def evaluate():
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [None, character_inference.INPUT_NODE],
name='x-input')
y_ = tf.placeholder(tf.float32, name='y-input')
y = character_inference.inference(x, None)
mse = tf.reduce_mean(tf.square(y_ - y))
variable_averages = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
while True:
with tf.Session() as sess:
ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
validate_feed = {x: text_list_side, y_: text_list_tag[:, 1]}
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split(
'/')[-1].split('-')[-1]
# eval_aws = sess.run(y, feed_dict=validate_feed)
loss = sess.run(mse, feed_dict=validate_feed)
print("After %s training step(s) loss %s" %
(global_step, loss))
print("==========================================")
else:
print('No checkpoint file found')
return
time.sleep(EVAL_INTERVAL_SECS)
def train():
x = tf.placeholder(tf.float32, [None, character_inference.INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, name='y-input')
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
y = character_inference.inference(x, regularizer)
global_step = tf.Variable(0, trainable=False)
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
variables_averages_op = variable_averages.apply(tf.trainable_variables())
mse = tf.reduce_mean(tf.square(y_ - y))
loss = mse + tf.add_n(tf.get_collection('losses'))
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
DATASET_SIZE / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
saver = tf.train.Saver()
with tf.Session() as sess:
tf.initialize_all_variables().run()
for i in range(TRAINING_STEPS):
_, loss_value, step = sess.run([train_op, loss, global_step],
feed_dict={x: train_list_side,
y_: train_list_tag[:, 1]})
if i % 1000 == 0:
print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
def evaluate(character):
with tf.Graph().as_default() as g:
x = tf.placeholder(tf.float32, [None, character_inference.INPUT_NODE],
name='x-input')
y_ = tf.placeholder(tf.float32, name='y-input')
y = character_inference.inference(x, None)
# 训练时损失函数
cross_entropy = tf.nn.sigmoid_cross_entropy_with_logits(logits=y,
targets=y_)
cross_entropy_mean = tf.reduce_mean(cross_entropy)
loss = cross_entropy_mean
variable_averages = tf.train.ExponentialMovingAverage(
MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
dict_acc = {}
dict_precision = {}
dict_recall = {}
dict_f1 = {}
dict_acc_lsit = {}
while True:
with tf.Session() as sess:
validate_feed = {x: text_list_side, y_: text_list_tag}
# tf.train.get_checkpoint_state 会根据checkpoint文件自动找到目录中最新模型的文件名
ckpt = tf.train.get_checkpoint_state(MODEL_SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
global_step = ckpt.model_checkpoint_path.split(
'/')[-1].split('-')[-1]
# accuracy_score = sess.run(accuracy, feed_dict=validate_feed)
# accuracy_score = get_acc(sess,true_y, pred_y)
# print("After %s training step(s), validation accuracy = %g" % (global_step, accuracy_score))
# print("the input data are \n%s" % test_list_side)
# print("the truly answer are \n%s" % test_list_tag)
eval_aws = sess.run(y, feed_dict=validate_feed)
eval_loss = sess.run(loss, feed_dict=validate_feed)
print("========the evaluate eval_loss are %s" % eval_loss)
# print("the evaluate answer are \n%s" % eval_aws)
accuracy_score, acc_list = get_acc(sess, text_list_tag,
eval_aws)
print(
"After %s training step(s), all validation accuracy = %g"
% (global_step, accuracy_score))
print(
"After %s training step(s), 5 validation accuracy = %s"
% (global_step, acc_list))
precision_list = get_precision(text_list_tag, eval_aws)
print("After %s training step(s), 5 precision = %s" %
(global_step, precision_list))
recall_list = get_recall(text_list_tag, eval_aws)
print("After %s training step(s), 5 recall = %s" %
(global_step, recall_list))
f1_list = get_f1(precision_list, recall_list)
print("After %s training step(s), 5 f1 = %s" %
(global_step, f1_list))
print("==========================================")
if int(global_step) > 1:
dict_acc[global_step] = accuracy_score
dict_precision[global_step] = precision_list
dict_recall[global_step] = recall_list
dict_f1[global_step] = f1_list
dict_acc_lsit[global_step] = acc_list
if int(global_step) == 29001:
# print("================全部准确率===================")
# sort_dict(dict_acc)
print("================5个准确率===================")
sort_dict(dict_acc_lsit)
print("================5个精准率===================")
sort_dict(dict_precision)
print("================5个召回率===================")
sort_dict(dict_recall)
print("================5个f1===================")
sort_dict(dict_f1)
break
else:
print('No checkpoint file found')
return
time.sleep(EVAL_INTERVAL_SECS)
def train():
# 定义输入输出placeholder。
x = tf.placeholder(tf.float32, [None, character_inference.INPUT_NODE], name='x-input')
y_ = tf.placeholder(tf.float32, name='y-input')
# L2正则化
regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
# 计算在当前参数下神经网络前向传播的结果
y = character_inference.inference(x, regularizer)
# y = character_inference.inference_nlayer(x,regularizer)
# 定义存储训练轮数的便利那个。这个变量不需要计算滑动平均值，所以这里指定这个变量为不可训练的变量
global_step = tf.Variable(0, trainable=False)
# ///////////////====定义损失函数、学习率、滑动平均操作以及训练过程。=====//////////////
# 初始化滑动平均类
variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
# 在所有代表神经网络参数的变量上使用滑动平均
variables_averages_op = variable_averages.apply(tf.trainable_variables())
# 计算交叉熵作为刻画预测值和真实值之间茶军的损失函数
"""
// 参考损失函数的计算 http://blog.csdn.net/u013250416/article/details/78230464
sigmoid_cross_entropy_with_logits 应用于多标签或者二分类
"""
# 多目标损失函数
cross_entropy = tf.nn.sigmoid_cross_entropy_with_logits(logits=y, targets=y_)
cross_entropy_mean = tf.reduce_mean(cross_entropy)
# 总损失等于交叉熵损失和正则化损失的和
loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
# 指数衰减设置学习率
learning_rate = tf.train.exponential_decay(
LEARNING_RATE_BASE,
global_step,
DATASET_SIZE / BATCH_SIZE,
LEARNING_RATE_DECAY,
staircase=True)
# 优化损失函数,在minimize中传入global_step将自动更新global_step,从而更新学习率
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
# 在训练神经网络模型时既需要通过反向传播来更新神经网络的参数，又要更新每一个参数的滑动平均值。
with tf.control_dependencies([train_step, variables_averages_op]):
train_op = tf.no_op(name='train')
# 初始化TensorFlow持久化类。
saver = tf.train.Saver()
with tf.Session() as sess:
tf.initialize_all_variables().run()
for i in range(TRAINING_STEPS):
# # 每次选取batch_size样本进行训练
# start = (i * BATCH_SIZE) % DATASET_SIZE
# end = min(start + BATCH_SIZE, DATASET_SIZE)
# _, loss_value, step = sess.run([train_op, loss, global_step],
# feed_dict={x: train_list_side[start:end],
# y_: train_list_tag[start:end]})
# 每次选取all_size样本进行训练
_, loss_value, step = sess.run([train_op, loss, global_step],
feed_dict={x: train_list_side,
y_: train_list_tag})
if i % 1000 == 0:
print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)