嗨,我正在尝试构建专家混合物神经网络。我在这里找到了一个代码:http://blog.sina.com.cn/s/blog_dc3c53e90102x9xu.html。我的目标是使门和专家来自不同的数据,但具有相同的维度。
def sliced(x,expert_num):
return x[:,:,:expert_num]
def reduce(x, axis):
return K.sum(x, axis=axis, keepdims=True)
def gatExpertLayer(inputGate, inputExpert, expert_num, nb_class):
#expert_num=30
#nb_class=10
input_vector1 = Input(shape=(inputGate.shape[1:]))
input_vector2 = Input(shape=(inputExpert.shape[1:]))
#The gate
gate = Dense(expert_num*nb_class, activation='softmax')(input_vector1)
gate = Reshape((1,nb_class, expert_num))(gate)
gate = Lambda(sliced, output_shape=(nb_class, expert_num), arguments={'expert_num':expert_num})(gate)
#The expert
expert = Dense(nb_class*expert_num, activation='sigmoid')(input_vector2)
expert = Reshape((nb_class, expert_num))(expert)
#The output
output = tf.multiply(gate, expert)
#output = keras.layers.merge([gate, expert], mode='mul')
output = Lambda(reduce, output_shape=(nb_class,), arguments={'axis': 2})(output)
model = Model(input=[input_vector1, input_vector2], output=output)
model.compile(loss='mean_squared_error', metrics=['mse'], optimizer='adam')
return model
但是,我得到了“'NoneType'对象没有属性'_inbound_nodes'”。我在这里检查了其他类似的问题:AttributeError: 'NoneType' object has no attribute '_inbound_nodes' while trying to add multiple keras Dense layers,但是问题已通过keras的Lambda函数转换为图层而得以解决。
答案 0 :(得分:2)
好吧,您需要将tf.multiply()
放在Lambda
层中才能获得Keras张量作为输出(而不是张量):
output = Lambda(lambda x: tf.multiply(x[0], x[1]))([gate, expert])