0x001 深度学习基础
由于本文只是简单做一下验证码的介绍 并不会过多深入讲述深度学习。只是简单概括一下 深度学习需要做的事情。总体来讲，深度学习的4个步骤
- 采样，制作样本文件
- 根据样本文件类型创建识别模型
- 对样本文件分为训练样本和测试样本来训练识别模型
- 保存识别模型和验证
- 下面按照上面四个历程来尝试 编写自用的验证码模型。
- 本文大多数代码来自于 腾讯开发者实验室
0x002 采样，制作样本文件
样本文件的来源有2种。
- 有生产验证码的代码 ，可以自己生成，例如众多的开源软件
- 人工采集，自行打码（最少最少需要200-300张左右）
为了快速验证结果，先直接使用ImageCaptcha 来生成验证码图案来识别 。
需要安装 captcha 库sudo pip install captcha
#!/usr/bin/python
# -*- coding: utf-8 -*
from captcha.image import ImageCaptcha
from PIL import Image
import numpy as np
import random
import string
class generateCaptcha():
def __init__(self,
width = 160,#验证码图片的宽
height = 60,#验证码图片的高
char_num = 4,#验证码字符个数
characters = string.digits + string.ascii_uppercase + string.ascii_lowercase):#验证码组成，数字+大写字母+小写字母
self.width = width
self.height = height
self.char_num = char_num
self.characters = characters
self.classes = len(characters)
def gen_captcha(self,batch_size = 50):
X = np.zeros([batch_size,self.height,self.width,1])
img = np.zeros((self.height,self.width),dtype=np.uint8)
Y = np.zeros([batch_size,self.char_num,self.classes])
image = ImageCaptcha(width = self.width,height = self.height)
while True:
for i in range(batch_size):
captcha_str = ''.join(random.sample(self.characters,self.char_num))
img = image.generate_image(captcha_str).convert('L')
img = np.array(img.getdata())
X[i] = np.reshape(img,[self.height,self.width,1])/255.0
for j,ch in enumerate(captcha_str):
Y[i,j,self.characters.find(ch)] = 1
Y = np.reshape(Y,(batch_size,self.char_num*self.classes))
yield X,Y
def decode_captcha(self,y):
y = np.reshape(y,(len(y),self.char_num,self.classes))
return ''.join(self.characters[x] for x in np.argmax(y,axis = 2)[0,:])
def get_parameter(self):
return self.width,self.height,self.char_num,self.characters,self.classes
def gen_test_captcha(self):
image = ImageCaptcha(width = self.width,height = self.height)
captcha_str = ''.join(random.sample(self.characters,self.char_num))
img = image.generate_image(captcha_str)
img.save(captcha_str + '.jpg')
if __name__ == '__main__':
g = generateCaptcha()
g.gen_test_captcha()保存为 generate_captcha.py
进到该目录 运行 python generate_captcha.py
你会看到该目录下会生成图片文件
自此 样本的工作完成了
0x003 创建识别模型
模型使用了卷积神经网络（CNN）。（CNN是深度学习一个特殊示例，它在计算机视觉有非常重要的影响。） 这里使用了 3 层隐藏层、2 层全连接层，对每层都进行 dropout。
- dropout是用来防止过拟合
-
过拟合 简单的理解就是 对于训练模型识别率过高，但是真正的识别率过低。打个比喻就是你考试前背题背的很熟悉，结果考试出的不是你背的，结果很差
-
层的计算公式
但是一般我们都是边调整 边测试已达到效率最优
模型代码 ：
#!/usr/bin/python
# -*- coding: utf-8 -*
import tensorflow as tf
import math
class captchaModel():
def __init__(self,
width = 160,
height = 60,
char_num = 4,
classes = 62):
self.width = width
self.height = height
self.char_num = char_num
self.classes = classes
def conv2d(self,x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(self,x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
def weight_variable(self,shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(self,shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def create_model(self,x_images,keep_prob):
#first layer
w_conv1 = self.weight_variable([5, 5, 1, 32])
b_conv1 = self.bias_variable([32])
h_conv1 = tf.nn.relu(tf.nn.bias_add(self.conv2d(x_images, w_conv1), b_conv1))
h_pool1 = self.max_pool_2x2(h_conv1)
h_dropout1 = tf.nn.dropout(h_pool1,keep_prob)
conv_width = math.ceil(self.width/2)
conv_height = math.ceil(self.height/2)
#second layer
w_conv2 = self.weight_variable([5, 5, 32, 64])
b_conv2 = self.bias_variable([64])
h_conv2 = tf.nn.relu(tf.nn.bias_add(self.conv2d(h_dropout1, w_conv2), b_conv2))
h_pool2 = self.max_pool_2x2(h_conv2)
h_dropout2 = tf.nn.dropout(h_pool2,keep_prob)
conv_width = math.ceil(conv_width/2)
conv_height = math.ceil(conv_height/2)
#third layer
w_conv3 = self.weight_variable([5, 5, 64, 64])
b_conv3 = self.bias_variable([64])
