tensorflow cnn 验证码

tensorflow cnn 验证码

​​1.config.py​​

NUMBER = '0123456789'CHAR_SMALL = 'abcdefghijklmnopqrstuvwxyz'CHAR_BIG = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'MAX_CAPTCHA = 6 # 测试1位的训练准确率VALIDATE_STRING = NUMBER + CHAR_SMALL # + CHAR_BIGCHAR_SET_LEN = len(VALIDATE_STRING) # 数字字母总长度，即所有可能的选项的数量IMAGE_HEIGHT = 60IMAGE_WIDTH = 160FONT_SIZE = 35MAX_ACCURACY = 0.9

2.gen_image.py

from captcha.image import ImageCaptchaimport numpy as npimport matplotlib.pyplot as plt# from config import NUMBER, CHAR_SMALL, CHAR_BIG, MAX_CAPTCHA, CHAR_SET_LEN, FONT_SIZEimport src.config as configfrom PIL import Imageimport randomchar_dict = {}number_dict = {}# 生成随机的指定的字符串def __gen_random_captcha_text(char_set=config.VALIDATE_STRING, size=None): # char_set must be a str if not char_set or not isinstance(char_set, str): raise ValueError('get the empty char_set') # 随机 result = list(char_set) random.shuffle(result) # 返回字符串 return ''.join(result[0:size])def gen_random_captcha_image(): image = ImageCaptcha(width=config.IMAGE_WIDTH, height=config.IMAGE_HEIGHT,font_sizes=[config.FONT_SIZE]) text = __gen_random_captcha_text(size=config.MAX_CAPTCHA) captcha = image.generate(text) captcha_image = Image.open(captcha) captcha_source = np.array(captcha_image) return text, captcha_source# always gen the require image height ,and width imagedef gen_require_captcha_image(): while 1: text, image = gen_random_captcha_image() if image.shape == (config.IMAGE_HEIGHT, config.IMAGE_WIDTH, 3): return text, image# 把彩色图像转为灰度图像（色彩对识别验证码没有什么用,对于抽取特征也没啥用）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# prepare the char to indexdef prepare_char_dict(): if char_dict: return char_dict for index, val in enumerate(config.VALIDATE_STRING): char_dict[val] = index return char_dictdef prepare_number_dict(): if number_dict: return number_dict for index, val in enumerate(config.VALIDATE_STRING): number_dict[index] = val return number_dictdef text_to_array(text): char_dict_tmp = prepare_char_dict() arr = np.zeros(config.MAX_CAPTCHA * config.CHAR_SET_LEN, dtype=np.int8) for i, p in enumerate(text): key_index = char_dict_tmp[p] index = i * config.CHAR_SET_LEN + key_index arr[index] = 1 return arrdef array_to_text(arr): num_dict_tmp = prepare_number_dict() text = [] char_pos = arr.nonzero()[0] for index, val in enumerate(char_pos): if index == 0: index = 1 key_index = val % (index * config.CHAR_SET_LEN) text.append(num_dict_tmp[key_index]) return ''.join(text)def show_image_text(): text, image = gen_random_captcha_image() f = plt.figure() ax = f.add_subplot(111) ax.text(0.1, 0.9, text, ha='center', va='center', transform=ax.transAxes) plt.imshow(image) plt.show()#if __name__ == '__main__': # __do_image_text() # arr = text_to_array('0142') # print '===========' # print array_to_text(arr) show_image_text()

3.gen_model.py

import tensorflow as tfimport numpy as npfrom src.gen_image import text_to_arrayfrom src.config import MAX_CAPTCHA, CHAR_SET_LEN, IMAGE_HEIGHT, IMAGE_WIDTH, MAX_ACCURACYfrom src.gen_image import gen_require_captcha_imagex_input = tf.placeholder(tf.float32, [None, IMAGE_HEIGHT * IMAGE_WIDTH])y_input = tf.placeholder(tf.float32, [None, CHAR_SET_LEN * MAX_CAPTCHA])keep_prob = tf.placeholder(tf.float32)# 把彩色图像转为灰度图像（色彩对识别验证码没有什么用,对于抽取特征也没啥用）def convert2gray(img): if len(img.shape) > 2: gray = np.mean(img, -1) return gray else: return imgdef __weight_variable(shape, stddev=0.01): initial = tf.random_normal(shape, stddev=stddev) return tf.Variable(initial)def __bias_variable(shape, stddev=0.1): initial = tf.random_normal(shape=shape, stddev=stddev) return tf.Variable(initial)def __conv2d(x, w): # strides 代表移动的平长 return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='SAME')def __max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')# 100个一个批次def gen_next_batch(batch_size=100): batch_x = np.zeros([batch_size, IMAGE_HEIGHT * IMAGE_WIDTH]) batch_y = np.zeros([batch_size, MAX_CAPTCHA * CHAR_SET_LEN]) for i in range(batch_size): text, image = gen_require_captcha_image() # 转成灰度图片，因为颜色对于提取字符形状是没有意义的 image = convert2gray(image) batch_x[i, :] = image.flatten() / 255 batch_y[i, :] = text_to_array(text) return batch_x, batch_ydef create_layer(x_input, keep_prob): x_image = tf.reshape(x_input, shape=[-1, IMAGE_WIDTH, IMAGE_HEIGHT, 1]) # 定义第1个卷积层 w_c1 = __weight_variable([5, 5, 1, 32], stddev=0.1) # 3x3 第一层32个卷积核 采用黑白色 b_c1 = __bias_variable([32], stddev=0.1) h_c1 = tf.nn.relu(tf.nn.bias_add(__conv2d(x_image, w_c1), b_c1)) # 定义第一个卷积层 h_pool1 = __max_pool_2x2(h_c1) # 定义第一个池化层 # h_pool1 = tf.nn.dropout(h_pool1, keep_prob) # 定义第2个卷积层 w_c2 = __weight_variable([5, 5, 32, 64], stddev=0.1) b_c2 = __bias_variable([64], stddev=0.1) h_c2 = tf.nn.relu(tf.nn.bias_add(__conv2d(h_pool1, w_c2), b_c2)) h_pool2 = __max_pool_2x2(h_c2) # h_pool2 = tf.nn.dropout(h_pool2, keep_prob) # 定义第3个卷积层 w_c3 = __weight_variable([5, 5, 64, 64], stddev=0.1) b_c3 = __bias_variable([64], stddev=0.1) h_c3 = tf.nn.relu(tf.nn.bias_add(__conv2d(h_pool2, w_c3), b_c3)) h_pool3 = __max_pool_2x2(h_c3) # h_pool3 = tf.nn.dropout(h_pool3, keep_prob) # 3层池化之后 width 144 / 8 = 18 # height 64 / 8 = 8 # 全链接层1 w_fc1 = __weight_variable([20 * 8 * 64, 1024], stddev=0.1) b_fc1 = __bias_variable([1024]) h_pool3_flat = tf.reshape(h_pool3, [-1, w_fc1.get_shape().as_list()[0]]) h_fc1 = tf.nn.relu(tf.add(tf.matmul(h_pool3_flat, w_fc1), b_fc1)) # drop out 内容0 h_fc1_dropout = tf.nn.dropout(h_fc1, keep_prob) # 全链接层2 w_output = __weight_variable([1024, MAX_CAPTCHA * CHAR_SET_LEN], stddev=0.1) b_output = __bias_variable([MAX_CAPTCHA * CHAR_SET_LEN]) y_output = tf.add(tf.matmul(h_fc1_dropout, w_output), b_output) return y_output# 计算loss的典型方法def create_loss(layer, y_input): loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y_input, logits=layer)) return loss# 计算accuracy的典型方法def create_accuracy(output, y_input): 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_input, [-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)) return accuracydef train(): # create the layer and loss layer_output = create_layer(x_input, keep_prob) loss = create_loss(layer_output, y_input) accuracy = create_accuracy(layer_output, y_input) global_step_tensor=tf.Variable(0,trainable="Flase",name="global_step") train_step = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss,global_step=global_step_tensor) # save model saver = tf.train.Saver() with tf.Session() as sess: tf.global_variables_initializer().run() acc = 0.0 i = 0 while acc < MAX_ACCURACY: i += 1 batch_x, batch_y = gen_next_batch(64) _, _loss = sess.run([train_step, loss], feed_dict={x_input: batch_x, y_input: batch_y, keep_prob: 0.5}) # 每20次输出loss # tf.train.global_step(sess,global_step_tensor)等于i if i % 20 == 0: print(tf.train.global_step(sess,global_step_tensor), _loss) # 每100 step计算一次准确率并保存模型 if i % 100 == 0: batch_x_test, batch_y_test = gen_next_batch(100) acc = sess.run(accuracy, feed_dict={x_input: batch_x_test, y_input: batch_y_test, keep_prob: 1.0}) print('step is %s' % i, 'and accy is %s' % acc) # 保存模型 saver.save(sess,"model/break.ckpt",global_step=i) # 如果准确率大于50%,完成训练 if acc > MAX_ACCURACY: print('current accuracy > %s ,stop now' % MAX_ACCURACY) breakif __name__ == '__main__': train()

4. ​​validate.py​​

from src.gen_model import create_layerimport tensorflow as tfimport src.config as configimport numpy as npfrom src.gen_image import convert2gray, gen_random_captcha_image, array_to_textdef crack_captcha(captcha_image): x_input = tf.placeholder(tf.float32, [None, config.IMAGE_HEIGHT * config.IMAGE_WIDTH]) keep_prob = tf.placeholder(tf.float32) # dropout output = create_layer(x_input, keep_prob) saver = tf.train.Saver() with tf.Session() as sess: saver.restore(sess, tf.train.latest_checkpoint('.')) predict = tf.argmax(tf.reshape(output, [-1, config.MAX_CAPTCHA, config.CHAR_SET_LEN]), 2) text_list = sess.run(predict, feed_dict={x_input: [captcha_image], keep_prob: 1}) text = text_list[0].tolist() vector = np.zeros(config.MAX_CAPTCHA * config.CHAR_SET_LEN) i = 0 for n in text: vector[i * config.CHAR_SET_LEN + n] = 1 i += 1 return array_to_text(vector)def validate_image(): text, image = gen_random_captcha_image() image = convert2gray(image) # map the value to 0 -> 1 ，this will really affect the loss function update ,always remember the value should # suit to the loss learning rate # refer 21:00 image = image.flatten() / 255 predict_text = crack_captcha(image) print("label is : {} <----> predict is : {}".format(text, predict_text))if __name__ == '__main__': validate_image()https://github.com/nanfengpo/crack_captcha

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。