def predict():
with open(map_path, "rb") as f:
word_to_id, cat_to_id, seq_length, num_classes = pickle.load(f)
id_to_cat = {v: k for k, v in cat_to_id.items()}
config = TRNNConfig()
config.num_classes = num_classes
config.vocab_size = len(word_to_id)
model = TextRNN(config)
session = tf.Session()
session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=session, save_path=save_path) # 读取保存的模型
while True:
line = input("请输入测试句子:")
data_id = [[
word_to_id[x] for x in list(native_content(line))
if x in word_to_id
]]
x_pad = kr.preprocessing.sequence.pad_sequences(data_id, seq_length)
y_pred_cls = session.run(model.y_pred_cls,
feed_dict={
model.input_x: x_pad,
model.keep_prob: 1.0
})
print('sentence : {}, prdict intent : {}'.format(
line, id_to_cat[y_pred_cls[0]]))
a = 1
def __init__(self):
self.config = TRNNConfig()
self.categories, self.cat_to_id = read_category()
self.words, self.word_to_id = read_vocab(vocab_dir)
self.config.vocab_size = len(self.words)
self.model = TextRNN(self.config)
self.session = tf.Session()
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=save_path) # 读取保存的模型
def __init__(self):
self.config = TRNNConfig()
self.categories, self.cat_to_id = read_category()
self.words = np.load('./datas/dict_token.npy')
self.word_to_id = np.load('./datas/token_to_id.npy').tolist()
self.config.vocab_size = len(self.words)
self.model = TextRNN(self.config)
self.session = tf.Session()
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=save_path) # 读取保存的模型
def __init__(self):
self.config = TRNNConfig()
self.categories = categories
self.cat_to_id = cat_to_id
self.words = words
self.word_to_id = word_to_id
self.config.vocab_size = len(self.words)
self.model = TextRNN(self.config)
self.session = sess
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=rnn_save_path) # 读取保存的模型
def init():
"""初始化模型"""
rnn = TextRNN(embedding_dim=FLAGS.embedding_dim,
seq_length=FLAGS.seq_length,
num_classes=FLAGS.num_classes,
vocab_size=FLAGS.vocab_size,
num_layers=FLAGS.num_layers,
hidden_dim=FLAGS.hidden_dim,
rnn=FLAGS.rnn,
dropout_keep_prob=FLAGS.dropout_keep_prob,
learning_rate=FLAGS.learning_rate,
batch_size=FLAGS.batch_size,
num_epochs=FLAGS.num_epochs,
print_per_batch=FLAGS.print_per_batch,
save_per_batch=FLAGS.save_per_batch)
return rnn
def __init__(self):
with open(map_path, "rb") as f:
self.word_to_id, self.cat_to_id, self.seq_length, self.num_classes = pickle.load(
f)
self.id_to_cat = {v: k for k, v in self.cat_to_id.items()}
if model_type == 'cnn':
self.config = TCNNConfig()
self.config.num_classes = self.num_classes
self.config.vocab_size = len(self.word_to_id)
self.model = TextCNN(self.config)
else:
self.config = TRNNConfig()
self.config.num_classes = self.num_classes
self.config.vocab_size = len(self.word_to_id)
self.model = TextRNN(self.config)
self.session = tf.Session()
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess=self.session, save_path=save_path) # 读取保存的模型
def load_model(self):
sess = tf.Session()
print('Configuring CNN model...')
config = TRNNConfig()
cnn_model = TextRNN(config)
saver = tf.train.Saver()
params_file = tf.train.latest_checkpoint(self.model_dir)
saver.restore(sess, params_file)
categories, cat_to_id = read_category()
vocab_dir = 'cnews/cnews.vocab.txt'
words, word_to_id = read_vocab(vocab_dir)
self.words = words
self.word_to_id = word_to_id
self.categories = categories
self.cat_to_id = cat_to_id
self.cnn_model = cnn_model
self.sess = sess
print(self.cnn_model)
print(self.sess)
# 评估
print("Precision, Recall and F1-Score...")
print(metrics.classification_report(y_test_cls, y_pred_cls, target_names=categories))
# 混淆矩阵
print("Confusion Matrix...")