h_conv3 = tf.nn.relu(tf.nn.bias_add(self.conv2d(h_dropout2, w_conv3), b_conv3))
h_pool3 = self.max_pool_2x2(h_conv3)
h_dropout3 = tf.nn.dropout(h_pool3,keep_prob)
conv_width = math.ceil(conv_width/2)
conv_height = math.ceil(conv_height/2)
#first fully layer
conv_width = int(conv_width)
conv_height = int(conv_height)
w_fc1 = self.weight_variable([64*conv_width*conv_height,1024])
b_fc1 = self.bias_variable([1024])
h_dropout3_flat = tf.reshape(h_dropout3,[-1,64*conv_width*conv_height])
h_fc1 = tf.nn.relu(tf.nn.bias_add(tf.matmul(h_dropout3_flat, w_fc1), b_fc1))
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#second fully layer
w_fc2 = self.weight_variable([1024,self.char_num*self.classes])
b_fc2 = self.bias_variable([self.char_num*self.classes])
y_conv = tf.add(tf.matmul(h_fc1_drop, w_fc2), b_fc2)
return y_conv保存为captcha_model.py
0x004 训练识别模型
有了样本和模型以后 我们开始训练模型
#!/usr/bin/python
import tensorflow as tf
import numpy as np
import string
import generate_captcha
import captcha_model
if __name__ == '__main__':
captcha = generate_captcha.generateCaptcha()
width,height,char_num,characters,classes = captcha.get_parameter()
x = tf.placeholder(tf.float32, [None, height,width,1])
y_ = tf.placeholder(tf.float32, [None, char_num*classes])
keep_prob = tf.placeholder(tf.float32)
model = captcha_model.captchaModel(width,height,char_num,classes)
y_conv = model.create_model(x,keep_prob)
cross_entropy = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=y_,logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
predict = tf.reshape(y_conv, [-1,char_num, classes])
real = tf.reshape(y_,[-1,char_num, classes])
correct_prediction = tf.equal(tf.argmax(predict,2), tf.argmax(real,2))
correct_prediction = tf.cast(correct_prediction, tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
step = 0
while True:
batch_x,batch_y = next(captcha.gen_captcha(64))
_,loss = sess.run([train_step,cross_entropy],feed_dict={x: batch_x, y_: batch_y, keep_prob: 0.75})
print ('step:%d,loss:%f' % (step,loss))
if step % 100 == 0:
batch_x_test,batch_y_test = next(captcha.gen_captcha(100))
acc = sess.run(accuracy, feed_dict={x: batch_x_test, y_: batch_y_test, keep_prob: 1.})
print ('###############################################step:%d,accuracy:%f' % (step,acc))
if acc > 0.99:
saver.save(sess,"capcha_model.ckpt")
break
step += 1保存为 train_captcha.py
执行 python train_captcha.py
- 其中 39行号 acc 代表准确率 此时需要准确率大于99%才保存
各位执行的时候可以设置成 0.01 先实验一下效果
等训练完成后 你会看得到 目录下保存了 这几个文件
0x004 验证
验证比较简单 只要加载刚才保存的模型
然后 生成一张图识别即可 。
!/usr/bin/python
from PIL import Image, ImageFilter
import tensorflow as tf
import numpy as np
import string
import sys
import generate_captcha
import captcha_model
if __name__ == '__main__':
captcha = generate_captcha.generateCaptcha()
width,height,char_num,characters,classes = captcha.get_parameter()
gray_image = Image.open(sys.argv[1]).convert('L')
img = np.array(gray_image.getdata())
test_x = np.reshape(img,[height,width,1])/255.0
x = tf.placeholder(tf.float32, [None, height,width,1])
keep_prob = tf.placeholder(tf.float32)
model = captcha_model.captchaModel(width,height,char_num,classes)
y_conv = model.create_model(x,keep_prob)
predict = tf.argmax(tf.reshape(y_conv, [-1,char_num, classes]),2)
init_op = tf.global_variables_initializer()
saver = tf.train.Saver()
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
with tf.Session(config=tf.ConfigProto(log_device_placement=False,gpu_options=gpu_options)) as sess:
sess.run(init_op)
saver.restore(sess, "capcha_model.ckpt")
pre_list = sess.run(predict,feed_dict={x: [test_x], keep_prob: 1})
for i in pre_list:
s = ''
for j in i:
s += characters[j]
print s保存为 predict_captcha.py
执行 python predict_captcha.py Mlzv.jpg
即可