-
Notifications
You must be signed in to change notification settings - Fork 45
/
Copy pathtrain.py
194 lines (163 loc) · 9.52 KB
/
train.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
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
# -*- coding: utf-8 -*-
"""
@author: alexyang
@contact: alex.yang0326@gmail.com
@file: train.py
@time: 2019/1/5 10:02
@desc:
"""
import os
import time
from config import Config
from data_loader import load_input_data, load_label
from models import SentimentModel
os.environ['CUDA_VISIBLE_DEVICES'] = '2'
def train_model(data_folder, data_name, level, model_name, is_aspect_term=True):
config.data_folder = data_folder
config.data_name = data_name
if not os.path.exists(os.path.join(config.checkpoint_dir, data_folder)):
os.makedirs(os.path.join(config.checkpoint_dir, data_folder))
config.level = level
config.model_name = model_name
config.is_aspect_term = is_aspect_term
config.init_input()
config.exp_name = '{}_{}_wv_{}'.format(model_name, level, config.word_embed_type)
config.exp_name = config.exp_name + '_update' if config.word_embed_trainable else config.exp_name + '_fix'
if config.use_aspect_input:
config.exp_name += '_aspv_{}'.format(config.aspect_embed_type)
config.exp_name = config.exp_name + '_update' if config.aspect_embed_trainable else config.exp_name + '_fix'
if config.use_elmo:
config.exp_name += '_elmo_alone_{}_mode_{}_{}'.format(config.use_elmo_alone, config.elmo_output_mode,
'update' if config.elmo_trainable else 'fix')
print(config.exp_name)
model = SentimentModel(config)
test_input = load_input_data(data_folder, 'test', level, config.use_text_input, config.use_text_input_l,
config.use_text_input_r, config.use_text_input_r_with_pad, config.use_aspect_input,
config.use_aspect_text_input, config.use_loc_input, config.use_offset_input,
config.use_mask)
test_label = load_label(data_folder, 'test')
if not os.path.exists(os.path.join(config.checkpoint_dir, '%s/%s.hdf5' % (data_folder, config.exp_name))):
start_time = time.time()
train_input = load_input_data(data_folder, 'train', level, config.use_text_input, config.use_text_input_l,
config.use_text_input_r, config.use_text_input_r_with_pad,
config.use_aspect_input, config.use_aspect_text_input, config.use_loc_input,
config.use_offset_input, config.use_mask)
train_label = load_label(data_folder, 'train')
valid_input = load_input_data(data_folder, 'valid', level, config.use_text_input, config.use_text_input_l,
config.use_text_input_r, config.use_text_input_r_with_pad,
config.use_aspect_input, config.use_aspect_text_input, config.use_loc_input,
config.use_offset_input, config.use_mask)
valid_label = load_label(data_folder, 'valid')
'''
Note: Here I combine the training data and validation data together, use them as training input to the model,
while I use test data to server as validation input. The reason behind is that i want to fully explore how
well can the model perform on the test data (Keras's ModelCheckpoint callback can help usesave the model
which perform best on validation data (here the test data)).
But generally, we won't do that, because test data will not (and should not) be accessible during training
process.
'''
train_combine_valid_input = []
for i in range(len(train_input)):
train_combine_valid_input.append(train_input[i] + valid_input[i])
train_combine_valid_label = train_label + valid_label
model.train(train_combine_valid_input, train_combine_valid_label, test_input, test_label)
elapsed_time = time.time() - start_time
print('training time:', time.strftime("%H:%M:%S", time.gmtime(elapsed_time)))
# load the best model
model.load()
# print('score over valid data...')
# model.score(valid_input, valid_label)
print('score over test data...')
