相关疑难解决方法(0)

我有一个有两层神经网络的例子.第一层有两个参数,有一个输出.第二个应该采用一个参数作为第一层和另一个参数的结果.它应该是这样的:

x1  x2  x3
 \  /   /
  y1   /
   \  /
    y2

所以,我创建了一个有两层的模型并尝试合并它们,但它返回一个错误:The first layer in a Sequential model must get an "input_shape" or "batch_input_shape" argument.就行了result.add(merged).

模型:

first = Sequential()
first.add(Dense(1, input_shape=(2,), activation='sigmoid'))

second = Sequential()
second.add(Dense(1, input_shape=(1,), activation='sigmoid'))

result = Sequential()
merged = Concatenate([first, second])
ada_grad = Adagrad(lr=0.1, epsilon=1e-08, decay=0.0)
result.add(merged)
result.compile(optimizer=ada_grad, loss=_loss_tensor, metrics=['accuracy'])

我试图在Keras 2.0中合并两个Sequential模型,使用以下行:

merged_model.add(Merge([model1, model2], mode='concat'))

这仍然可以正常工作,但会发出警告:

"The `Merge` layer is deprecated and will be removed after 08/2017. Use
instead layers from `keras.layers.merge`, e.g. `add`, `concatenate`, etc." 

但是,研究Keras文档并尝试添加Add(),并没有产生有效的东西.我已经阅读了几个有相同问题的人发帖,但发现没有解决方案适用于我的情况.有什么建议？

model = Sequential()
model1 = Sequential()
model1.add(Dense(300, input_dim=40, activation='relu', name='layer_1'))
model2 = Sequential()
model2.add(Dense(300, input_dim=40, activation='relu', name='layer_2'))
merged_model = Sequential()

merged_model.add(Merge([model1, model2], mode='concat'))

merged_model.add(Dense(1, activation='softmax', name='output_layer'))
merged_model.compile(loss='binary_crossentropy', optimizer='adam', 
metrics=['accuracy'])

checkpoint = ModelCheckpoint('weights.h5', monitor='val_acc',
save_best_only=True, verbose=2)
early_stopping = EarlyStopping(monitor="val_loss", patience=5)

merged_model.fit([x1, x2], y=y, batch_size=384, epochs=200,
             verbose=1, validation_split=0.1, shuffle=True, 
callbacks=[early_stopping, checkpoint])

编辑:当我尝试时(如下面由Kent Sommer建议):

from keras.layers.merge …