(3)循环神经网络RNN

一、目录
二、代码
1、词嵌入+simpleRNN
存在梯度消失问题

model = Sequential()
model.add(Embedding(10000, 32))
model.add(SimpleRNN(32, return_sequences=True))
model.add(SimpleRNN(32, return_sequences=True))
model.add(SimpleRNN(32, return_sequences=True))
model.add(SimpleRNN(32))
model.summary()

2、LSTM

from keras.layers import LSTM
model = Sequential()
model.add(Embedding(max_features, 32))
model.add(LSTM(32))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',loss='binary_crossentropy',metrics=['acc'])

history = model.fit(input_train, y_train,epochs=10,batch_size=128,validation_split=0.2)

3、GRU

model = Sequential()
model.add(layers.GRU(32,dropout=0.2,recurrent_dropout=0.2,input_shape=(None, float_data.shape[-1])))
model.add(layers.Dense(1))
model.compile(optimizer=RMSprop(), loss='mae')

history = model.fit_generator(train_gen,steps_per_epoch=500,epochs=20,validation_data=val_gen,validation_steps=val_steps)

4、堆叠循环层与双向RNN
4.1堆叠循环层

model = Sequential()
model.add(layers.GRU(32,dropout=0.1,recurrent_dropout=0.5,return_sequences=True,input_shape=(None, float_data.shape[-1])))
model.add(layers.GRU(64, activation='relu',dropout=0.1,recurrent_dropout=0.5))
model.add(layers.Dense(1))
model.compile(optimizer=RMSprop(), loss='mae')

history = model.fit_generator(train_gen,steps_per_epoch=500,epochs=40,validation_data=val_gen,validation_steps=val_steps)

4.2双向RNN

#双向LSTM
model = Sequential()
model.add(layers.Embedding(max_features, 32))
model.add(layers.Bidirectional(layers.LSTM(32)))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])
history = model.fit(x_train, y_train,epochs=10,batch_size=128,validation_split=0.2)

#双向GRU
model = Sequential()
model.add(layers.Bidirectional(layers.GRU(32), input_shape=(None, float_data.shape[-1])))
model.add(layers.Dense(1))
model.compile(optimizer=RMSprop(), loss='mae')
history = model.fit_generator(train_gen,steps_per_epoch=500,epochs=40,validation_data=val_gen,validation_steps=val_steps)