TextClassification/TextRNNmodel.py at master · lytforgood/TextClassification · GitHub

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
# -*- coding: utf-8 -*-
from keras.models import Sequential
from keras.layers import Dense, Dropout, Embedding, LSTM, Bidirectional,GRU,SimpleRNN
import logging
from keras.callbacks import EarlyStopping

def train(x_train, y_train, x_test, y_test,maxlen,max_token,embedding_matrix,embedding_dims,batch_size,epochs,logpath,modelpath,modelname):
    embedding_layer = Embedding(max_token + 1,
                                embedding_dims,
                                input_length=maxlen,
                                weights=[embedding_matrix],
                                trainable=False)
    print(modelname + 'Build model...')
    model = Sequential()
    model.add(embedding_layer)
    model.add(SimpleRNN(128, activation="relu"))
    # model.add(LSTM(128))
    # model.add(Bidirectional(LSTM(200))) ### 输出维度64 GRU
    # model.add(Bidirectional(GRU(64)))
    model.add(Dropout(0.2))
    model.add(Dense(1, activation='sigmoid'))
    # try using different optimizers and different optimizer configs
    model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])
    # lstm常选参数model.add(LSTM(128, dropout=0.2, recurrent_dropout=0.2))
    # a stateful LSTM model
    # lahead: the input sequence length that the LSTM
    # https://github.com/keras-team/keras/blob/master/examples/lstm_stateful.py
    # model = Sequential()
    # model.add(LSTM(20,input_shape=(lahead, 1),
    #               batch_size=batch_size,
    #               stateful=stateful))
    # model.add(Dense(1))
    # model.compile(loss='mse', optimizer='adam')

    # patience经过几个epoch后loss不在变化停止训练
    early_stopping = EarlyStopping(monitor='val_loss', patience=2)
    # model.fit(X, y, validation_split=0.2, callbacks=[early_stopping])
    print('Train...')
    hist = model.fit(x_train, y_train,
                     batch_size=batch_size,
                     epochs=epochs,
                     validation_data=(x_test, y_test), callbacks=[early_stopping])
    # print(hist.history)
    ##输出loss与acc到日志文件
    log_format = "%(asctime)s - %(message)s"
    logging.basicConfig(filename=logpath, level=logging.DEBUG, format=log_format)
    logging.warning(modelname)
    for i in range(len(hist.history["acc"])):
        strlog=str(i+1)+" Epoch "+"-loss: "+str(hist.history["loss"][i])+" -acc: "+str(hist.history["acc"][i])+" -val_loss: "+str(hist.history["val_loss"][i])+" -val_acc: "+str(hist.history["val_acc"][i])
        logging.warning(strlog)

    model.save(modelpath + modelname + '.h5')

def train2(x_train, y_train, x_test, y_test,maxlen,max_token,embedding_matrix,embedding_dims,batch_size,epochs,logpath,modelpath,modelname):
    embedding_layer = Embedding(max_token + 1,
                                embedding_dims,
                                input_length=maxlen,
                                weights=[embedding_matrix],
                                trainable=False)
    print(modelname + 'Build model...')
    model = Sequential()
    model.add(embedding_layer)
    # model.add(SimpleRNN(128, activation="relu"))
    # model.add(LSTM(128))
    model.add(Bidirectional(LSTM(200))) ### 输出维度64 GRU
    # model.add(Bidirectional(GRU(64)))
    model.add(Dropout(0.2))
    model.add(Dense(1, activation='sigmoid'))
    # try using different optimizers and different optimizer configs
    model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])
    # lstm常选参数model.add(LSTM(128, dropout=0.2, recurrent_dropout=0.2))
    # a stateful LSTM model
    # lahead: the input sequence length that the LSTM
    # https://github.com/keras-team/keras/blob/master/examples/lstm_stateful.py
    # model = Sequential()
    # model.add(LSTM(20,input_shape=(lahead, 1),
    #               batch_size=batch_size,
    #               stateful=stateful))
    # model.add(Dense(1))
    # model.compile(loss='mse', optimizer='adam')

    # patience经过几个epoch后loss不在变化停止训练
    early_stopping = EarlyStopping(monitor='val_loss', patience=2)
    # model.fit(X, y, validation_split=0.2, callbacks=[early_stopping])
    print('Train...')
    hist = model.fit(x_train, y_train,
                     batch_size=batch_size,
                     epochs=epochs,
                     validation_data=(x_test, y_test), callbacks=[early_stopping])
    # print(hist.history)
    ##输出loss与acc到日志文件
    log_format = "%(asctime)s - %(message)s"
    logging.basicConfig(filename=logpath, level=logging.DEBUG, format=log_format)
    logging.warning(modelname)
    for i in range(len(hist.history["acc"])):
        strlog=str(i+1)+" Epoch "+"-loss: "+str(hist.history["loss"][i])+" -acc: "+str(hist.history["acc"][i])+" -val_loss: "+str(hist.history["val_loss"][i])+" -val_acc: "+str(hist.history["val_acc"][i])
        logging.warning(strlog)

    model.save(modelpath + modelname + '.h5')

def train3(x_train, y_train, x_test, y_test,maxlen,max_token,embedding_matrix,embedding_dims,batch_size,epochs,logpath,modelpath,modelname):
    embedding_layer = Embedding(max_token + 1,
                                embedding_dims,
                                input_length=maxlen,
                                weights=[embedding_matrix],
                                trainable=False)
    print(modelname+'Build model...')
    model = Sequential()
    model.add(embedding_layer)
    # model.add(SimpleRNN(128, activation="relu"))
    # model.add(LSTM(128))
    # model.add(Bidirectional(LSTM(200))) ### 输出维度64 GRU
    model.add(Bidirectional(GRU(128)))
    model.add(Dropout(0.2))
    model.add(Dense(1, activation='sigmoid'))
    # try using different optimizers and different optimizer configs
    model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])
    # lstm常选参数model.add(LSTM(128, dropout=0.2, recurrent_dropout=0.2))
    # a stateful LSTM model
    # lahead: the input sequence length that the LSTM
    # https://github.com/keras-team/keras/blob/master/examples/lstm_stateful.py
    # model = Sequential()
    # model.add(LSTM(20,input_shape=(lahead, 1),
    #               batch_size=batch_size,
    #               stateful=stateful))
    # model.add(Dense(1))
    # model.compile(loss='mse', optimizer='adam')

    # patience经过几个epoch后loss不在变化停止训练
    early_stopping = EarlyStopping(monitor='val_loss', patience=2)
    # model.fit(X, y, validation_split=0.2, callbacks=[early_stopping])
    print('Train...')
    hist = model.fit(x_train, y_train,
                     batch_size=batch_size,
                     epochs=epochs,
                     validation_data=(x_test, y_test), callbacks=[early_stopping])
    # print(hist.history)
    ##输出loss与acc到日志文件
    log_format = "%(asctime)s - %(message)s"
    logging.basicConfig(filename=logpath, level=logging.DEBUG, format=log_format)
    logging.warning(modelname)
    for i in range(len(hist.history["acc"])):
        strlog=str(i+1)+" Epoch "+"-loss: "+str(hist.history["loss"][i])+" -acc: "+str(hist.history["acc"][i])+" -val_loss: "+str(hist.history["val_loss"][i])+" -val_acc: "+str(hist.history["val_acc"][i])
        logging.warning(strlog)

    model.save(modelpath + modelname + '.h5')