv2 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv1, w_c2, strides=[1, 1, 1, 1], padding='SAME'), b_c2))
    conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    conv2 = tf.nn.dropout(conv2, keep_prob)

    w_c3 = tf.Variable(w_alpha * tf.random_normal([3, 3, 64, 64]))
    b_c3 = tf.Variable(b_alpha * tf.random_normal([64]))
    conv3 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(conv2, w_c3, strides=[1, 1, 1, 1], padding='SAME'), b_c3))
    conv3 = tf.nn.max_pool(conv3, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    conv3 = tf.nn.dropout(conv3, keep_prob)

    # Fully connected layer
    w_d = tf.Variable(w_alpha * tf.random_normal([8 * 20 * 64, 1024]))
    b_d = tf.Variable(b_alpha * tf.random_normal([1024]))
    dense = tf.reshape(conv3, [-1, w_d.get_shape().as_list()[0]])
    dense = tf.nn.relu(tf.add(tf.matmul(dense, w_d), b_d))
    dense = tf.nn.dropout(dense, keep_prob)

    w_out = tf.Variable(w_alpha * tf.random_normal([1024, MAX_CAPTCHA * CHAR_SET_LEN]))
    b_out = tf.Variable(b_alpha * tf.random_normal([MAX_CAPTCHA * CHAR_SET_LEN]))
    out = tf.add(tf.matmul(dense, w_out), b_out)
    return out


def crack_captcha(captcha_image):
    output = crack_captcha_cnn()
    saver = tf.train.Saver()
    with tf.Session() as sess:
        saver.restore(sess, "./model/crack_capcha.model-3150")

        predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
        text_list = sess.run(predict, feed_dict={X: [captcha_image], keep_prob: 1})
        text = text_list[0].tolist()
        return text


if __name__ == '__main__':
    # captcha_text, captcha_image = gen_captcha_text_and_image()
    # cv2.imwrite('./images/yzm2.jpg', captcha_image)#先生成几张图片
    image = cv2.imread('./images/yzm.jpg')
    print(image.shape)
    cv2.imshow('yzm', image)
    cv2.waitKey(0)
    number = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
    IMAGE_HEIGHT = 60
    IMAGE_WIDTH = 160
    char_set = number
    CHAR_SET_LEN = len(char_set)
    MAX_CAPTCHA = 4
    image = convert2gray(image)
    image = image.flatten() / 255
    X = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT * IMAGE_WIDTH])
    Y = tf.placeholder(tf.float32, [None, MAX_CAPTCHA * CHAR_SET_LEN])
    keep_prob = tf.placeholder(tf.float32)  # dropout
    predict_text = crack_captcha(image)
    print(predict_text)

 

小结:使用自己的CPU,花费了2个半小时左右,刚开始时,准确率一直为0.1左右浮动,一直以为代码问题,或者模型层数不够,继续等待,直到训练1700次个batch后,准确率才慢慢开始上升。本文未对代码做详细分析,需要工程代码或是训练好的模型可以留言,如果想使用GPU训练模型,自己电脑又没有,可以考虑谷歌的colab,一定时长内可以免费使用GPU、TPU,具体找个视频很容易上手。

 

  不足或错误之处,欢迎评论与指正!

标签:nn,text,模型,random,验证码,captcha,tf,识别,image
From: https://www.cnblogs.com/wancy/p/17439115.html

相关文章

  • [转]基于图像的三维模型重建4——增量SFM
    内容几种BA的形式同时优化相机和三维点优化相机只优化三维点单目相机增量运动恢复结构(IncrementalSFM)运动恢复结构的几个问题几种BA的形式数学模型n个三维点和m个相机,一些三维点在相机上的投影点。i表示三维点的索引,j表示相机的索引。 u 表示观测点, u^ 表示理......
  • 首个大规模使用工具的大模型来了:伯克利发布Gorilla
    前言 OneAItorulethemall.本文转载自机器之心欢迎关注公众号CV技术指南,专注于计算机视觉的技术总结、最新技术跟踪、经典论文解读、CV招聘信息。CV各大方向专栏与各个部署框架最全教程整理【CV技术指南】CV全栈指导班、基础入门班、论文指导班全面上线!!大型语言模型......
  • GPT-4多态大模型研究
    1.概述GPT-4是OpenAI最新的系统,能够产生更安全和更有用的回应。它是一个大型的多模态模型(接受图像和文本输入,输出文本),在各种专业和学术的基准测试中展现了人类水平的表现。例如,它在模拟的律师资格考试中得分位于前10%的考生之列;相比之下,GPT-3.5的得分位于后10%。GPT-4是如何做到......
  • 2023-05-28:为什么Redis单线程模型效率也能那么高?
    2023-05-28:为什么Redis单线程模型效率也能那么高?答案2023-05-28:1.C语言实现,效率高C语言程序运行速度快,因为其相较于其他高级语言更加接近底层机器。由于C语言直接操作内存,不会像其他语言那样依赖虚拟机或垃圾回收机制等中间层,从而能够实现更高的执行效率。2.单线程的优势Redi......
  • 2023-05-28:为什么Redis-单线程模型效率也能那么高?
    2023-05-28:为什么Redis-单线程模型效率也能那么高?答案2023-05-28:1.C语言实现,效率高C语言程序运行速度快,因为其相较于其他高级语言更加接近底层机器。由于C语言直接操作内存,不会像其他语言那样依赖虚拟机或垃圾回收机制等中间层,从而能够实现更高的执行效率。2.单线程的优势Redis采用......
  • 深入理解 Java 虚拟机 —— Java 内存模型与线程
    处理器的效率和一致性(与java内存访问可类比)计算机同时去做几件事情,不仅是因为计算机的运算能力强大了,还有一个很重要的原因是计算机的运算速度与它的存储和通信子系统的速度差距太大,大量的时间都花费在磁盘I/O、网络通信或者数据库访问上。如果不希望处理器在大部分时间里都处......
  • iOS MachineLearning 系列(20)—— 训练生成CoreML模型
    iOSMachineLearning系列(20)——训练生成CoreML模型本系列前面的文章详细的介绍了在iOS中与AI能力相关的API的使用,也介绍了如何使用训练好的CoreML模型来实现更强大的AI能力。然而,无论是成熟的API提供的能力,还是各种各样的三方模型,有时候都并不能满足某一领域内的定制化需求。当我......
  • 前端自动识别CAD图纸提取信息方法总结
    前言CAD图纸自动识别和提取信息具有许多意义,包括以下几个方面:提高工作效率:传统上,对于大量的CAD图纸,人工识别和提取信息是一项耗时且繁琐的任务。通过自动化这一过程,可以大大提高工作效率,节省时间和人力资源。减少错误和精度提升:人工处理CAD图纸容易出现错误,例如错读数字或......
  • 大模型全情投入,低代码也越来越清晰
    众所周知,许多大企业加码其中,甚至不少互联网大佬级人物也在其中全情投入,。那么在这阵阵浪潮中,我们可以观察到什么样的“众生相”?今年3月以来,国内已有超过20家企业入局大模型赛道。从百度“文心一言”、阿里“通义千问”的发布,华为“盘古”等的预告。互联网巨头、科技公司纷纷秀出......
  • 基于移动网络通讯行为的风险用户识别
    访问【WRITE-BUG数字空间】_[内附完整源码和文档]大赛地址:基于移动网络通讯行为的风险用户识别,该比赛是联通大数据公司发起的,同时作为我们的实训的比赛。下面是自己参加比赛过程的报告:第一次参加这种比赛,发现自己经验明显不足。初赛0.787(52/624),复赛0.784(71/624),虽然成绩很差,但是感觉......