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
if __name__ == '__main__':
if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
raise ValueError("""usage: python run_rnn.py [train / test]""")
print('Configuring RNN model...')
config = TRNNConfig()
if not os.path.exists(vocab_dir): # 如果不存在词汇表，重建
build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
config.vocab_size = len(words)
model = TextRNN(config)
if sys.argv[1] == 'train':
train()
else:
test()
# default=path + '/valid2.csv')
parser.add_argument('--test_data', type=str, default='data/test.csv')
# parser.add_argument('--tensorboard_dir', type=str,
# default=path + '/tensorboard')
parser.add_argument('--save_path', type=str, default=path + '/model.ckpt')
parser.add_argument('--word_file', type=str, default=path + '/words.csv')
# parser.add_argument('--label_file', type=str,
# default=path + '/labels.csv')
parser.add_argument('--result', type=str, default=path + '/result.csv')
FLAGS, unparser = parser.parse_known_args()
# contents, labels, _ = read_data(FLAGS.train_data, sep=' ')
# train_contents, valid_contents, train_labels, valid_labels = train_test_split(contents, labels, test_size=0.1,
# random_state=0)
# valid_contents, valid_labels, _ = read_data(FLAGS.valid_data)
# words, word2id, labels, label2id = word_to_id(train_contents, train_labels, FLAGS.vocab_size)
# save_words(word2id, FLAGS.word_file)
# save_labels(label2id, FLAGS.label_file)
pred_contents, review_id, texts = read_data(FLAGS.test_data, sep=' ')
model = TextRNN(FLAGS.embedding_size, FLAGS.hidden_layers,
FLAGS.hidden_units, FLAGS.number_classes,
FLAGS.learning_rate, FLAGS.sequence_length,
FLAGS.vocab_size)
# train()
# test()
predict()
print("Time usage:", time_dif)
if __name__ == '__main__':
if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
raise ValueError("""usage: python run_rnn.py [train / test]""")
conn = pymysql.connect(host='localhost',
user='******',
passwd='sasa',
db='text_clf',
charset='utf8')
cur = conn.cursor()
print('Configuring RNN model...')
config = TRNNConfig()
#if not os.path.exists(vocab_dir): # 如果不存在词汇表，重建
# build_vocab(train_dir, vocab_dir, config.vocab_size)
categories, cat_to_vec = read_category()
#words, word_to_id = read_vocab(vocab_dir)
#config.vocab_size = len(words)
model = TextRNN(config, get_embedding())
print('training')
if sys.argv[1] == 'train':
train()
else:
test()
def train():
print('Configuring RNN model...')
config = TRNNConfig()
config.dropout_keep_prob = 1.0
start_time = time.time()
# config.batch_size = 10
total_batch = 0 # 总批次
best_mse_val = 99999999 # 最佳验证集准确率
best_loss_val = 99999999 # 最佳验证集准确率
last_improved = 0 # 记录上一次提升批次
require_improvement = 5000 # 如果超过1000轮未提升，提前结束训练
count = 0
tensorboard_dir = config.tensorboard_dir
# 配置GPU内存分配方式
tfconfig = tf.ConfigProto(log_device_placement=True)
tfconfig.gpu_options.allow_growth = True
tfconfig.gpu_options.per_process_gpu_memory_fraction = 0.6
with tf.Graph().as_default(), tf.Session(config=tfconfig) as sess:
train_dir_list = os.listdir(config.train_dir_tf)
train_dir_list = [
os.path.join(config.train_dir_tf, i) for i in train_dir_list
]
queueTrain = tf.train.string_input_producer(
