我就废话不多说了，大家还是直接看代码吧~
|
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
|
import kerasfrom sklearn.model_selection import train_test_splitimport tensorflow as tffrom keras.callbacks import ModelCheckpoint,Callback# import keras.backend as Kfrom keras.layers import *from keras.models import Modelfrom keras.optimizers import SGD, RMSprop, Adagrad,Adamfrom keras.models import *from keras.metrics import *from keras import backend as Kfrom keras.regularizers import *from keras.metrics import categorical_accuracy# from keras.regularizers import activity_l1 #通过L1正则项，使得输出更加稀疏from keras_contrib.layers import CRFfrom visual_callbacks import AccLossPlotterplotter = AccLossPlotter(graphs=['acc', 'loss'], save_graph=True, save_graph_path=sys.path[0])# from crf import CRFLayer,create_custom_objectsclass LossHistory(Callback): def on_train_begin(self, logs={}): self.losses = [] def on_batch_end(self, batch, logs={}): self.losses.append(logs.get('loss'))# def on_epoch_end(self, epoch, logs=None):word_input = Input(shape=(max_len,), dtype='int32', name='word_input')word_emb = Embedding(len(char_value_dict)+2, output_dim=64, input_length=max_len, dropout=0.2, name='word_emb')(word_input)bilstm = Bidirectional(LSTM(32, dropout_W=0.1, dropout_U=0.1, return_sequences=True))(word_emb)bilstm_d = Dropout(0.1)(bilstm)half_window_size = 2paddinglayer = ZeroPadding1D(padding=half_window_size)(word_emb)conv = Conv1D(nb_filter=50, filter_length=(2 * half_window_size + 1), border_mode='valid')(paddinglayer)conv_d = Dropout(0.1)(conv)dense_conv = TimeDistributed(Dense(50))(conv_d)rnn_cnn_merge = merge([bilstm_d, dense_conv], mode='concat', concat_axis=2)dense = TimeDistributed(Dense(class_label_count))(rnn_cnn_merge)crf = CRF(class_label_count, sparse_target=False)crf_output = crf(dense)model = Model(input=[word_input], output=[crf_output])model.compile(loss=crf.loss_function, optimizer='adam', metrics=[crf.accuracy])model.summary()# serialize model to JSONmodel_json = model.to_json()with open("model.json", "w") as json_file: json_file.write(model_json)#编译模型# model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['acc',])# 用于保存验证集误差最小的参数，当验证集误差减少时，立马保存下来checkpointer = ModelCheckpoint(filepath="bilstm_1102_k205_tf130.w", verbose=0, save_best_only=True, save_weights_only=True) #save_weights_only=Truehistory = LossHistory()history = model.fit(x_train, y_train, batch_size=32, epochs=500,#validation_data = ([x_test, seq_lens_test], y_test), callbacks=[checkpointer, history, plotter], verbose=1, validation_split=0.1, ) |
补充知识：keras训练模型使用自定义CTC损失函数，重载模型时报错解决办法
使用keras训练模型，用到了ctc损失函数，需要自定义损失函数如下：
self.ctc_model.compile(loss={'ctc': lambda y_true, output: output}, optimizer=opt)
其中loss为自定义函数，使用字典{‘ctc': lambda y_true, output: output}
训练完模型后需要重载模型，如下：
from keras.models import load_model
model=load_model('final_ctc_model.h5')
报错：
Unknown loss function : <lambda>
由于是自定义的损失函数需要加参数custom_objects，这里需要定义字典{'': lambda y_true, output: output}，正确代码如下：
model=load_model('final_ctc_model.h5',custom_objects={'<lambda>': lambda y_true, output: output})
可能是因为要将自己定义的loss函数加入到keras函数里
在这之前试了很多次，如果用lambda y_true, output: output定义loss
函数字典名只能是'<lambda>'，不能是别的字符
如果自定义一个函数如loss_func作为loss函数如：
self.ctc_model.compile(loss=loss_func, optimizer=opt)
可以在重载时使用
am=load_model('final_ctc_model.h5',custom_objects={'loss_func': loss_func})
此时注意字典名和函数名要相同
以上这篇使用keras实现BiLSTM+CNN+CRF文字标记NER就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持服务器之家。
原文链接：https://blog.csdn.net/xinfeng2005/article/details/78485748
