-
Notifications
You must be signed in to change notification settings - Fork 12
/
main.py
124 lines (108 loc) · 5.71 KB
/
main.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
import tensorflow as tf
import numpy as np
import os, argparse, time, random
from model import BiLSTM_CRF
from utils import str2bool, get_logger, get_entity
from data import read_corpus, read_dictionary, tag2label, random_embedding
## Session configuration
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' # default: 0
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.gpu_options.per_process_gpu_memory_fraction = 0.2 # need ~700MB GPU memory
## hyperparameters
parser = argparse.ArgumentParser(description='BiLSTM-CRF for Chinese NER task')
parser.add_argument('--train_data', type=str, default='data_path', help='train data source')
parser.add_argument('--test_data', type=str, default='data_path', help='test data source')
parser.add_argument('--batch_size', type=int, default=64, help='#sample of each minibatch')
parser.add_argument('--epoch', type=int, default=40, help='#epoch of training')
parser.add_argument('--hidden_dim', type=int, default=300, help='#dim of hidden state')
parser.add_argument('--optimizer', type=str, default='Adam', help='Adam/Adadelta/Adagrad/RMSProp/Momentum/SGD')
parser.add_argument('--CRF', type=str2bool, default=True, help='use CRF at the top layer. if False, use Softmax')
parser.add_argument('--lr', type=float, default=0.001, help='learning rate')
parser.add_argument('--clip', type=float, default=5.0, help='gradient clipping')
parser.add_argument('--dropout', type=float, default=0.5, help='dropout keep_prob')
parser.add_argument('--update_embedding', type=str2bool, default=True, help='update embedding during training')
parser.add_argument('--pretrain_embedding', type=str, default='random', help='use pretrained char embedding or init it randomly')
parser.add_argument('--embedding_dim', type=int, default=300, help='random init char embedding_dim')
parser.add_argument('--shuffle', type=str2bool, default=True, help='shuffle training data before each epoch')
parser.add_argument('--mode', type=str, default='demo', help='train/test/demo')
parser.add_argument('--demo_model', type=str, default='1521112368', help='model for test and demo')
args = parser.parse_args()
## 构造输入向量
# word2id.pkl文件是由执行data.vocab_build生成，去除语料中的低频词后给每一个词一个递增的编号，构造对应的词典
word2id = read_dictionary(os.path.join('.', args.train_data, 'word2id.pkl'))
# 每个charactor 入参随机初始化为300维向量（根据word2id来选择矩阵的某一行）
if args.pretrain_embedding == 'random':
embeddings = random_embedding(word2id, args.embedding_dim)
else:
embedding_path = 'pretrain_embedding.npy'
embeddings = np.array(np.load(embedding_path), dtype='float32')
## read corpus and get training data
if args.mode != 'demo':
train_path = os.path.join('.', args.train_data, 'train_data')
test_path = os.path.join('.', args.test_data, 'test_data')
train_data = read_corpus(train_path)
test_data = read_corpus(test_path); test_size = len(test_data)
## 路径设置
paths = {}
timestamp = str(int(time.time())) if args.mode == 'train' else args.demo_model
output_path = os.path.join('.', args.train_data+"_save", timestamp)
if not os.path.exists(output_path): os.makedirs(output_path)
summary_path = os.path.join(output_path, "summaries")
paths['summary_path'] = summary_path
if not os.path.exists(summary_path): os.makedirs(summary_path)
model_path = os.path.join(output_path, "checkpoints/")
if not os.path.exists(model_path): os.makedirs(model_path)
ckpt_prefix = os.path.join(model_path, "model")
paths['model_path'] = ckpt_prefix
result_path = os.path.join(output_path, "results")
paths['result_path'] = result_path
if not os.path.exists(result_path): os.makedirs(result_path)
log_path = os.path.join(result_path, "log.txt")
paths['log_path'] = log_path
get_logger(log_path).info(str(args))
## training model
if args.mode == 'train':
model = BiLSTM_CRF(args, embeddings, tag2label, word2id, paths, config=config)
model.build_graph()
## hyperparameters-tuning, split train/dev
# dev_data = train_data[:5000]; dev_size = len(dev_data)
# train_data = train_data[5000:]; train_size = len(train_data)
# print("train data: {0}\ndev data: {1}".format(train_size, dev_size))
# model.train(train=train_data, dev=dev_data)
## train model on the whole training data
print("train data: {}".format(len(train_data)))
model.train(train=train_data, dev=test_data) # use test_data as the dev_data to see overfitting phenomena
## testing model
elif args.mode == 'test':
ckpt_file = tf.train.latest_checkpoint(model_path)
print(ckpt_file)
paths['model_path'] = ckpt_file
model = BiLSTM_CRF(args, embeddings, tag2label, word2id, paths, config=config)
model.build_graph()
print("test data: {}".format(test_size))
model.test(test_data)
## demo
elif args.mode == 'demo':
ckpt_file = tf.train.latest_checkpoint(model_path)
print(ckpt_file)
paths['model_path'] = ckpt_file
model = BiLSTM_CRF(args, embeddings, tag2label, word2id, paths, config=config)
model.build_graph()
saver = tf.train.Saver()
with tf.Session(config=config) as sess:
print('============= demo =============')
saver.restore(sess, ckpt_file)
while(1):
print('Please input your sentence:')
demo_sent = input()
if demo_sent == '' or demo_sent.isspace():
print('See you next time!')
break
else:
demo_sent = list(demo_sent.strip())
demo_data = [(demo_sent, ['O'] * len(demo_sent))]
tag = model.demo_one(sess, demo_data)
PER, LOC, ORG = get_entity(tag, demo_sent)
print('PER: {}\nLOC: {}\nORG: {}'.format(PER, LOC, ORG))