train_dir_list, num_epochs=config.num_epochs)
title_len, title, label, frame_weight = read_example(queueTrain)
title_len_batch, title_batch, label_batch, frame_weight_batch = tf.train.batch(
[title_len, title, label, frame_weight],
batch_size=config.batch_size,
capacity=100000,
num_threads=1)
with tf.variable_scope("model",
initializer=tf.random_uniform_initializer(
-1 * 1, 1)):
model = TextRNN(config=config,
input_x_len=title_len_batch,
input_x=title_batch,
input_y=label_batch,
frame_weight=frame_weight_batch)
tf.summary.scalar("loss", model.loss)
tf.summary.scalar("mse", model.mse)
merged_summary = tf.summary.merge_all()
writer = tf.summary.FileWriter(tensorboard_dir, sess.graph)
fetches = [model.loss, model.mse]
feed_dict = {}
# init
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
sess.run(init_op)
# 配置 Saver
saver = tf.train.Saver(write_version=saver_pb2.SaverDef.V1)
if not config.retraining:
saver.restore(sess=sess, save_path=config.modelPath) # 读取保存的模型
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
if not os.path.exists(config.save_dir):
os.makedirs(config.save_dir)
try:
while not coord.should_stop():
# Run training steps or whatever
# titles, labels = sess.run([title_batch, label_batch])
if total_batch % config.save_per_batch == 0:
# 每多少轮次将训练结果写入tensorboard scalar
s = sess.run(merged_summary, feed_dict)
writer.add_summary(s, total_batch)
if total_batch % config.print_per_batch == 0:
# 每多少轮次输出在训练集和验证集上的性能
loss_val, mse_val = sess.run(fetches, feed_dict)
if mse_val < best_mse_val or loss_val < best_loss_val:
# 保存最好结果
best_mse_val = mse_val
best_loss_val = loss_val
last_improved = total_batch
improved_str = '*'
# saver.save(sess=sess, save_path=config.save_path)
if total_batch % config.save_per_batch == 0:
saver.save(sess,
config.save_path + '_%03d' %
(total_batch / config.save_per_batch),
write_meta_graph=False)
else:
improved_str = ''
time_dif = get_time_dif(start_time)
msg = 'Iter: {0:>6}, Val Loss: {1:>6.5}, Mse: {2:>6.5}, Time: {3} {4}'
print(
msg.format(total_batch, loss_val, mse_val, time_dif,
improved_str))
# print(embedding_inputs)
sess.run(model.optim, feed_dict)
total_batch += 1
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...")
coord.should_stop()
break # 跳出循环
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
coord.request_stop()
coord.join(threads)
def test():
print('Configuring RNN model...')
config = TRNNConfig()
config.dropout_keep_prob = 1.0
config.num_epochs = 1
start_time = time.time()
config.batch_size = 10
count = 0
# 配置GPU内存分配方式
tfconfig = tf.ConfigProto(log_device_placement=True)
tfconfig.gpu_options.allow_growth = True
tfconfig.gpu_options.per_process_gpu_memory_fraction = 0.6
fw = file(config.test_dir_output, "w")
with tf.Graph().as_default(), tf.Session(config=tfconfig) as sess:
test_dir_list = os.listdir(config.test_dir_tf)
test_dir_list = [
os.path.join(config.test_dir_tf, i) for i in test_dir_list
]
queueTest = tf.train.string_input_producer(
test_dir_list, num_epochs=config.num_epochs)
text, title_len, title, label, frame_weight = read_example_test(
queueTest)
text_batch, title_len_batch, title_batch, label_batch, frame_weight_batch = tf.train.batch(
