from gen_check_code import gen_captcha_text_and_image_new
from gen_check_code import number, alphabet
from test_check_code import get_test_captcha_text_and_image, get_test_sets_length
import numpy as np
import tensorflow as tf
text, image = gen_captcha_text_and_image_new()
print("验证码图像channel:", image.shape) # (60, 160, 3)
# 图像大小
IMAGE_HEIGHT = image.shape[0]
IMAGE_WIDTH = image.shape[1]
image_shape = image.shape
MAX_CAPTCHA = len(text)
print("验证码文本最长字符数", MAX_CAPTCHA) # 验证码最长4字符; 我全部固定为4,可以不固定. 如果验证码长度小于4,用'_'补齐
# 把彩色图像转为灰度图像(色彩对识别验证码没有什么用)
# 度化是将三分量转化成一样数值的过程
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
# int gray = (int) (0.3 * r + 0.59 * g + 0.11 * b);
return gray
else:
return img
"""
cnn在图像大小是2的倍数时性能最高, 如果你用的图像大小不是2的倍数,可以在图像边缘补无用像素。
np.pad(image,((2,3),(2,2)), 'constant', constant_values=(255,)) # 在图像上补2行,下补3行,左补2行,右补2行
"""
char_set = number + alphabet # 如果验证码长度小于4, '_'用来补齐
CHAR_SET_LEN = len(char_set)
# 文本转向量
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):
try:
if ord(c) <= ord('9'):
k = ord(c)-ord('0')
else:
k = ord(c)-ord('a') + 10
except:
raise ValueError('No Map')
return k
for i, c in enumerate(text):
idx = i * CHAR_SET_LEN + char2pos(c)
vector[idx] = 1
return vector
# 向量转回文本
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)
# 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_new()
if image.shape == image_shape:
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CNN
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_alpha = np.sqrt(2.0/(IMAGE_HEIGHT*IMAGE_WIDTH)) #
# w_c2_alpha = np.sqrt(2.0/(3*3*32))
# w_c3_alpha = np.sqrt(2.0/(3*3*64))
# w_d1_alpha = np.sqrt(2.0/(8*32*64))
# out_alpha = np.sqrt(2.0/1024)
# 定义三层的卷积神经网络
# 定义第一层的卷积神经网络
# 定义第一层权重
w_c1 = tf.Variable(w_alpha * tf.random_normal([3, 3, 1, 32]))
# 定义第一层的偏置
b_c1 = tf.Variable(b_alpha * tf.random_normal([32]))
# 定义第一层的激励函数
conv1 = tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(x, w_c1, strides=[1, 1, 1, 1], padding='SAME'), b_c1))
# conv1 为输入 ksize 表示使用2*2池化,即将2*2的色块转化成1*1的色块
conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# dropout防止过拟合。
conv1 = tf.nn.dropout(conv1, keep_prob)
# 定义第二层的卷积神经网络
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)
# 定义第三层的卷积神经网络
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
# 随机生成权重
w_d = tf.Variable(w_alpha * tf.random_normal([11776, 2048]))
# 随机生成偏置
b_d = tf.Variable(b_alpha * tf.random_normal([2048]))
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([2048, 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)
# out = tf.nn.softmax(out)
return out
# 训练
def train_crack_captcha_cnn():
# 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
output = crack_captcha_cnn()
# loss
# loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(output, Y))
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
# 最后一层用来分类的softmax和sigmoid有什么不同?
# optimizer 为了加快训练 learning_rate应该开始大,然后慢慢衰
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(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(1600)
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 > 0.9999999999) & (step > 20000):
saver.save(sess, "./crack_capcha.model", global_step=step)
break
step += 1
## 训练(如果要训练则去掉下面一行的注释)
train_crack_captcha_cnn()
def crack_captcha():
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
# print("正确率:" + str(count) + "/1324")
for i in range(get_test_sets_length()):
text, image = get_test_captcha_text_and_image(i)
image = convert2gray(image)
captcha_image = 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(" ","")
tmp = ''
for char_idx in predict_text:
if char_idx < 10:
char_code = char_idx + ord('0')
elif char_idx < 36:
char_code = char_idx - 10 + ord('a')
tmp = tmp + chr(char_code)
predict_text = tmp
if text == predict_text:
count += 1
check_result = ",预测结果正确"
else:
check_result = ",预测结果不正确"
print(str(i) + ':' + predict_text + check_result)
print("正确率:" + str(count) + "/" + str(get_test_sets_length()))
# 测试(如果要测试则去掉下面一行的注释)
# crack_captcha()
crack_captcha_cnn: 定义一个神经网络
train_crack_captcha_cnn:训练神经网络
def crack_captcha:测试神经网络
从下一篇博客开始进行真正的训练的过程。