keras - 是否可以根据 Keras 中的输入实现层之间的切换？

Question

可以在 Keras 中实现具有这样结构的神经网络吗？

思路如下：

在输入中，模型接收一个整数i（标记为红色）和其他一些东西v（在图片中是 0.12345）。接下来，有几个类似的并行层。根据i的值，v进入第i层，忽略其他层，然后该层的输出进入输出层。

换句话说，除了i之外的所有层都被忽略了。

标签： keras

Answer 1

如果我正确理解了您的问题，我认为这里最简单的解决方案是根据您的i.

因此，将您的X_train并将其拆分为X_train_1,X_train_2等。同样将您的X_test, 拆分为X_test_1,X_test_2等。

from keras.models import Sequential, Model
from keras.layers import *
from keras.utils import plot_model

然后设置单独的模型：

model1 = Sequential()
model1.add(Conv2D(32, kernel_size=(3,3), activation="relu", input_shape=(24,24,3)))
model1.add(MaxPooling2D(pool_size=(2,2)))
model1.add(Flatten())
model1.add(Dropout(0.5))
model1.add(Dense(512, activation = "relu"))

model2 = Sequential()
model2.add(Conv2D(32, kernel_size=(3,3), activation="relu", input_shape=(24,24,3)))
model2.add(MaxPooling2D(pool_size=(2,2)))
model2.add(Flatten())
model2.add(Dropout(0.5))
model2.add(Dense(512, activation = "relu"))

您将需要使用功能 API 来组合它们。我已经使用过Concatenate()，其他选项显示在此处的文档中。

outputs = Concatenate()([model1.output,model2.output])
outputs = Dense(256, activation='relu')(outputs)
outputs = Dropout(.5)(outputs)
outputs = Dense(5, activation='softmax')(outputs)

现在配置您的最终模型，指定输入和输出：

model = Model(inputs=[model1.inputs, model2.inputs], outputs=outputs)

检查model.summary()，你可以看到每一层是如何连接的：

__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
conv2d_input (InputLayer)       [(None, 24, 24, 3)]  0                                            
__________________________________________________________________________________________________
conv2d_1_input (InputLayer)     [(None, 24, 24, 3)]  0                                            
__________________________________________________________________________________________________
conv2d (Conv2D)                 (None, 22, 22, 32)   896         conv2d_input[0][0]               
__________________________________________________________________________________________________
conv2d_1 (Conv2D)               (None, 22, 22, 32)   896         conv2d_1_input[0][0]             
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D)    (None, 11, 11, 32)   0           conv2d[0][0]                     
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D)  (None, 11, 11, 32)   0           conv2d_1[0][0]                   
__________________________________________________________________________________________________
flatten (Flatten)               (None, 3872)         0           max_pooling2d[0][0]              
__________________________________________________________________________________________________
flatten_1 (Flatten)             (None, 3872)         0           max_pooling2d_1[0][0]            
__________________________________________________________________________________________________
dropout (Dropout)               (None, 3872)         0           flatten[0][0]                    
__________________________________________________________________________________________________
dropout_1 (Dropout)             (None, 3872)         0           flatten_1[0][0]                  
__________________________________________________________________________________________________
dense (Dense)                   (None, 512)          1982976     dropout[0][0]                    
__________________________________________________________________________________________________
dense_1 (Dense)                 (None, 512)          1982976     dropout_1[0][0]                  
__________________________________________________________________________________________________
concatenate (Concatenate)       (None, 1024)         0           dense[0][0]                      
                                                                 dense_1[0][0]                    
__________________________________________________________________________________________________
dense_2 (Dense)                 (None, 256)          262400      concatenate[0][0]                
__________________________________________________________________________________________________
dropout_2 (Dropout)             (None, 256)          0           dense_2[0][0]                    
__________________________________________________________________________________________________
dense_3 (Dense)                 (None, 5)            1285        dropout_2[0][0]                  
==================================================================================================
Total params: 4,231,429
Trainable params: 4,231,429
Non-trainable params: 0
__________________________________________________________________________________________________

但是使用以下方法更容易可视化模型plot_model(model, to_file='image.png', show_shapes=True)：

然后为了训练模型，你需要输入不同的输入，不要忘记你的测试（或验证）数据：

model.fit([X_train_1, X_train_2], y_train, validation_data = ([X_test_1, X_test_2], y_val), ...)    

注意：子模型（此处model1为 、model2等）不必具有相同的结构。它们可以有不同大小的层、不同数量的层和不同类型的层。这也是您可以在模型中包含具有不同类型特征的数据集的方式。