model.score(test_input, test_label)
if __name__ == '__main__':
config = Config()
config.use_elmo = False
config.use_elmo_alone = False
config.elmo_trainable = False
config.word_embed_trainable = True
config.aspect_embed_trainable = True
train_model('laptop/term', 'laptop', 'word', 'td_lstm')
train_model('laptop/term', 'laptop', 'word', 'tc_lstm')
train_model('laptop/term', 'laptop', 'word', 'ae_lstm')
train_model('laptop/term', 'laptop', 'word', 'at_lstm')
train_model('laptop/term', 'laptop', 'word', 'atae_lstm')
train_model('laptop/term', 'laptop', 'word', 'memnet')
train_model('laptop/term', 'laptop', 'word', 'ram')
train_model('laptop/term', 'laptop', 'word', 'ian')
train_model('laptop/term', 'laptop', 'word', 'cabasc')
train_model('restaurant/term', 'restaurant', 'word', 'td_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'tc_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'ae_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'at_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'atae_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'memnet')
train_model('restaurant/term', 'restaurant', 'word', 'ram')
train_model('restaurant/term', 'restaurant', 'word', 'ian')
train_model('restaurant/term', 'restaurant', 'word', 'cabasc')
train_model('twitter', 'twitter', 'word', 'td_lstm')
train_model('twitter', 'twitter', 'word', 'tc_lstm')
train_model('twitter', 'twitter', 'word', 'ae_lstm')
train_model('twitter', 'twitter', 'word', 'at_lstm')
train_model('twitter', 'twitter', 'word', 'atae_lstm')
train_model('twitter', 'twitter', 'word', 'memnet')
train_model('twitter', 'twitter', 'word', 'ram')
train_model('twitter', 'twitter', 'word', 'ian')
train_model('twitter', 'twitter', 'word', 'cabasc')
config.word_embed_trainable = False
config.aspect_embed_trainable = True
train_model('laptop/term', 'laptop', 'word', 'td_lstm')
train_model('laptop/term', 'laptop', 'word', 'tc_lstm')
train_model('laptop/term', 'laptop', 'word', 'ae_lstm')
train_model('laptop/term', 'laptop', 'word', 'at_lstm')
train_model('laptop/term', 'laptop', 'word', 'atae_lstm')
train_model('laptop/term', 'laptop', 'word', 'memnet')
train_model('laptop/term', 'laptop', 'word', 'ram')
train_model('laptop/term', 'laptop', 'word', 'ian')
train_model('laptop/term', 'laptop', 'word', 'cabasc')
train_model('restaurant/term', 'restaurant', 'word', 'td_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'tc_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'ae_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'at_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'atae_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'memnet')
train_model('restaurant/term', 'restaurant', 'word', 'ram')
train_model('restaurant/term', 'restaurant', 'word', 'ian')
train_model('restaurant/term', 'restaurant', 'word', 'cabasc')
train_model('twitter', 'twitter', 'word', 'td_lstm')
train_model('twitter', 'twitter', 'word', 'tc_lstm')
train_model('twitter', 'twitter', 'word', 'ae_lstm')
train_model('twitter', 'twitter', 'word', 'at_lstm')
train_model('twitter', 'twitter', 'word', 'atae_lstm')
train_model('twitter', 'twitter', 'word', 'memnet')
train_model('twitter', 'twitter', 'word', 'ram')
train_model('twitter', 'twitter', 'word', 'ian')
train_model('twitter', 'twitter', 'word', 'cabasc')
config.word_embed_trainable = False
config.aspect_embed_trainable = False
train_model('laptop/term', 'laptop', 'word', 'td_lstm')
train_model('laptop/term', 'laptop', 'word', 'tc_lstm')
train_model('laptop/term', 'laptop', 'word', 'ae_lstm')
train_model('laptop/term', 'laptop', 'word', 'at_lstm')
train_model('laptop/term', 'laptop', 'word', 'atae_lstm')
train_model('laptop/term', 'laptop', 'word', 'memnet')
train_model('laptop/term', 'laptop', 'word', 'ram')
train_model('laptop/term', 'laptop', 'word', 'ian')
train_model('laptop/term', 'laptop', 'word', 'cabasc')
train_model('restaurant/term', 'restaurant', 'word', 'td_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'tc_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'ae_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'at_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'atae_lstm')
train_model('restaurant/term', 'restaurant', 'word', 'memnet')
train_model('restaurant/term', 'restaurant', 'word', 'ram')
train_model('restaurant/term', 'restaurant', 'word', 'ian')
train_model('restaurant/term', 'restaurant', 'word', 'cabasc')
train_model('twitter', 'twitter', 'word', 'td_lstm')
train_model('twitter', 'twitter', 'word', 'tc_lstm')
train_model('twitter', 'twitter', 'word', 'ae_lstm')
train_model('twitter', 'twitter', 'word', 'at_lstm')
train_model('twitter', 'twitter', 'word', 'atae_lstm')
train_model('twitter', 'twitter', 'word', 'memnet')
train_model('twitter', 'twitter', 'word', 'ram')
train_model('twitter', 'twitter', 'word', 'ian')
train_model('twitter', 'twitter', 'word', 'cabasc')