def wrap_gen_captcha_text_and_image():
''' 获取一张图，判断其是否符合（60，160，3）的规格'''
while True:
text, image = gen_captcha_text_and_image()
if image.shape == (60, 160, 3): #此部分应该与开头部分图片宽高吻合
#if image.shape == (60, 200, 3):#此部分应该与开头部分图片宽高吻合
return text, image
def wrap_gen_captcha_text_and_image():
''' 获取一张图，判断其是否符合（60，160，3）的规格'''
while True:
text, image = gen_captcha_text_and_image()
if image.shape == (IMAGE_HEIGHT, IMAGE_WIDTH,
3): #此部分应该与开头部分图片宽高吻合
return text, image
def test_times(n):
output = crack_captcha_cnn()
all = n
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('./'))
right_times = 0
for i in range(n):
raw_text, image = gen_captcha_text_and_image()
image = convert2gray(image) #生成一张新图
image = image.flatten() / 255 # 将图片一维化
predict = tf.argmax(
tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
text_list = sess.run(predict, feed_dict={X: [image], keep_prob: 1})
text = text_list[0].tolist()
vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)
i = 0
for n in text:
vector[i * CHAR_SET_LEN + n] = 1
i += 1
predict_text = vec2text(vector)
print("正确: {} 预测: {},tolower:{},{}".format(
raw_text, predict_text, raw_text.lower(),
predict_text.lower()))
if raw_text.lower() == predict_text.lower():
right_times += 1
print("right times:", right_times, all)
right_prop = float(right_times) / float(all)
print("正确率:", right_prop)
def make_prediction():
text, image = gen_captcha_text_and_image()
image = convert2gray(image)
image = image.flatten() / 255
predict_text = crack_captcha(image)
print("正确: {} 预测: {}".format(text, predict_text))
'''
def crack_captcha():
#tf.reset_default_graph()#avoid variable change
output = crack_captcha_cnn()
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('saveyzm'))
for intt in range(10):
text1, image = gen_captcha_text_and_image()
plt.imshow(image)
plt.show()
image = convert2gray(image)
captcha_image = image.flatten() / 255
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()
vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)
i = 0
for n in text:
vector[i * CHAR_SET_LEN + n] = 1
i += 1
print("正确: {} 预测: {}".format(text1, vec2text(vector)))
def wrap_gen_captcha_text_and_image():
while True:
text, image = gen_captcha_text_and_image(IMAGE_WIDTH, IMAGE_HEIGHT,
CHAR_SET,
CAPTCHA_TEXT_LEN,
FONT_SIZE)
if image.shape == (IMAGE_HEIGHT, IMAGE_WIDTH, 3):
return text, image
def crack_captcha_test():
session, predict = restore_latest_checkpoint()
failed_count = 0
for i in range(100):
text, image = gen_captcha_text_and_image(IMAGE_WIDTH, IMAGE_HEIGHT,
CHAR_SET, CAPTCHA_TEXT_LEN,
FONT_SIZE)
image = convert2gray(image)
image = image.flatten() / 255
predict_text = crack_captcha(session, predict, image)
if text != predict_text:
failed_count += 1
print("expected: {} predicted: {} failed_count:{}".format(
text, predict_text, failed_count))
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]) for i in range(batch_size): #获取图片，并灰度转换 text, image = gen_captcha_text_and_image() image = convert2gray(image) # flatten 图片一维化 以及对应的文字内容也一维化，形成一个128行每行一个图片及对应文本 batch_x[i,:] = image.flatten() / 255 # (image.flatten()-128)/128 mean为0 batch_y[i,:] = text2vec(text) return batch_x, batch_y
def get_next_batch(batch_size=128):
"""
生成一个训练batch
"""
batch_x = np.zeros([batch_size, IMAGE_HEIGHT * IMAGE_WIDTH])
batch_y = np.zeros([batch_size, MAX_CAPTCHA * CHAR_SET_LEN])
for i in range(batch_size):
text, image = 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
def crack_captcha():
output = crack_captcha_cnn()
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint('.'))
print(tf.train.latest_checkpoint('.'))
