tensorflow 验证码识别

搞学习深度学习，我第一个做的小项目就是这个 ，验证码识别，前前后后花了一个多月的时间，还是很菜，下面是我的成果，大部分代码是自己写的，部分借鉴了别人的。然后分享一点我的经验，训练的时候要有耐心，只要损失值在变小，或者在波动（但准确率却没多大变化），就说明大致的方向没有错，坚持等下去，我这个是在训练到3000多次的时候，损失值发生了突变，走上正轨了。

训练代码：

import numpy as np
import tensorflow as tf
from captcha.image import ImageCaptcha
import matplotlib.pyplot as plt
import os
import random
from PIL import Image
print(3)
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):
        c=random.choice(char_set)
        captcha_text.append(c)
    return captcha_text
def gen_captcha_text_and_image():
#     while(1):
        image=ImageCaptcha()
        captcha_text=random_captcha_text()
        captcha_text=''.join(captcha_text)
        captcha_image=image.generate(captcha_text)
        captcha_image=Image.open(captcha_image)
        
        captcha_image=np.array(captcha_image)
        
#         if captcha_image.shape==(60,160,30):
#             break
        return captcha_text,captcha_image

text,image=gen_captcha_text_and_image()
IMAGE_HEIGHT =60
IMAGE_WIDTH = 160
MAX_CAPTCHA =len(text)
char_set =number+alphabet+ALPHABET+['_']
CHAR_SET_LEN = len(char_set)
print(CHAR_SET_LEN)
print("验证码文本最长字符数",MAX_CAPTCHA)


def convert2gray(img):
    if len(img.shape)>2:
        gray =np.mean(img,-1)
#         print(gray)
        return gray
    else:
        return img

print ()
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 
        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])
                                                
    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
        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)

def crack_captcha_cnn(w_alpha=0.01,b_alpha=0.1):
    x=tf.reshape(X,shape=[-1,IMAGE_HEIGHT,IMAGE_WIDTH,1])
    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)
    
    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

    
def train_crack_captcha_cnn():
    import time
    start_time=time.time()
    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 (time.strftime('%Y-%m-%d %H: %M: %S',time.localtime(time.time())),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("*********第{}次的准确率为{}*****".format(step,acc))
                if acc>0.9:
                    saver.save(sess,"./model/crack_captcha.model",global_step=step)
                    print(time.time()-start_time)
                    break
            
            step +=1
train_crack_captcha_cnn()