深度学习基于TF破解验证码
来源:互联网 发布:web java开发就业前景 编辑:程序博客网 时间:2024/06/09 22:58
前言
学习腾讯的开发者课程以后,感觉很不错,记录一下,验证码主要用于防刷,传统的验证码识别算法一般需要把验证码分割为单个字符,然后逐个识别,如果字符之间相互重叠,传统的算法就然并卵了,本文采用cnn对验证码进行整体识别。通过本文的学习,大家可以学到几点:1.captcha库生成验证码;2.如何将验证码识别问题转化为分类问题;3.可以训练自己的验证码识别模型。
步骤
- prepare_data.py - 验证码生成,使用python库captcha来生成,速度快,数量多
- prepare_model.py - 两层RNN网络模型,采用LSTM模型;
- train.py - 训练CNN模型(3 层隐藏层、2 层全连接层)
- predict.py - 使用图片进行预测
生成数据
安装 captcha 库
captcha 可以生成语音和图片验证码,我们采用生成图片验证码功能,验证码是由数字、大写字母、小写字母组成(当然你也可以根据自己的需求调整,比如添加一些特殊字符),长度为 4,所以总共有 62^4 种组合验证码,没有的自行安装
sudo pip install captcha
下面是生成验证码的代码:
#!/usr/bin/python# -*- coding: utf-8 -*from captcha.image import ImageCaptchafrom PIL import Imageimport numpy as npimport randomimport stringclass generateCaptcha(): def __init__(self, width = 160,#验证码图片的宽 height = 60,#验证码图片的高 char_num = 4,#验证码字符个数 characters = string.digits + string.ascii_uppercase + string.ascii_lowercase):#验证码组成,数字+大写字母+小写字母 self.width = width self.height = height self.char_num = char_num self.characters = characters self.classes = len(characters) def gen_captcha(self,batch_size = 50): X = np.zeros([batch_size,self.height,self.width,1]) img = np.zeros((self.height,self.width),dtype=np.uint8) Y = np.zeros([batch_size,self.char_num,self.classes]) image = ImageCaptcha(width = self.width,height = self.height) while True: for i in range(batch_size): captcha_str = ''.join(random.sample(self.characters,self.char_num)) img = image.generate_image(captcha_str).convert('L') img = np.array(img.getdata()) X[i] = np.reshape(img,[self.height,self.width,1])/255.0 for j,ch in enumerate(captcha_str): Y[i,j,self.characters.find(ch)] = 1 Y = np.reshape(Y,(batch_size,self.char_num*self.classes)) yield X,Y def decode_captcha(self,y): y = np.reshape(y,(len(y),self.char_num,self.classes)) return ''.join(self.characters[x] for x in np.argmax(y,axis = 2)[0,:]) def get_parameter(self): return self.width,self.height,self.char_num,self.characters,self.classes def gen_test_captcha(self): image = ImageCaptcha(width = self.width,height = self.height) captcha_str = ''.join(random.sample(self.characters,self.char_num)) img = image.generate_image(captcha_str) img.save(captcha_str + '.jpg')
准备模型
对每层都进行 dropout。input——>conv——>pool——>dropout——>conv——>pool——>dropout——>conv——>pool——>dropout——>fully connected layer——>dropout——>fully connected layer——>output ,所有对图片处理都需要这些步骤,只是层数不同而已。
#!/usr/bin/python# -*- coding: utf-8 -*import tensorflow as tfimport mathclass captchaModel(): def __init__(self, width = 160, height = 60, char_num = 4, classes = 62): self.width = width self.height = height self.char_num = char_num self.classes = classes def conv2d(self,x, W): return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') def max_pool_2x2(self,x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') def weight_variable(self,shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) def bias_variable(self,shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial) def create_model(self,x_images,keep_prob): #first layer w_conv1 = self.weight_variable([5, 5, 1, 32]) b_conv1 = self.bias_variable([32]) h_conv1 = tf.nn.relu(tf.nn.bias_add(self.conv2d(x_images, w_conv1), b_conv1)) h_pool1 = self.max_pool_2x2(h_conv1) h_dropout1 = tf.nn.dropout(h_pool1,keep_prob) conv_width = math.ceil(self.width/2) conv_height = math.ceil(self.height/2) #second layer w_conv2 = self.weight_variable([5, 5, 32, 64]) b_conv2 = self.bias_variable([64]) h_conv2 = tf.nn.relu(tf.nn.bias_add(self.conv2d(h_dropout1, w_conv2), b_conv2)) h_pool2 = self.max_pool_2x2(h_conv2) h_dropout2 = tf.nn.dropout(h_pool2,keep_prob) conv_width = math.ceil(conv_width/2) conv_height = math.ceil(conv_height/2) #third layer w_conv3 = self.weight_variable([5, 5, 64, 64]) b_conv3 = self.bias_variable([64]) h_conv3 = tf.nn.relu(tf.nn.bias_add(self.conv2d(h_dropout2, w_conv3), b_conv3)) h_pool3 = self.max_pool_2x2(h_conv3) h_dropout3 = tf.nn.dropout(h_pool3,keep_prob) conv_width = math.ceil(conv_width/2) conv_height = math.ceil(conv_height/2) #first fully layer conv_width = int(conv_width) conv_height = int(conv_height) w_fc1 = self.weight_variable([64*conv_width*conv_height,1024]) b_fc1 = self.bias_variable([1024]) h_dropout3_flat = tf.reshape(h_dropout3,[-1,64*conv_width*conv_height]) h_fc1 = tf.nn.relu(tf.nn.bias_add(tf.matmul(h_dropout3_flat, w_fc1), b_fc1)) h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) #second fully layer w_fc2 = self.weight_variable([1024,self.char_num*self.classes]) b_fc2 = self.bias_variable([self.char_num*self.classes]) y_conv = tf.add(tf.matmul(h_fc1_drop, w_fc2), b_fc2) return y_conv
