def run(self):
self.signal.emit(QtGui.QListWidget, 'listWidget', '训练已开始。')
step = 1
while True:
if not self.status:
self.signal.emit(QtGui.QListWidget, 'listWidget', '训练已停止。')
return
if self.is_paused:
if not self.pause_flag:
self.signal.emit(QtGui.QListWidget, 'listWidget', '训练已暂停。')
self.pause_flag = True
time.sleep(0.1)
continue
batch_x, batch_y = get_next_batch(32)
_, loss_ = self.sess.run([self.optimizer, self.loss], {
X: batch_x,
Y: batch_y,
keep_prob: 0.98
})
# print(step, 'loss:\t', loss_)
self.signal.emit(QtGui.QListWidget, 'listWidget',
'%s loss:\t %s' % (step, loss_))
if 0 == step % self.rate:
self.saver.save(self.sess, save_model, step)
if 0 == step % 100:
batch_x_test, batch_y_test = get_next_batch(100)
acc = self.sess.run(self.accuracy, {
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
# print(step, 'acc---------------------------------\t', acc)
self.signal.emit(
QtGui.QListWidget, 'listWidget',
'%d acc---------------------------------\t%s' %
(step, acc))
if ' ∞' != self.count and int(self.count) == step:
return
step += 1
def train_crack_captcha_cnn():
output = crack_captcha_cnn()
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))
print("Configuring TensorBoard and Saver...")
# 配置 Tensorboard，重新训练时，请将tensorboard文件夹删除，不然图会覆盖
tensorboard_dir = 'tensorboard/sougou_cnn'
if not os.path.exists(tensorboard_dir):
os.makedirs(tensorboard_dir)
tf.summary.scalar("loss", loss)
tf.summary.scalar("accuracy", accuracy)
merged_summary = tf.summary.merge_all()
writer = tf.summary.FileWriter(tensorboard_dir)
# 配置 Saver
saver = tf.train.Saver()
if not os.path.exists(save_dir):
os.makedirs(save_dir)
start_time = time.time()
best_acc_val = 0.0 # 最佳验证集准确率
last_improved = 0 # 记录上一次提升批次
#require_improvement = 1600 # 如果超过xx轮未提升，提前结束训练
with tf.Session() as sess:
writer.add_graph(sess.graph)
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: 0.5})
# 每100 step计算一次准确率
if step % 100 == 0:
batch_x_test, batch_y_test = get_next_batch(100)
s, acc, losss = sess.run([merged_summary, accuracy, loss], feed_dict={X: batch_x_test, Y: batch_y_test, keep_prob: 1.})
# 将训练结果写入tensorboard scalar
writer.add_summary(s, step)
if acc > best_acc_val:
# 保存最好结果
best_acc_val = acc
last_improved = step
saver.save(sess=sess, save_path=save_dir)
improved_str = '*'
else:
improved_str = ''
time_dif = get_time_dif(start_time)
msg = 'Step: {0:>6}, Train Loss: {1:>6.2}, Val Loss: {2:>6.2}, Train Acc: {3:>7.2%}, Time: {4} {5}'
print(msg.format(step, loss_, losss, acc, time_dif, improved_str))
"""
if total_batch - last_improved > require_improvement:
# 验证集正确率长期不提升，提前结束训练
print("No optimization for a long time, auto-stopping...")
break # 跳出循环
"""
step += 1
def train_crack_captcha_cnn():
"""
训练模型
:return:
"""
output = crack_captcha_cnn()
with tf.name_scope('Monitor'):
# loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=output, labels=Y))
loss = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))
tf.summary.scalar('Loss', loss)
# 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)
with tf.name_scope('Monitor'):
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
tf.summary.scalar('Accuracy', accuracy)
saver = tf.train.Saver(max_to_keep=0)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter(tb_log_path, sess.graph)
step = 0
cnt = 0
while True:
if cnt == 125:
saver.save(sess, save_model, global_step=step)
break
batch_x, batch_y = get_next_batch(64, rand[cnt])
for j in range(100):
_, lossSize = sess.run([optimizer, loss],
feed_dict={
X: batch_x,
Y: batch_y,
keep_prob: 0.8
})
if step % 5 == 0:
print("cnt: " + str(cnt) + "\tstep: " + str(step) +
"\tloss: " + str(lossSize))
batch_x_test, batch_y_test = batch_x, batch_y
acc = sess.run(accuracy,
feed_dict={
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
print("Accuracy: " + str(acc))
if step % 2000 == 0:
saver.save(sess, save_model, global_step=step)
if step % 100 == 0:
summary = sess.run(merged,
feed_dict={
X: batch_x_test,
Y: batch_y_test,
keep_prob: 1.
})
writer.add_summary(summary, step)
step += 1
cnt += 1
def train_crack_captcha_cnn():
"""
训练模型
:return:
"""
global_step = tf.Variable(0, trainable=False)
output = crack_captcha_cnn()
predict = tf.reshape(output, [-1, MAX_CAPTCHA, CHAR_SET_LEN])
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))#最大概率分类
#loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=output, labels=Y))#二进制分类
tf.summary.scalar('my_loss', loss)
# 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=0.0003).minimize(loss,global_step=global_step)
with tf.name_scope('my_monitor'):
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
tf.summary.scalar('my_accuracy', accuracy)
with tf.device('/gpu:0'):
sess = tf.Session(config=tf.ConfigProto(log_device_placement=False))
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver(tf.global_variables(),max_to_keep=2) # 将训练过程进行保存
try:
saver.restore(sess, tf.train.latest_checkpoint(model_path))
except Exception as e:
print (e)
merged = tf.summary.merge_all()
writer = tf.summary.FileWriter(tb_log_path, sess.graph)
step = 0
time_ep_start=time.time()
max_acc_on_tax_pic=0
max_acc_step=0
while True:
batch_x, batch_y = get_next_batch(64) # 64
_, loss_ ,step= sess.run([optimizer, loss,global_step], feed_dict={X: batch_x, Y: batch_y, keep_prob: 1.0})
if step%10==0:
print(step, 'loss: ', loss_)
# 每100步保存一次实验结果
if step % 100 == 0:
saver.save(sess, save_model, global_step=step)
else:
continue
# 生成测试集计算精度
ep_time=time.time()-time_ep_start
time_ep_start=time.time()
acc_train_pic=test_hack_captcha_training_data(sess,output)
print('EP spend:%0.2fs\n'%ep_time,
'acc_on_train_pic: %0.2f%%'%(acc_train_pic*100)
)
# 终止条件
if acc_train_pic>0.98:
break
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)
# 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=0.0001).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(100) # 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 % 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_test_batch(300) # 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: 1.0})
print(step, 'acc---------------------------------\t', acc)
# 终止条件
if acc > 0.95:
break
# 启用监控 tensor board
summary = sess.run(merged, feed_dict={X: batch_x_test, Y: batch_y_test, keep_prob: 1.0})
writer.add_summary(summary, step)