CNN+LSTM的模型结合（keras代码实现）
CNN-LSTM模型
运⾏环境：python3.6.5 、Keras 2.1.5 、tensorflow 2.3.1等
CNN-LSTM的Sequential()写法：
dels import Sequential
from keras.layers import Den, Dropout, Activation
凯撒之死
from keras.layers import Convolution1D, MaxPooling1D
from keras.layers import LSTM
#模型参数
time_step=100
# Convolution 卷积
filter_length = 5 # 滤波器长度
nb_filter = 64 # 滤波器个数
pool_length = 4 # 池化长度
# LSTM
设计主管lstm_output_size = 70 # LSTM 层输出尺⼨
# Training 训练参数
batch_size = 30 # 批数据量⼤⼩
nb_epoch = 2 # 迭代次数
# 构建模型
华洋外国语学校model = Sequential()
model.add(Input(shape=(time_step, 128)) # 输⼊特征接收维度) # 词嵌⼊层
model.add(Dropout(0.25)) # Dropout层
# 1D 卷积层，对词嵌⼊层输出做卷积操作
model.add(Convolution1D(nb_filter=nb_filter,
filter_length=filter_length,
border_mode='valid',
activation='relu',
subsample_length=1))佛教起源地
# 池化层
model.add(MaxPooling1D(pool_length=pool_length))
# LSTM 循环层
model.add(LSTM(lstm_output_size))
# 全连接层，只有⼀个神经元，输⼊是否为正⾯情感值
model.add(Den(1))
model.add(Activation('sigmoid')) # sigmoid判断情感（此处来做⽂本的情感分类问题）
model.summary() # 模型概述
optimizer='adam',
metrics=['accuracy'])
# 训练
model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch,
validation_data=(X_test, y_test))
自动档车正确起步方法输⼊[100, 128]的序列（100为序列长度，50为词嵌⼊维度），经过（池化层为MaxPooling1D，） Co
nvlution1D(nb_filters=64, filter_length=5) 后，变为 [96, 64]，再经过 MaxPooling1D(pool_length=4) 后，变成了 [24, 64]。其模型维度结构如图所⽰：
Layer (type) Output Shape Param # Connected to
==================================================================================================== embedding_1 (Embedding) (None, 100, 128) 2560000 embedding_input_1[0][0]
____________________________________________________________________________________________________ dropout_1 (Dropout) (None, 100, 128) 0 embedding_1[0][0]
____________________________________________________________________________________________________ convolution1d_1 (Convolution1D) (None, 96, 64) 41024 dropout_1[0][0]
____________________________________________________________________________________________________ maxpooling1d_1 (MaxPooling1D) (None, 24, 64) 0 convolution1d_1[0][0]
____________________________________________________________________________________________________ lstm_1 (LSTM) (None, 70) 37800 maxpooling1d_1[0][0]
____________________________________________________________________________________________________ den_1 (Den) (None, 1) 71 lstm_1[0][0]
____________________________________________________________________________________________________ activation_1 (Activation) (None, 1) 0 den_1[0][0]
==================================================================================================== CNN-LSTM的结构化写法：
inputs = Input(shape=(1, 3)) # 输⼊特征接收维度
a=Dropout(0.25)(inputs)
conv=Convolution1D(10, 1,strides=1,padding="valid", dilation_rate=1)(a)#filters, kernel_size, strides=1
max=MaxPooling1D(pool_length=pool_length)(conv)
lstm1=LSTM(lstm_output_size)(max)
output = Den(1, activation='linear')(lstm1) # 输出类别（此次来做简单的线性预测问题）
model = Model(inputs=inputs, outputs=output) # 初始命名训练的模型为model
model.summary()
其模型维度结构如图所⽰：
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
酵母片的作用与功效
input_1 (InputLayer) (None, 1, 3) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 1, 3) 0
_________________________________________________________________
conv1d_1 (Conv1D) (None, 1, 10) 40
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 1, 10) 0
_________________________________________________________________
lstm_1 (LSTM) (None, 70) 22680
_________________________________________________________________
den_1 (Den) (None, 1) 71
=================================================================
Total params: 22,791
Trainable params: 22,791
Non-trainable params: 0
_________________________________________________________________东北四大顺口溜
