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 __init__(self):
self.output = crack_captcha_cnn()
self.predict = tf.argmax(
tf.reshape(self.output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]), 2)
self.saver = tf.train.Saver()
self.sess = tf.Session()
self.saver.restore(self.sess, tf.train.latest_checkpoint(model_path))
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 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 train_crack_captcha_cnn():
"""
train model
:return:
"""
output = crack_captcha_cnn()
predict = tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]) # 36行，4列
label = tf.reshape(Y, [-1, MAX_CAPTCHA, CHAR_SET_LEN])
max_idx_p = tf.argmax(predict, 2) # shape:batch_size,4,nb_cls
max_idx_l = tf.argmax(label, 2)
correct_pred = tf.equal(max_idx_p, max_idx_l)
with tf.name_scope('my_monitor'):
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=predict,
labels=label))
# loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
tf.summary.scalar('my_loss', loss)
#What is the difference between softmax and sigmoid
#We use optimizer to accelerate the speed of training, and then decrease slowly
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
with tf.name_scope('my_monitor'):
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
tf.summary.scalar('my_accuracy', accuracy)
saver = tf.train.Saver() # save the procedures of training
sess = tf.InteractiveSession(config=tf.ConfigProto(
log_device_placement=False))
sess.run(tf.global_variables_initializer())
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter(tb_log_path, sess.graph)
step = 0
while True:
batch_x, batch_y = get_next_batch(64) # 64
_, loss_ = sess.run([optimizer, loss],
feed_dict={
X: batch_x,
Y: batch_y,
keep_prob: 0.95
})
print(step, 'loss:\t', loss_)
step += 1
# save the result once every 2000 times
if step % 2000 == 0:
saver.save(sess, save_model, global_step=step)
# Calculate the accuracy on the train set
if step % 50 != 0:
continue
# use the new data generated to calculate the accuracy, we calculated once every 50 steps
batch_x_test, batch_y_test = get_next_batch(
256) # use the new data to test
acc = sess.run(accuracy,
feed_dict={
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
print(step, 'acc---------------------------------\t', acc)
# end this operation when
if acc > 0.98:
break
# invocate the tensor board
summary = sess.run(merged,
feed_dict={
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
writer.add_summary(summary, step)
def train_crack_captcha_cnn():
output = crack_captcha_cnn()
predict = tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]) # 36行，4列
label = tf.reshape(Y, [-1, MAX_CAPTCHA, CHAR_SET_LEN])
max_idx_p = tf.argmax(predict, 2) # shape:batch_size,4,nb_cls
max_idx_l = tf.argmax(label, 2)
correct_pred = tf.equal(max_idx_p, max_idx_l)
with tf.name_scope('my_monitor'):
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=predict,
labels=label))
# loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
tf.summary.scalar('my_loss', loss)
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
with tf.name_scope('my_monitor'):
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
tf.summary.scalar('my_accuracy', accuracy)
saver = tf.train.Saver() # 将训练过程进行保存
sess = tf.InteractiveSession(config=tf.ConfigProto(
log_device_placement=False))
sess.run(tf.global_variables_initializer())
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter(tb_log_path, sess.graph)
step = 0
while True:
batch_x, batch_y = get_next_batch(64) # 64
_, loss_ = sess.run([optimizer, loss],
feed_dict={
X: batch_x,
Y: batch_y,
keep_prob: 0.95
})
print(step, 'loss:\t', loss_)
step += 1
# 每2000步保存一次实验结果
if step % 2000 == 0:
saver.save(sess, save_model, global_step=step)
# 在测试集上计算精度
if step % 50 != 0:
continue
# 每50 step计算一次准确率，使用新生成的数据
batch_x_test, batch_y_test = get_next_batch(256) # 新生成的数据集个来做测试
acc = sess.run(accuracy,
feed_dict={
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
print(step, 'acc---------------------------------\t', acc)
# 终止条件
if acc > 0.98:
break
# 启用监控 tensor board
summary = sess.run(merged,
feed_dict={
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
writer.add_summary(summary, step)
def train_crack_captcha_cnn():
"""
训练模型
:return:
"""
output = crack_captcha_cnn()
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/array_ops.md#reshape
predict = tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN]) # 36行，4列
label = tf.reshape(Y, [-1, MAX_CAPTCHA, CHAR_SET_LEN])
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/math_ops.md#argmax
max_idx_p = tf.argmax(predict, 2) # shape:batch_size,4,nb_cls
max_idx_l = tf.argmax(label, 2)
correct_pred = tf.equal(max_idx_p, max_idx_l)
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/framework.md#Graph.name_scope
with tf.name_scope('my_monitor'):
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/math_ops.md#reduce_mean
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/nn.md#softmax_cross_entropy_with_logits
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits_v2(logits=predict,
labels=label))
# loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/train.md#scalar_summary
tf.summary.scalar('my_loss', loss)
# 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
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/train.md#AdamOptimizer
optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)
with tf.name_scope('my_monitor'):
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
tf.summary.scalar('my_accuracy', accuracy)
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/state_ops.md#Saver
saver = tf.train.Saver() # 将训练过程进行保存
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/client.md#InteractiveSession
'''
sess = tf.InteractiveSession(
config=tf.ConfigProto(
log_device_placement=False
)
)
'''
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/train.md#merge_all_summaries
merged = tf.summary.merge_all()
# https://github.com/jikexueyuanwiki/tensorflow-zh/blob/master/SOURCE/api_docs/python/train.md#SummaryWriter
writer = tf.summary.FileWriter(tb_log_path, sess.graph)
step = 0
while True:
batch_x, batch_y = get_next_batch(64) # 64
#x_, conv1_, conv2_, conv3_, dense_, output_, predict_, label_ = sess.run([x, conv1, conv2, conv3, dense, output, predict, label], feed_dict={X: batch_x, Y: batch_y, keep_prob: 0.9})
_, loss_ = sess.run([optimizer, loss],
feed_dict={
X: batch_x,
Y: batch_y,
keep_prob: 0.9
})
print(step, 'loss:\t', loss_)
step += 1
# 每2000步保存一次实验结果
if step % 1000 == 0:
saver.save(sess, save_model, global_step=step)
# 在测试集上计算精度
if step % 50 != 0:
continue
# 每50 step计算一次准确率，使用新生成的数据
batch_x_test, batch_y_test = get_next_batch(256) # 新生成的数据集个来做测试
acc = sess.run(accuracy,
feed_dict={
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
print(step, 'acc---------------------------------\t', acc)
# 终止条件
if acc > 0.98:
break
# 启用监控 tensor board
summary = sess.run(merged,
feed_dict={
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
writer.add_summary(summary, step)
