Tensorflow实战(三)：验证码识别

做的项目多了才渐渐的发现对于一类问题的解决方案过程都是相似的，所以在本文仅仅记录了验证码识别的流程，对于原理性的问题并没有过多介绍，但是代码中配有详尽的注释。再有，这样分块记录的一个好处是在做其他项目时如果遇到相似的问题，可以直接调用该函数块。

首先我先介绍一下在训练过程中需要的两个bug以及解决方案：
1、GPU显存被占用

解决方案：

# 找到占用GPU的进程
nvidia-smi -q
# 杀死进程
kill -p XXXXX

２、显存不足

解决方案：减小batch或者减小图片尺寸。
３、GPU分配问题
解决

一.制作验证码数据集

• 导入包

import numpy as np  
import tensorflow as tf
from captcha.image import ImageCaptcha
import numpy as np  
import matplotlib.pyplot as plt  
from PIL import Image  
import random  

• 生成四个字符的list

number = ['0','1','2','3','4','5','6','7','8','9']  
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+alphabet+ALPHABET, captcha_size=4):  
    captcha_text = []  
    for i in range(captcha_size):  
    　# 随机选择一个字符
        c = random.choice(char_set)  
        captcha_text.append(c)  
    return captcha_text  

• 生成字符串和验证码

def gen_captcha_text_and_image():  
    image = ImageCaptcha()  
   #将list转化成str
    captcha_text = random_captcha_text()  
    captcha_text = ''.join(captcha_text)  
   #生成验证码
    captcha = image.generate(captcha_text)  
    #image.write(captcha_text, captcha_text + '.jpg')   
   #将image转换成net的input格式
    captcha_image = Image.open(captcha)  
    captcha_image = np.array(captcha_image)  
    return captcha_text, captcha_image  

• 生成一个训练batch
  在生成一个训练batch过程中，我们需要将输入image 进行灰度化和归一化，以便网络更容易训练，并将标签制作成一个列向量。

#图片的灰度化
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  

#将text转换成vecter
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  

#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  

二.定义一个３层卷积层两层全连接层的的网络

def crack_captcha_cnn(w_alpha=0.01, b_alpha=0.1):  
    x = tf.reshape(X, shape=[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 1])  
    
    # 3 conv layer  
    w_c1 = tf.Variable(w_alpha*tf.random_normal([3, 3, 1, 32]))  
    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 

三.构建训练函数

def train_crack_captcha_cnn():  
    #通过网络得到输出
    output = crack_captcha_cnn()  
    #计算损失函数
    loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(output, Y))  
    #定义优化器
    optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)  
    #计算精度值
    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50%,保存模型,完成训练  
                if acc > 0.50:  
                　#global_step表示第几步保存的模型
                    saver.save(sess, "./model/crack_capcha.model", global_step=step)  
                    break  
   
            step += 1  

四.开始训练网络

train = 1
    if train == 0:
        number = ['0','1','2','3','4','5','6','7','8','9']  
        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']
        
        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)
        # 文本转向量  
        #char_set = number + alphabet + ALPHABET + ['_']  # 如果验证码长度小于4, '_'用来补齐  
        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()

模型训练得到的参数：

五.构建预测函数

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 

六.开始预测

if train == 1:
        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)
       
        text, image = gen_captcha_text_and_image()  
         
        f = plt.figure()  
        #定义文本标注位置
        ax = f.add_subplot(111)  
        #添加文本
        ax.text(0.1, 0.9,text, ha='center', va='center', transform=ax.transAxes)  
        plt.imshow(image)  
       
        plt.show()  
        
        MAX_CAPTCHA = len(text)
        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("正确: {}  预测: {}".format(text, predict_text))