tensorflow训练cnn网络识别验证码


          

生成数字验证码图片:

from captcha.image import ImageCaptcha  # pip install captcha  
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']  
#随机生成4个数字的数组
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  
#随机生成4个数字的图片
def gen_captcha_text_and_image():  
    image = ImageCaptcha()  
    captcha_text = random_captcha_text() 
    captcha_text = ''.join(captcha_text) #将数组转成字符串  
    captcha = image.generate(captcha_text)  
    #image.write(captcha_text, captcha_text + '.jpg')  # 写到文件  

    captcha_image = Image.open(captcha)  
    captcha_image = np.array(captcha_image)  
    return captcha_text, captcha_image  
训练网络及测试代码:
from __future__ import print_function

import tensorflow as tf
import numpy as np  
import matplotlib.pyplot as plt  

from check_img import gen_captcha_text_and_image  
from check_img import number  
   
text, image = gen_captcha_text_and_image()  
print("验证码图像channel:", image.shape)  # (60, 160, 3)  

IMAGE_HEIGHT = 60  
IMAGE_WIDTH = 160  
MAX_CAPTCHA = len(text)  
char_set = number + ['_']  # 如果验证码长度小于4, '_'用来补齐  
CHAR_SET_LEN = len(char_set) 

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)  
    def char2pos(c):  
        if c =='_':  
            k = 62  
            return k  
        k = ord(c)-48  
        if k > 9:  
            k = ord(c) - 55  
            if k > 35:  
                k = ord(c) - 61  
                if k > 61:  
                    raise ValueError('No Map')   
        return k  
    for i, c in enumerate(text):  
        idx = i * CHAR_SET_LEN + char2pos(c)  
        vector[idx] = 1  
    return vector 

def vec2text(vec):  
    char_pos = vec.nonzero()[0]  
    text=[]  
    for i, c in enumerate(char_pos):  
        char_at_pos = i #c/63  
        char_idx = c % CHAR_SET_LEN  
        if char_idx < 10:  
            char_code = char_idx + ord('0')  
        elif char_idx <36:  
            char_code = char_idx - 10 + ord('A')  
        elif char_idx < 62:  
            char_code = char_idx-  36 + ord('a')  
        elif char_idx == 62:  
            char_code = ord('_')  
        else:  
            raise ValueError('error')  
        text.append(chr(char_code))  
    return "".join(text)  

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  

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  
   
# 定义卷积神经网络
def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1):  
    x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])  
   
    # 3层卷积网络  
    w_c1 = tf.Variable(w_alpha*tf.random_normal([3, 3, 1, 32]))  
    b_c1 = tf.Variable(b_alpha*tf.random_normal([32]))  
    #下面不去掉激励函数relu就会出现训练准确度在0.1左右变化,不知道为什么别人加上就可以的,
    #而我这里要去掉才正常???
    conv1 = 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.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.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*32*40, 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())  
        
        for step in range(2000):  
            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_)  
            if step % 100 == 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("acc=", acc)  
                if acc > 0.9:  
                    saver.save(sess, "crack_capcha.model", global_step=step) 

train_crack_captcha_cnn() 

#测试
def crack_captcha_test():  
    output = crack_captcha_cnn()  
   
    saver = tf.train.Saver()  
    with tf.Session() as sess:  
        saver.restore(sess, tf.train.latest_checkpoint('.'))
        predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
        count = 0
        all_count = 100
        for i in range(all_count):
            text, image = gen_captcha_text_and_image()
            gray_image = convert2gray(image)
            captcha_image = gray_image.flatten() / 255

            text_list = sess.run(predict, feed_dict={X: [captcha_image], keep_prob: 1})  
            predict_text = text_list[0].tolist() 
            predict_text = str(predict_text)
            predict_text = predict_text.replace("[", "").replace("]", "").replace(",", "").replace(" ","")
            if text == predict_text:
                count += 1
                check_result = ",预测结果正确"
            else:
                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()  
                check_result = ",预测结果不正确"
            print("正确: {}  预测: {}".format(text, predict_text) + check_result)
        print("正确率:" , count, "/", all_count)
        
crack_captcha_test()
结果: