keras实现BiLSTM+CNN+CRF文字标记NER

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,                    )