[text, title_len, title, label, frame_weight],
batch_size=config.batch_size,
capacity=50000,
num_threads=1)
with tf.variable_scope("model",
initializer=tf.random_uniform_initializer(
-1 * 1, 1)):
model = TextRNN(config=config,
input_x_len=title_len_batch,
input_x=title_batch,
input_y=label_batch,
frame_weight=frame_weight_batch)
fetches = [text_batch, model.input_x_len, model.y_pred, model.input_y]
feed_dict = {}
# init
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
sess.run(init_op)
# 配置 Saver
saver = tf.train.Saver()
saver.restore(sess=sess, save_path=config.modelPath) # 读取保存的模型
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
if not os.path.exists(config.save_dir):
os.makedirs(config.save_dir)
try:
while not coord.should_stop():
texts, x_len, y_pred, y_test = sess.run(fetches,
feed_dict=feed_dict)
texts = "".join(texts.values).split("\n")
for i in range(len(texts) - 1):
score = [str(int(j * 100))
for j in y_test[i]][:x_len[i][0]]
y_test_i = " ".join(score)
score = [str(int(j * 100))
for j in y_pred[i]][:x_len[i][0]]
y_pred_i = " ".join(score)
fw.write(texts[i] + "\ttarget:\t" + y_test_i +
"\tpredict\t" + y_pred_i + "\n")
count = count + 1
if count % 10000 == 0:
print(count)
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
coord.request_stop()
coord.join(threads)
fw.close()
-0.0, 0.0, (rnn.config.vocab_size, embedding_dim))
count = 0
for i in range(0, rnn.config.vocab_size):
if (rnn.words[i] in word_vector_map
): #word_vector_map.has_key(cnn.words[i])
count = count
sub_embeddings[i] = word_vector_map.get(rnn.words[i])
else:
count = count + 1
missing_words_file.write(rnn.words[i] + '\n')
print('no embedding: ' + str(1.0 * count / len(rnn.words)))
print(str(len(sub_embeddings)) + '\t' + str(len(sub_embeddings[0])))
missing_words_file.close()
rnn.model = TextRNN(rnn.config)
rnn.train()
predict_y = rnn.test() #predicting results
print(predict_y)
print(len(predict_y))
print(len(test_data_Y))
tf.reset_default_graph()
correct_count = 0
for i in range(len(test_data_Y)):
if rnn.id_to_cat[predict_y[i]] == test_data_Y[i]:
correct_count += 1
doc_node = doc.createElement("doc")
doc_node.setAttribute("id", test_docs[i].split(',')[0])
# 混淆矩阵
print("Confusion Matrix...")
cm = metrics.confusion_matrix(y_test_cls, y_pred_cls)
print(cm)
time_dif = get_time_dif(start_time)
print("Time usage:", time_dif)
if __name__ == '__main__':
if len(sys.argv) != 2 or sys.argv[1] not in ['train', 'test']:
raise ValueError("""usage: python run_rnn.py [train / test]""")
print('Configuring RNN model...')
print('load data. . .')
X = pickle.load(open(train_data, 'rb'))
df, word_vecs, word_cab_num, sentence_max_len, class_num = X[0], X[1], X[2], X[3], X[4]
config = TRNNConfig(sentence_max_len, class_num, word_cab_num)
word_ids, W_list = process_data.getWordsVect(config, word_vecs)
model = TextRNN(config, W_list, False) #默认不训练词向量
if sys.argv[1] == 'train':
train()
else:
test()
def train():
# Training procedure
# ======================================================
# 设定最小显存使用量
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
config = RNNConfig()
rnn = TextRNN(config)
rnn.prepare_data()
rnn.setRNN()
print('Setting Tensorboard and Saver...')