k = 0
while True:
text, image = gen_captcha_text_and_image()
image = convert2gray(image)
image = image.flatten() / 255
predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
text_list = sess.run(predict, feed_dict={X: [image], keep_prob: 1})
texts = text_list[0].tolist()
vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)
i = 0
for n in texts:
vector[i * CHAR_SET_LEN + n] = 1
i += 1
predict_text = vec2text(vector)
print("text: {} predict_text: {}".format(text, predict_text))
k += 1
def wrap_gen_captcha_text_and_image():
while True:
text, _image = gen_captcha_text_and_image()
if _image.shape == (IMAGE_HEIGHT, IMAGE_WIDTH, 3):
return text, _image
def wrap_gen_captcha_text_and_image():
while True:
text, image = gen_captcha_text_and_image()
#logging.debug("image,shape:%s",str(image.shape))
if image.shape == (60, 160, 3):
return text, image
def wrap_gen_captcha_text_and_image():
''' 获取一张图，判断其是否符合（60，160，3）的规格'''
while True:
text, image = gen_captcha_text_and_image()
if image.shape == (60, 160, 3):
return text, image
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
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
def test_crack_captcha_cnn():
text, image = gen_captcha_text_and_image()
image = convert2gray(image) #生成一张新图
image = image.flatten() / 255 # 将图片一维化
predict_text = crack_captcha(image) #导入模型识别
print("正确: {} 预测: {}".format(text, predict_text))
def cnn_random():
text, image = gen_captcha_text_and_image()
image = Image.fromarray(image)
image.save(captcha_path)
return redirect(url_for('cnn.cnn_index'))
def wrap_gen_captcha_text_and_image(self):
while True:
text, image = gen_captcha_text_and_image()
if image.shape == (self.IMAGE_HEIGHT, self.IMAGE_WIDTH,
self.IMAGE_CHANNEL):
return text, image
# 验证码最长N字符; 如果验证码长度小于N，用'_'补齐
MAX_CAPTCHA = 6
MIN_CAPTCHA = 6
print("Max number of label:", MAX_CAPTCHA)
# 图像大小
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
BATCH_SIZE = 128
EPOCH_SIZE = 50000
EVAL_PER_STEPS = 100
text, image = gen_captcha_text_and_image(MAX_CAPTCHA, MIN_CAPTCHA)
print("verification code iamge channel:", image.shape) # (60, 160, 3)
"""
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
"""
# 文本转向量
char_set = number + ['_'] # 如果验证码长度小于N, '_'用来补齐
CHAR_SET_LEN = len(char_set)
# 向量转回文本
def vec2text(vec):
char_pos = vec.nonzero()[0]
text = []
# -*- coding: utf-8 -*-
"""
Created on Tue Jan 23 09:29:46 2018
@author: Administrator
"""
import os
import numpy as np
import tensorflow as tf
from gen_captcha import gen_captcha_text_and_image
from gen_captcha import CHAR_SET_LEN, IMAGE_HEIGHT, IMAGE_WIDTH, MAX_CAPTCHA
import matplotlib.pyplot as plt
from cnn import crack_captcha_cnn, X, keep_prob
from data_iter import convert2gray, vec2text
_, random_im = gen_captcha_text_and_image()
def crack_captcha(captcha_image=random_im):
if captcha_image.shape != (IMAGE_HEIGHT, IMAGE_WIDTH, 3):
captcha_image = captcha_image.resize((IMAGE_HEIGHT, IMAGE_WIDTH, 3))
plt.imshow(captcha_image)
plt.show()
# 定义预测计算图
output = crack_captcha_cnn()
predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess=sess,
# coding:utf-8 ''' @author = super_fazai @File : TensorFlow_cnn_批量生成验证码并用cnn训练.py @connect : [email protected] ''' from gen_captcha import gen_captcha_text_and_image, number, alphabet, ALPHABET import numpy as np import tensorflow as tf text, image = gen_captcha_text_and_image() # 先生成验证码和文字测试模块是否完全 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) # 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 def convert2gray(img): ''' # 把彩色图像转为灰度图像(色彩对识别验证码没有什么用) :param img: :return: ''' 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]
#coding:utf-8
from gen_captcha import gen_captcha_text_and_image
from gen_captcha import number
from gen_captcha import alphabet
from gen_captcha import ALPHABET
import numpy as np
import tensorflow as tf
text, image = gen_captcha_text_and_image() #先生成验证码和文字测试模块是否完全
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) # 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）
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
"""
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
def train_crack_captcha_cnn():
import time
start_time = time.time()
output = crack_captcha_cnn()
# loss
#loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(output, Y))
