也许对你的问题有帮助?
这是一个带有 LSTM 和注意力的分类模型
字符级:
首先为注意力创建一个自定义层:
课堂注意力(层):
def init(self,**kwargs):
super(attention,self).init(**kwargs)
def build(self,input_shape):
self.W=self.add_weight(name='attention_weight', shape=(input_shape[-1],1),
initializer='random_normal', trainable=True)
self.b=self.add_weight(name='attention_bias', shape=(input_shape[1],1),
initializer='zeros', trainable=True)
super(attention, self).build(input_shape)
def call(self,x):
# Alignment scores. Pass them through tanh function
e = K.tanh(K.dot(x,self.W)+self.b)
# Remove dimension of size 1
e = K.squeeze(e, axis=-1)
# Compute the weights
alpha = K.softmax(e)
# Reshape to tensorFlow format
alpha = K.expand_dims(alpha, axis=-1)
# Compute the context vector
context = x * alpha
context = K.sum(context, axis=1)
return context
LEN_CHA = 64 # 字符数
LEN_Input = 110 # 取决于最长的句子,用零填充
def LSTM_model_attention(Labels=3):
model = Sequential()
model.add(Embedding(LEN_CHA, EMBEDDING_DIM, input_length=LEN_INPUT))
model.add(SpatialDropout1D(0.7))
model.add(Bidirectional(LSTM(256, return_sequences=True)))
model.add(attention())
model.add(Dense(Labels, activation='softmax'))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['acc'])
return model
LSTM_attention = LSTM_model_attention()
LSTM_attention.summary()