定义好模型和数据后,下面开始训练
训练
每批次采用 64 个训练样本,每 100 次循环采用 100 个测试样本检查识别准确度,当准确度大于 99% 时,训练结束,采用 GPU 需要 5-6 个小时左右,CPU 大概需要 20 个小时左右
—-来自腾讯大大
#!/usr/bin/pythonimport tensorflow as tfimport numpy as npimport stringimport generate_captchaimport captcha_modelif __name__ == '__main__': captcha = generate_captcha.generateCaptcha() width,height,char_num,characters,classes = captcha.get_parameter() x = tf.placeholder(tf.float32, [None, height,width,1]) y_ = tf.placeholder(tf.float32, [None, char_num*classes]) keep_prob = tf.placeholder(tf.float32) model = captcha_model.captchaModel(width,height,char_num,classes) y_conv = model.create_model(x,keep_prob) cross_entropy = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y_,logits=y_conv)) train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) predict = tf.reshape(y_conv, [-1,char_num, classes]) real = tf.reshape(y_,[-1,char_num, classes]) correct_prediction = tf.equal(tf.argmax(predict,2), tf.argmax(real,2)) correct_prediction = tf.cast(correct_prediction, tf.float32) accuracy = tf.reduce_mean(correct_prediction) saver = tf.train.Saver() with tf.Session() as sess: sess.run(tf.global_variables_initializer()) step = 0 while True: batch_x,batch_y = next(captcha.gen_captcha(64)) _,loss = sess.run([train_step,cross_entropy],feed_dict={x: batch_x, y_: batch_y, keep_prob: 0.75}) print ('step:%d,loss:%f' % (step,loss)) if step % 100 == 0: batch_x_test,batch_y_test = next(captcha.gen_captcha(100)) acc = sess.run(accuracy, feed_dict={x: batch_x_test, y_: batch_y_test, keep_prob: 1.}) print ('###############################################step:%d,accuracy:%f' % (step,acc)) if acc > 0.99: saver.save(sess,"capcha_model.ckpt") break step += 1
题外话
免训练的快速通道:
wget http://tensorflow-1253902462.cosgz.myqcloud.com/captcha/capcha_model.zipunzip capcha_model.zip
预测
鸡冻人心的时刻来了
#!/usr/bin/pythonfrom PIL import Image, ImageFilterimport tensorflow as tfimport numpy as npimport stringimport sysimport generate_captchaimport captcha_modelif __name__ == '__main__': captcha = generate_captcha.generateCaptcha() width,height,char_num,characters,classes = captcha.get_parameter() gray_image = Image.open(sys.argv[1]).convert('L') img = np.array(gray_image.getdata()) test_x = np.reshape(img,[height,width,1])/255.0 x = tf.placeholder(tf.float32, [None, height,width,1]) keep_prob = tf.placeholder(tf.float32) model = captcha_model.captchaModel(width,height,char_num,classes) y_conv = model.create_model(x,keep_prob) predict = tf.argmax(tf.reshape(y_conv, [-1,char_num, classes]),2) init_op = tf.global_variables_initializer() saver = tf.train.Saver() gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95) with tf.Session(config=tf.ConfigProto(log_device_placement=False,gpu_options=gpu_options)) as sess: sess.run(init_op) saver.restore(sess, "capcha_model.ckpt") pre_list = sess.run(predict,feed_dict={x: [test_x], keep_prob: 1}) for i in pre_list: s = '' for j in i: s += characters[j] print s
运行如下:
“`
python predict_captcha.py Tc0m.jpg
如果没有测试图片,使用prepare_data下的gen_test_captcha()方法即可生成一张。
所有代码托管于:https://github.com/tengxing/tensorflow-learn/captcha 欢迎start!
- 深度学习基于TF破解验证码
- TensorFlow学习之深度学习破解验证码
- TensorFlow20: 使用深度学习破解字符验证码
- TensorFlow练习20: 使用深度学习破解字符验证码
- TensorFlow使用深度学习破解字符验证码
- 基于深度学习的验证码自动识别(caffe)
- 基于深度学习的验证码自动识别(caffe)
- 腾讯云开发者实验室——深度学习破解验证码
- 基于TensorFlow的字符验证码破解
- 深度学习识别 验证码
- 深度学习训练验证码
- 深度学习—caffe—验证码
- 使用tensorflow深度学习识别验证码
- 深度学习caffe实战验证码识别
- 使用tensorflow深度学习识别验证码
- 学习笔记TF042:TF.Learn、分布式Estimator、深度学习Estimator
- 第一次破解验证码
- 验证码破解
- 20.子菜单的使用
- 26.Nginx HTTP之ngx_http_block
- htmlhintrc
- git使用方法
- 时间戳工具类
- 深度学习基于TF破解验证码
- selenium+python测试全部用例
- ubuntu 16.04 配置国内快速软件源
- mongodb常用命令
- UGUI中的文本添加链接下划线并跳转
- python Threading线程关键点
- Reactor server 服务器模式的初步了解
- hibernate中@column自定义字段名无效错误解决
- eslint