#sigmoid函数输出的是概率
# 定义损失函数,依旧使用交叉熵 同时定义优化器 learning rate = 1e-4
# 函数说明：sigmoid损失函数计算
# 参数1：labels
# 类型和logits一致
# 参数2：logits
# 类型 `float32` or `float64`.
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)
# 定义评测准确率
correct_pred = tf.equal(max_idx_p, max_idx_l)
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
#开始训练
isTrain = False #来区分训练阶段和测试阶段，True 表示训练，False表示测试
train_steps = 1000 #表示训练的次数，例子中使用100
checkpoint_steps = 10 #表示训练多少次保存一下checkpoints，例子中使用50
checkpoint_dir = '.\\' #表示checkpoints文件的保存路径，例子中使用当前路径F:\\py3workspace\\train_captcha\\
isAgainTrain = True #表示是否恢复保存的模型继续训练
if isTrain:
saver = tf.train.Saver(max_to_keep=1)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer()) #初始化所有变量
start_step = 0
if isAgainTrain:
# 检查是否有checkpoint
checkpoint = tf.train.get_checkpoint_state(checkpoint_dir)
if checkpoint and checkpoint.model_checkpoint_path:
#saver.restore(sess, checkpoint.model_checkpoint_path)
#print(checkpoint.model_checkpoint_path.rsplit('-',1)[1])
start_step = int(
checkpoint.model_checkpoint_path.rsplit('-', 1)[1])
print(start_step)
saver.restore(sess,
tf.train.latest_checkpoint(checkpoint_dir))
# params=tf.trainable_variables()
# print("Trainable variables:------------------------")
# for idx, v in enumerate(params):
# print(" param {:3}: {:15} {}".format(idx, str(v.get_shape()), v.name))
# #读取图片
# text, image = gen_captcha_text_and_image()
# image = convert2gray(image)
# image = image.flatten() / 255
# sess=tf.Session()
# sess.run(tf.global_variables_initializer())
# #提取最后一个全连接层的参数 W和b
# W=sess.run(params[8])
# b=sess.run(params[9])
# #print(W,b)
# predict = tf.argmax(tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
# #提取第二个全连接层的输出值作为特征
# fea=sess.run(predict,feed_dict={X:image})
# print(fea)
# quit()
f = open(checkpoint_dir + 'acc.txt', 'w')
for step in range(start_step, train_steps):
#step += 50
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_)
f.write(str(step) + ', val_acc: ' + str(loss_) + '\n')
# 每100 step计算一次准确率
if step % checkpoint_steps == 0 and step > 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(
u'***************************************************************第%s次的准确率为%s'
% (step, acc))
#saver.save(sess, checkpoint_dir + 'model.ckpt', global_step=step)
saver.save(sess,
checkpoint_dir + "crack_capcha.model",
global_step=step)
# 如果准确率大于50%,保存模型,完成训练
if acc > 0.5: ##我这里设了0.9，设得越大训练要花的时间越长，如果设得过于接近1，很难达到。如果使用cpu，花的时间很长，cpu占用很高电脑发烫。
#saver.save(sess, checkpoint_dir +"crack_capcha.model", global_step=step)
print(time.time() - start_time)
break
#summary_writer = tf.summary.FileWriter("F://py3workspace//train_captcha//log", sess.graph)
#summary_writer.close()
else:
#output = crack_captcha_cnn()
saver = tf.train.Saver(max_to_keep=1)
sess = tf.Session()
#latest_checkpoint自动获取最后一次保存的模型
saver.restore(sess, tf.train.latest_checkpoint(checkpoint_dir))
#batch_x_test, batch_y_test = get_next_batch(100)
#_, loss_ = sess.run([optimizer, loss], feed_dict={X: batch_x_test, Y: batch_y_test, keep_prob: 1.})
#print(loss_)
#quit()
n = 10
while (n):
text, image = gen_captcha_text_and_image()
image = convert2gray(image)
image = image.flatten() / 255
predict = tf.argmax(
tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
text_list = sess.run(predict, feed_dict={X: [image], keep_prob: 1})
#print(text_list)
predict_text = text_list[0].tolist()
#print(predict_text)
vector = np.zeros(MAX_CAPTCHA * CHAR_SET_LEN)
#print(vector)
i = 0
for t in predict_text:
vector[i * 5 + t] = 1
i += 1
# break
#print(vector)
print("正确: {} 预测: {}".format(text, vec2text(vector)))
n = n - 1
#break
sess.close()
def wrap_gen_captcha_text_and_image(): ''' 获取一张图，判断其是否符合（60，160，3）的规格''' while True: text, image = gen_captcha_text_and_image() if image.shape == (60, 160, 3):#此部分应该与开头部分图片宽高吻合 return text, image
#!/usr/bin/env python3
# coding=utf-8
import os
from gen_captcha import gen_captcha_text_and_image
from gen_captcha import number
from gen_captcha import alphabet
from gen_captcha import ALPHABET
import numpy as np
import tensorflow as tf
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) # 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）
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
def cnn_random():
text, image = gen_captcha_text_and_image()
image = Image.fromarray(image)
image.save(captcha_path)
return redirect(url_for('cnn.cnn_index'))
import tensorflow as tf
import random
import os
from tensorflow.python.framework import ops
from tensorflow.python.framework import dtypes
from gen_captcha import gen_captcha_text_and_image
from gen_captcha import number
from gen_captcha import alphabet
from gen_captcha import ALPHABET
import numpy as np
import tensorflow as tf
text, image = gen_captcha_text_and_image()
IMAGE_HEIGHT = 60
IMAGE_WIDTH = 160
MAX_CAPTCHA = len(text)
def transformX(image):
image = convert2gray(image)
return image / 255
def transformY(text):
return text2vec(text)
def convert2gray(img):
if len(img.shape) > 2:
gray = np.mean(img, -1)
# r, g, b = img[:,:,0], img[:,:,1], img[:,:,2]
def wrap_gen_captcha_text_and_image(self):
while True:
text, image = gen_captcha_text_and_image()
if image.shape == (self.IMAGE_HEIGHT, self.IMAGE_WIDTH, self.IMAGE_CHANNEL):
return text, image
