def get_next_batch_test_hzeng(batch_size=128):
"""
# 生成一个训练batch
:param batch_size:
:return:
"""
batch_x = np.zeros([batch_size, IMAGE_HEIGHT * IMAGE_WIDTH])
batch_y = np.zeros([batch_size, MAX_CAPTCHA * CHAR_SET_LEN])
rootdir = join(capt.cfg.workspace, 'test')
file_names = []
for parent, dirnames, filenames in os.walk(
rootdir): # 三个参数：分别返回1.父目录 2.所有文件夹名字（不含路径） 3.所有文件名字
file_names = filenames
for i in range(batch_size):
text, image = wrap_get_captcha_text_and_image(rootdir, file_names)
image = convert2gray(image)
# fig, axarr = pylab.plt.subplots(2, 2)
# axarr[0, 0].imshow(image)
# pylab.show()
batch_x[
i, :] = image.flatten() / 255 # (image.flatten()-128)/128 mean为0
batch_y[i, :] = text2vec(text)
return batch_x, batch_y
def batch_hack_captcha():
"""
批量生成验证码，然后再批量进行识别
:return:
"""
# 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 = tf.train.import_meta_graph(save_model + ".meta")
saver.restore(sess, tf.train.latest_checkpoint(model_path))
stime = time.time()
task_cnt = 1000
right_cnt = 0
for i in range(task_cnt):
text, image = wrap_gen_captcha_text_and_image()
image = convert2gray(image)
image = image.flatten() / 255
predict_text = hack_function(sess, predict, image)
if text == predict_text:
right_cnt += 1
else:
print("标记: {} 预测: {}".format(text, predict_text))
pass
# print("标记: {} 预测: {}".format(text, predict_text))
print('task:', task_cnt, ' cost time:', (time.time() - stime), 's')
print('right/total-----', right_cnt, '/', task_cnt)
def batch_hack_captcha_save():
"""
批量生成验证码，然后再批量进行识别
:return:
"""
# 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 = tf.train.import_meta_graph(save_model + ".meta")
saver.restore(sess, tf.train.latest_checkpoint(model_path))
stime = time.time()
task_cnt = 1000
right_cnt = 0
rootdir = join(capt.cfg.workspace, 'test')
file_names = []
for parent, dirnames, filenames in os.walk(
rootdir): # 三个参数：分别返回1.父目录 2.所有文件夹名字（不含路径） 3.所有文件名字
file_names = filenames
for file_name in filenames:
print(file_name)
file_name, image = get_captcha_text_and_image2(rootdir, file_name)
image = convert2gray(image)
image = image.flatten() / 255
predict_text = hack_function(sess, predict, image)
file_name2 = '__' + predict_text + '__' + file_name
os.rename(join(rootdir, file_name), join(rootdir, file_name2))
def predict_captcha(image):
image = Image.open(image)
image = np.array(image)
image = convert2gray(image)
image = image.flatten() / 255
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:
# restore only once
saver.restore(sess, tf.train.latest_checkpoint(model_path))
text = hack_function(sess, predict, image)
return text
def hack_captcha(captcha_image):
# 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()
predict_text = "error"
with tf.Session() as sess:
# saver = tf.train.import_meta_graph(save_model + ".meta")
saver.restore(sess, tf.train.latest_checkpoint(model_path))
stime = time.time()
image = convert2gray(captcha_image)
image = image.flatten() / 255
predict_text = hack_function(sess, predict, image)
return predict_text
def get_next_batch(batch_size=128):
"""
# 生成一个训练batch
:param batch_size:
:return:
"""
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 = 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
def get_next_batch(batch_size=128):
"""
# 生成一个训练batch
:param batch_size:
:return:
"""
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 = wrap_gen_captcha_text_and_image()
image = convert2gray(image)
text = text.upper()
batch_x[
i, :] = image.flatten() / 255 # (image.flatten()-128)/128 mean为0
try:
batch_y[i, :] = text2vec(text)
except IndexError as e:
i -= 1
print("IndexError:%s", text)
continue
return batch_x, batch_y
def batch_hack_captcha():
"""
批量生成验证码，然后再批量进行识别
:return:
"""
# 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 = tf.train.import_meta_graph(save_model + ".meta")
saver.restore(sess, tf.train.latest_checkpoint(model_path))
stime = time.time()
task_cnt = 1000
right_cnt = 0
rootdir = join(capt.cfg.workspace, 'test')
file_names = []
for parent, dirnames, filenames in os.walk(
rootdir): # 三个参数：分别返回1.父目录 2.所有文件夹名字（不含路径） 3.所有文件名字
file_names = filenames
for i in range(task_cnt):
text, image = get_captcha_text_and_image(rootdir, file_names)
image = convert2gray(image)
image = image.flatten() / 255
predict_text = hack_function(sess, predict, image)
if text == predict_text:
right_cnt += 1
else:
print("标记: {} 预测: {}".format(text, predict_text))
pass
# print("标记: {} 预测: {}".format(text, predict_text))
print('task:', task_cnt, ' cost time:', (time.time() - stime), 's')
print('right/total-----', right_cnt, '/', task_cnt)
def batch_hack_captcha():
"""
批量生成验证码，然后再批量进行识别
:return:
"""
# 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 = tf.train.import_meta_graph(save_model + ".meta")
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/state_ops.md#latest_checkpoint
saver.restore(sess, tf.train.latest_checkpoint(model_path))
stime = time.time()
task_cnt = 1000
right_cnt = 0
for i in range(task_cnt):
text, image = wrap_gen_captcha_text_and_image()
text = text.upper()
image = convert2gray(image)
image = image.flatten() / 255
predict_text = hack_function(sess, predict, image)
if text == predict_text:
right_cnt += 1
print("正确预测:标记: {} 预测: {}".format(text, predict_text))
else:
print("错误预测:标记: {} 预测: {}".format(text, predict_text))
pass
# print("标记: {} 预测: {}".format(text, predict_text))
print('task:', task_cnt, ' cost time:', (time.time() - stime), 's')
print('right/total-----', right_cnt, '/', task_cnt)
pass
def hack_capt(self, image):
image = Image.open(image)
image = np.array(image)
image = convert2gray(image)
image = image.flatten() / 255
return hack_function(self.sess, self.predict, image)
def hack_captcha(captcha_image):
w_alpha = 0.01
b_alpha = 0.1
with tf.Graph().as_default() as g:
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
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
"""
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)
# 3 conv layer
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)
# Fully connected layer
w_d = tf.Variable(w_alpha * tf.random_normal([8 * 20 * 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_SET_LEN]))
b_out = tf.Variable(b_alpha *
tf.random_normal([MAX_CAPTCHA * CHAR_SET_LEN]))
output = tf.add(tf.matmul(dense, w_out), b_out) # 36*4
predict_text = "error"
#output=crack_captcha_cnn()
with g.name_scope(
"myscope"
) as scope: # 有了这个scope，下面的op的name都是类似myscope/Placeholder这样的前缀
sess = tf.Session(target='', graph=g,
config=None) # target表示要连接的tf执行引擎
predict = tf.argmax(
tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
saver = tf.train.Saver()
predict_text = "error"
with tf.Session() as sess:
saver.restore(sess, tf.train.latest_checkpoint(model_path))
stime = time.time()
image = convert2gray(captcha_image)
image = image.flatten() / 255
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)
return predict_text
