验证码进阶（TensorFlow--基于卷积神经网络的验证码识别）

本人的第一个深度学习实战项目，参考了网络上诸多牛人的代码，在此谢过，因时间久已，不记出处，就不一一列出，罪过罪过。

我的数据集是我用脚本在网页上扒的，标签是用之前写的验证码识别方法打的。大概用了4000+多张图训练。

我的数据集都经过处理了，降噪，二值化，最后裁剪为18*60的大小，详细见我之前的验证码简单识别那篇随笔。

#coding:utf-8
import tensorflow as tf
from PIL import Image
import os
import random
import numpy as np

img_height = 18
img_width = 60
max_captcha = 4   #验证码长度
char_len =63　　　　#用63个二进制数表示一个字符

def get_name_image():
    all_image = os.listdir('D:\sctest')
    random_file = random.randint(0,4000)
    base = os.path.basename('D:\sctest\\' + all_image[random_file])
    name = os.path.splitext(base)[0]
    image = Image.open('D:\sctest\\' + all_image[random_file])
    image = np.array(image)
    return name,image、
#我的标签就是图片名
#标签转成向量
def name2vec(name):
    vector = np.zeros(max_captcha*char_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(name):
        idx = i * char_len + char2pos(c)
        vector[idx] = 1
    return vector
#将向量装成名字，也就是输出结果，最后预测的时候用到
def vec2name(vec):
    name = []
    for i, c in enumerate(vec):
        char_idx = c % char_len
        if char_idx < 10:
            char_code = char_idx + ord('')
        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')
        name.append(chr(char_code))
    return "".join(name)

def get_next_batch(batch_size=64):
    batch_x = np.zeros([batch_size, img_height*img_width])
    batch_y = np.zeros([batch_size, max_captcha*char_len])

    for i in range(batch_size):
        name, image = get_name_image()
        batch_x[i, :] = 1*(image.flatten())
        batch_y[i, :] = name2vec(name)
    return batch_x, batch_y
X = tf.placeholder(tf.float32,[None,img_width*img_height])
Y = tf.placeholder(tf.float32,[None,max_captcha*char_len])
keep_prob = tf.placeholder(tf.float32)

#CNN
def crack_captcha_cnn(w_alpha=0.01,b_alpha=0.1):
    x = tf.reshape(X, shape=[-1, img_height, img_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([3 * 8 * 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_len]))
    b_out = tf.Variable(b_alpha * tf.random_normal([max_captcha * char_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_len])
    max_idx_p = tf.argmax(predict, 2)
    max_idx_l = tf.argmax(tf.reshape(Y, [-1, max_captcha, char_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: 0.5})
            print(step, loss_)

            # 每100 step计算一次准确率
            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(step, acc)
                # acc大于0.9999保存模型退出
                if acc > 0.9999:
                    saver.save(sess, "./crack_capcha.model", global_step=step)
                    break

            step += 1
train_crack_captcha_cnn()

#训练完成后注释掉train_crack_captcha_cnn()方法，跑下面的预测方法，进行预测。
def crack_captcha():
    output = crack_captcha_cnn()

    saver = tf.train.Saver()
    with tf.Session() as sess:
        saver.restore(sess, tf.train.latest_checkpoint('.'))
        n = 1
        while n <= 100:
            name, image = get_name_image()
            image = 1 * (image.flatten())
            predict = tf.argmax(tf.reshape(output, [-1, max_captcha, char_len]), 2)
            name_list = sess.run(predict, feed_dict={X: [image], keep_prob: 1})
            vec = name_list[0].tolist()
            predict_text = vec2name(vec)
            print("正确: {}  预测: {}".format(name, predict_text))
            n += 1

crack_captcha()

跑了2800步，acc为1，又用1000多张图进行测试，有一张G，C识别错误。准确率在99.9%以上。