如何在keras中连接两层？

0 829

我有一个具有两层的神经网络的示例。第一层有两个参数，并有一个输出。第二个参数应接受一个参数作为第一层的结果，并附加一个参数。它看起来应该像这样: 因此，我创建了一个具有两层的模型，并尝试将它们合并，但是它返回一个错误：在result.add(merged)行上：

The first layer in a Sequential model must get an "input_shape" or "batch_input_shape" argument.

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'])

2021-02-02 11:35 更新

karry • 4552

共 1 个回答

高赞时间

你的错误是因为定义为 Sequential() 的 result只是模型的容器，你还没有为它定义输入。

给定你要构建的集合，使result接受第三个输入x3。

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

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

third = Sequential()# of course you must provide the input to result which will be your x3
third.add(Dense(1, input_shape=(1,), activation='sigmoid'))
# lets say you add a few more layers to first and second.# concatenate them
merged = Concatenate([first, second])
# then concatenate the two outputs

result = Concatenate([merged,  third])

ada_grad = Adagrad(lr=0.1, epsilon=1e-08, decay=0.0)

result.compile(optimizer=ada_grad, loss='binary_crossentropy',
               metrics=['accuracy'])

但是，构建具有这种输入结构类型的模型的首选方法是使用 functional api. 以下是你的需求的实现

from keras.models import Modelfrom keras.layers import Concatenate, Dense, LSTM, Input, concatenatefrom keras.optimizers import Adagrad

first_input = Input(shape=(2, ))
first_dense = Dense(1, )(first_input)

second_input = Input(shape=(2, ))
second_dense = Dense(1, )(second_input)

merge_one = concatenate([first_dense, second_dense])

third_input = Input(shape=(1, ))
merge_two = concatenate([merge_one, third_input])

model = Model(inputs=[first_input, second_input, third_input], outputs=merge_two)
ada_grad = Adagrad(lr=0.1, epsilon=1e-08, decay=0.0)
model.compile(optimizer=ada_grad, loss='binary_crossentropy',
               metrics=['accuracy'])