# 设置Saver和checkpoint来保存模型
# ===================================================
checkpoint_dir = os.path.join(os.path.abspath("checkpoints"), "textrnn")
checkpoint_prefix = os.path.join(checkpoint_dir, rnn.train_mode)
if not os.path.exists(checkpoint_dir):
os.makedirs(checkpoint_dir)
saver = tf.train.Saver(tf.global_variables())
# =====================================================
# 配置Tensorboard，重新训练时，请将tensorboard文件夹删除，不然图会覆盖
# ====================================================================
train_tensorboard_dir = 'tensorboard/textrnn/train/' + config.train_mode
valid_tensorboard_dir = 'tensorboard/textrnn/valid/' + config.train_mode
if not os.path.exists(train_tensorboard_dir):
os.makedirs(train_tensorboard_dir)
if not os.path.exists(valid_tensorboard_dir):
os.makedirs(valid_tensorboard_dir)
# 训练结果记录
log_file = open(valid_tensorboard_dir+'/log.txt', mode='w')
merged_summary = tf.summary.merge([tf.summary.scalar('loss', rnn.loss),
tf.summary.scalar('accuracy', rnn.accuracy)])
train_summary_writer = tf.summary.FileWriter(train_tensorboard_dir, sess.graph)
# =========================================================================
global_step = tf.Variable(0, trainable=False)
# 保证Batch normalization的执行
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops): # 保证train_op在update_ops执行之后再执行。
train_op = tf.train.AdamOptimizer(config.learning_rate).minimize(rnn.loss, global_step)
# 训练步骤
def train_step(batch_x, batch_y, keep_prob=config.dropout_keep_prob):
feed_dict = {
rnn.input_x: batch_x,
rnn.labels: batch_y,
rnn.dropout_keep_prob: keep_prob,
rnn.training: True
}
sess.run(train_op, feed_dict=feed_dict)
step, loss, accuracy, summery = sess.run(
[global_step, rnn.loss, rnn.accuracy, merged_summary],
feed_dict={rnn.input_x: batch_x,
rnn.labels: batch_y,
rnn.dropout_keep_prob: 1.0,
rnn.training: False})
t = datetime.datetime.now().strftime('%m-%d %H:%M')
print('%s: epoch: %d, step: %d, loss: %f, accuracy: %f' % (t, epoch,step, loss, accuracy))
# 把结果写入Tensorboard中
train_summary_writer.add_summary(summery, step)
# 验证步骤
def valid_step(next_valid_element):
# 把valid_loss和valid_accuracy归0
valid_loss = 0.0
valid_accuracy = 0.0
valid_precision = 0.0
valid_recall = 0.0
valid_f1_score = 0.0
i = 0
while True:
try:
lines = sess.run(next_valid_element)
batch_x, batch_y = rnn.convert_input(lines)
feed_dict = {
rnn.input_x: batch_x,
rnn.labels: batch_y,
rnn.dropout_keep_prob: 1.0,
rnn.training: False
}
loss, accuracy, prediction, y_true = sess.run(
[rnn.loss, rnn.accuracy, rnn.prediction, rnn.labels],
feed_dict)
precision = sk.metrics.precision_score(y_true=y_true, y_pred=prediction, average='weighted')
recall = sk.metrics.recall_score(y_true=y_true, y_pred=prediction, average='weighted')
f1_score = sk.metrics.f1_score(y_true=y_true, y_pred=prediction, average='weighted')
valid_loss += loss
valid_accuracy += accuracy
valid_precision += precision
valid_recall += recall
valid_f1_score += f1_score
i += 1
except tf.errors.OutOfRangeError:
# 遍历完验证集，然后对loss和accuracy求平均值
valid_loss /= i
valid_accuracy /= i
valid_precision /= i
valid_recall /= i
valid_f1_score /= i
t = datetime.datetime.now().strftime('%m-%d %H:%M')
log = '%s: epoch %d, validation loss: %0.6f, accuracy: %0.6f' % (
t, epoch, valid_loss, valid_accuracy)
log = log + '\n' + ('precision: %0.6f, recall: %0.6f, f1_score: %0.6f' % (
valid_precision, valid_recall, valid_f1_score))
print(log)
log_file.write(log + '\n')
time.sleep(3)
# 把结果写入Tensorboard中
# valid_summary_writer.add_summary(valid_summary, step)
return
print('Start training TextRNN, training mode='+rnn.train_mode)
sess.run(tf.global_variables_initializer())
# Training loop
for epoch in range(config.epoch_num):
train_init_op, valid_init_op, next_train_element, next_valid_element = rnn.shuffle_datset()
sess.run(train_init_op)
while True:
try:
lines = sess.run(next_train_element)
batch_x, batch_y = rnn.convert_input(lines)
train_step(batch_x, batch_y, config.dropout_keep_prob)
except tf.errors.OutOfRangeError:
# 初始化验证集迭代器
sess.run(valid_init_op)
valid_step(next_valid_element)
break
train_summary_writer.close()
log_file.close()
# 训练完成后保存参数
path = saver.save(sess, checkpoint_prefix, global_step=global_step)
print("Saved model checkpoint to {}\n".format(path))