![](/img/trans.png)
[英]AttributeError: 'NoneType' object has no attribute '_inbound_nodes' in Keras
[英]NoneType' object has no attribute '_inbound_nodes'
嗨,我正在尝试构建专家混合神经网络。 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,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”对象在尝试添加多个keras密集层时没有属性“ _inbound_nodes”,但是该问题已由keras的Lambda函数解决,可以转换为一个层。
好吧,您需要将tf.multiply()
放入Lambda
图层中,以获取Keras张量作为输出(而不是张量):
output = Lambda(lambda x: tf.multiply(x[0], x[1]))([gate, expert])
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.