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
|
import json
import codecs
import pandas as pd
import numpy as np
from keras_bert import load_trained_model_from_checkpoint, Tokenizer
from keras.layers import *
from keras.models import Model
from keras.optimizers import Adam
maxlen = 300
BATCH_SIZE = 8
config_path = './chinese_L-12_H-768_A-12/bert_config.json'
checkpoint_path = './chinese_L-12_H-768_A-12/bert_model.ckpt'
dict_path = './chinese_L-12_H-768_A-12/vocab.txt'
token_dict = {}
with codecs.open(dict_path, 'r', 'utf-8') as reader:
for line in reader:
token = line.strip()
token_dict[token] = len(token_dict)
class OurTokenizer(Tokenizer):
def _tokenize(self, text):
R = []
for c in text:
if c in self._token_dict:
R.append(c)
else:
R.append('[UNK]')
return R
tokenizer = OurTokenizer(token_dict)
def seq_padding(X, padding=0):
L = [len(x) for x in X]
ML = max(L)
return np.array([
np.concatenate([x, [padding] * (ML - len(x))]) if len(x) < ML else x for x in X
])
class DataGenerator:
def __init__(self, data, batch_size=BATCH_SIZE):
self.data = data
self.batch_size = batch_size
self.steps = len(self.data) // self.batch_size
if len(self.data) % self.batch_size != 0:
self.steps += 1
def __len__(self):
return self.steps
def __iter__(self):
while True:
idxs = list(range(len(self.data)))
np.random.shuffle(idxs)
X1, X2, Y = [], [], []
for i in idxs:
d = self.data[i]
text = d[0][:maxlen]
x1, x2 = tokenizer.encode(first=text)
y = d[1]
X1.append(x1)
X2.append(x2)
Y.append(y)
if len(X1) == self.batch_size or i == idxs[-1]:
X1 = seq_padding(X1)
X2 = seq_padding(X2)
Y = seq_padding(Y)
yield [X1, X2], Y
[X1, X2, Y] = [], [], []
def create_cls_model(num_labels):
bert_model = load_trained_model_from_checkpoint(config_path, checkpoint_path, seq_len=None)
for layer in bert_model.layers:
layer.trainable = True
x1_in = Input(shape=(None,))
x2_in = Input(shape=(None,))
x = bert_model([x1_in, x2_in])
cls_layer = Lambda(lambda x: x[:, 0])(x)
p = Dense(num_labels, activation='softmax')(cls_layer)
model = Model([x1_in, x2_in], p)
model.compile(
loss='categorical_crossentropy',
optimizer=Adam(1e-5),
metrics=['accuracy']
)
return model
if __name__ == '__main__':
print("begin data processing...")
train_df = pd.read_csv("data/cnews/cnews_train.csv").fillna(value="")
test_df = pd.read_csv("data/cnews/cnews_test.csv").fillna(value="")
labels = train_df["label"].unique()
with open("label.json", "w", encoding="utf-8") as f:
f.write(json.dumps(dict(zip(range(len(labels)), labels)), ensure_ascii=False, indent=2))
train_data = []
test_data = []
for i in range(train_df.shape[0]):
label, content = train_df.iloc[i, :]
label_id = [0] * len(labels)
for j, _ in enumerate(labels):
if _ == label:
label_id[j] = 1
train_data.append((content, label_id))
for i in range(test_df.shape[0]):
label, content = test_df.iloc[i, :]
label_id = [0] * len(labels)
for j, _ in enumerate(labels):
if _ == label:
label_id[j] = 1
test_data.append((content, label_id))
print("finish data processing!")
model = create_cls_model(len(labels))
train_D = DataGenerator(train_data)
test_D = DataGenerator(test_data)
print("begin model training...")
model.fit_generator(
train_D.__iter__(),
steps_per_epoch=len(train_D),
epochs=3,
validation_data=test_D.__iter__(),
validation_steps=len(test_D)
)
print("finish model training!")
model.save('cls_cnews.h5')
print("Model saved!")
result = model.evaluate_generator(test_D.__iter__(), steps=len(test_D))
print("模型评估结果:", result)
|
