Keras：如何将 CNN 模型与决策树连接起来

Question

我想训练一个模型来根据物理信号预测一个人的情绪。我有一个物理信号并将其用作输入特征；

心电图（心电图）

我想使用 CNN 架构从数据中提取特征，然后使用这些提取的特征来输入经典的“决策树分类器”。下面，您可以看到我的 CNN 方法没有决策树；

model = Sequential()
model.add(Conv1D(15,60,padding='valid', activation='relu',input_shape=(18000,1), strides = 1,  kernel_regularizer=regularizers.l1_l2(l1=0.1, l2=0.1)))
model.add(MaxPooling1D(2,data_format='channels_last'))
model.add(Dropout(0.6))
model.add(BatchNormalization())
model.add(Conv1D(30, 60, padding='valid', activation='relu',kernel_regularizer = regularizers.l1_l2(l1=0.1, l2=0.1), strides=1))
model.add(MaxPooling1D(4,data_format='channels_last'))
model.add(Dropout(0.6))
model.add(BatchNormalization())
model.add(Flatten())
model.add(Dense(3, activation = 'softmax'))

我想编辑这段代码，以便在输出层中有工作的决策树，而不是model.add(Dense(3, activation = 'softmax'))。我试图像这样保存最后一个卷积层的输出；

output = model.layers[-6].output

当我打印出output 变量时，结果是这样的；

输出：Tensor("conv1d_56/Relu:0", shape=(?, 8971, 30), dtype=float32)

我猜，output 变量保存了提取的特征。现在，如何使用存储在 output 变量中的这些数据来提供我的 决策树 分类器模型？这是来自 scikit learn 的决策树；

from sklearn.tree import DecisionTreeClassifier

dtc = DecisionTreeClassifier(criterion = 'entropy')
dtc.fit()

我应该如何提供fit() 方法？提前致谢。

Answer 1

要提取可以传递给另一个算法的特征向量，您需要在 softmax 层之前有一个全连接层。像这样的东西会在你的 softmax 层之前添加一个 128 维的层：

model = Sequential()
model.add(Conv1D(15,60,padding='valid', activation='relu',input_shape=(18000,1), strides = 1,  kernel_regularizer=regularizers.l1_l2(l1=0.1, l2=0.1)))
model.add(MaxPooling1D(2,data_format='channels_last'))
model.add(Dropout(0.6))
model.add(BatchNormalization())
model.add(Conv1D(30, 60, padding='valid', activation='relu',kernel_regularizer = regularizers.l1_l2(l1=0.1, l2=0.1), strides=1))
model.add(MaxPooling1D(4,data_format='channels_last'))
model.add(Dropout(0.6))
model.add(BatchNormalization())
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(3, activation = 'softmax'))

如果您随后运行model.summary()，您可以看到图层的名称：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv1d_9 (Conv1D)            (None, 17941, 15)         915       
_________________________________________________________________
max_pooling1d_9 (MaxPooling1 (None, 8970, 15)          0         
_________________________________________________________________
dropout_10 (Dropout)         (None, 8970, 15)          0         
_________________________________________________________________
batch_normalization_9 (Batch (None, 8970, 15)          60        
_________________________________________________________________
conv1d_10 (Conv1D)           (None, 8911, 30)          27030     
_________________________________________________________________
max_pooling1d_10 (MaxPooling (None, 2227, 30)          0         
_________________________________________________________________
dropout_11 (Dropout)         (None, 2227, 30)          0         
_________________________________________________________________
batch_normalization_10 (Batc (None, 2227, 30)          120       
_________________________________________________________________
flatten_6 (Flatten)          (None, 66810)             0         
_________________________________________________________________
dense_7 (Dense)              (None, 128)               8551808   
_________________________________________________________________
dropout_12 (Dropout)         (None, 128)               0         
_________________________________________________________________
dense_8 (Dense)              (None, 3)                 387       
=================================================================
Total params: 8,580,320
Trainable params: 8,580,230
Non-trainable params: 90
_________________________________________________________________

一旦您的网络经过训练，您就可以创建一个新模型，其中输出层变为“dense_7”，它将生成 128 维特征向量：

feature_vectors_model = Model(model.input, model.get_layer('dense_7').output)
dtc_features = feature_vectors_model.predict(your_X_data)  # fit your decision tree on this data