之前介绍过使用keras进行二分类，多分类。使用的是keras框架中的贯序模型。
model <- keras_model_sequential()
# define and compile the model
model %>%
layer_dense(units = 64, activation = 'relu', input_shape = c(20)) %>%
layer_dropout(rate = 0.5) %>%
layer_dense(units = 64, activation = 'relu') %>%
layer_dropout(rate = 0.5) %>%
layer_dense(units = 1, activation = 'sigmoid') %>%
compile(
loss = 'binary_crossentropy',
optimizer = 'rmsprop',
metrics = c('accuracy')
)
# train
model %>% fit(x_train, y_train, epochs = 20, batch_size = 128)
# evaluate
score = model %>% evaluate(x_test, y_test, batch_size=128)
用的是这个模型
model <- keras_model_sequential()
这样建立的深度学习模型就是一层一层的网络结构。
但是深度网络结构可以是多输入和多输出的，这样就不能使用贯序模型模型进行定义网络结构，这个时候就需要keras框架里面一种更加灵活的定义方式。
下面介绍一个简单的例子：
首先你需要定义一个输入:
inputs <- layer_input(shape = c(100))
其次，定义输出：
prediction <- inputs%>%layer_dense(units = 30,
activation = "relu",
input_shape = 100) %>%
layer_dropout(rate = 0.4) %>% layer_dense(units = 30, activation = "relu") %>%
layer_dropout(rate = 0.4) %>% layer_dense(units = 1, activation = "sigmoid")
创建以及编译模型
x_train <-
matrix(runif(100000, min = 0, max = 2), nrow = 1000, ncol = 100)
y_train <- matrix(sample(
x = 0:1,
size = 1000,
replace = T
))
x_test <-
matrix(runif(100000, min = 0, max = 2), nrow = 1000, ncol = 100)
y_test <- matrix(sample(
x = 0:1,
size = 1000,
replace = T
))
# 以上是数据
# 创建模型
model <- keras_model(inputs = inputs,outputs = prediction)
# 编译模型
model %>% compile(
loss = 'binary_crossentropy',
optimizer = 'rmsprop',
metrics = c('accuracy')
)
# 训练模型
model%>%fit(x_train,y_train,BATCH_SIZE=80,epochs = 40)
image.png
评估模型
model %>% evaluate(x_test,y_test)
1000/1000 [==============================] - 1s 531us/step
$loss
[1] 0.7711746
$acc
[1] 0.473
与之对应的贯序模型的定义方式如下：
x_train <-
matrix(runif(100000, min = 0, max = 2), nrow = 1000, ncol = 100)
y_train <- matrix(sample(
x = 0:1,
size = 1000,
replace = T
))
x_test <-
matrix(runif(100000, min = 0, max = 2), nrow = 1000, ncol = 100)
y_test <- matrix(sample(
x = 0:1,
size = 1000,
replace = T
))
model <- keras_model_sequential()
model %>% layer_dense(units = 30,
activation = "relu",
input_shape = 100) %>%
layer_dropout(rate = 0.4) %>% layer_dense(units = 30, activation = "relu") %>%
layer_dropout(rate = 0.4) %>% layer_dense(units = 1, activation = "sigmoid")
model %>% compile(
loss = 'binary_crossentropy',
optimizer = 'rmsprop',
metrics = c('accuracy')
)
model %>% fit(x_train,y_train,epochs = 30,batch_size = 70,validation_split =0.2)
model %>% evaluate(x_test,y_test)
看见差别了没
接下来要干的事，是贯序模型做不了了，我们要训练这样一个模型，模型结构如下图：
image.png
其有两部分输入构成，又对应着两部分输出。
- 定义住输入：
library(keras)
main_input <- layer_input(shape = c(100), dtype = 'int32', name = 'main_input')
lstm_out <- main_input %>%
layer_embedding(input_dim = 10000, output_dim = 512, input_length = 100) %>%
layer_lstm(units = 32)
- 定义副输出：
auxiliary_output <- lstm_out %>%
layer_dense(units = 1, activation = 'sigmoid', name = 'aux_output')
3.定义副输入与主输出：
auxiliary_input <- layer_input(shape = c(5), name = 'aux_input')
main_output <- layer_concatenate(c(lstm_out, auxiliary_input)) %>%
layer_dense(units = 64, activation = 'relu') %>%
layer_dense(units = 64, activation = 'relu') %>%
layer_dense(units = 64, activation = 'relu') %>%
layer_dense(units = 1, activation = 'sigmoid', name = 'main_output')
需要注意的是输出层都定义了名字
- 定义模型
model <- keras_model(
inputs = c(main_input, auxiliary_input),
outputs = c(main_output, auxiliary_output)
)
看一下模型结构：
summary(model)
____________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
============================================================================================
main_input (InputLayer) (None, 100) 0
____________________________________________________________________________________________
embedding_2 (Embedding) (None, 100, 512) 5120000 main_input[0][0]
____________________________________________________________________________________________
lstm_4 (LSTM) (None, 32) 69760 embedding_2[0][0]
____________________________________________________________________________________________
aux_input (InputLayer) (None, 5) 0
____________________________________________________________________________________________
concatenate_2 (Concatenate) (None, 37) 0 lstm_4[0][0]
aux_input[0][0]
____________________________________________________________________________________________
dense_137 (Dense) (None, 64) 2432 concatenate_2[0][0]
____________________________________________________________________________________________
dense_138 (Dense) (None, 64) 4160 dense_137[0][0]
____________________________________________________________________________________________
dense_139 (Dense) (None, 64) 4160 dense_138[0][0]
____________________________________________________________________________________________
main_output (Dense) (None, 1) 65 dense_139[0][0]
____________________________________________________________________________________________
aux_output (Dense) (None, 1) 33 lstm_4[0][0]
============================================================================================
Total params: 5,200,610
Trainable params: 5,200,610
Non-trainable params: 0
_____________________________
5,200,610个参数
- 编译模型
model %>% compile(
optimizer = 'rmsprop',
loss = 'binary_crossentropy',
loss_weights = c(1.0, 0.2)
)
6.训练模型
model %>% fit(
x = list(headline_data, additional_data),
y = list(labels, labels),
epochs = 50,
batch_size = 32
)
注意，我这里没有生成数据
也可以指定不同的损失函数：
model %>% fit(
x = list(main_input = headline_data, aux_input = additional_data),
y = list(main_output = labels, aux_output = labels),
epochs = 50,
batch_size = 32
)
