crf的实现 keras_使用keras实现BiLSTM+CNN+CRF文字标记NER

我就废话不多说了，大家还是直接看代码吧~

import keras

from sklearn.model_selection import train_test_split

import tensorflow as tf

from keras.callbacks import ModelCheckpoint,Callback

# import keras.backend as K

from keras.layers import *

from keras.models import Model

from keras.optimizers import SGD, RMSprop, Adagrad,Adam

from keras.models import *

from keras.metrics import *

from keras import backend as K

from 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 CRF

from visual_callbacks import AccLossPlotter

plotter = AccLossPlotter(graphs=['acc', 'loss'], save_graph=True, save_graph_path=sys.path[0])

# from crf import CRFLayer,create_custom_objects

class 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 = 2

paddinglayer = 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 JSON

model_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=True

history = 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 :

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 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''，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我们。

本文标题: 使用keras实现BiLSTM+CNN+CRF文字标记NER

本文地址: http://www.cppcns.com/jiaoben/python/324119.html