我正在尝试使用其他来源的相同波士顿住房数据集来复制以下深度学习示例。
https://jjallaire.github.io/deep--with-r-notebooks/notebooks/3.6-predicting-house-prices.nb.html
最初的数据源是：
library(keras) dataset <- dataset_boston_housing()
另外，我尝试使用：
library(mlbench)
data(BostonHousing)
数据集之间的区别是：
mlbench中的数据集包含列名称。
来自keras的数据集已经在测试和训练之间分配。
来自keras的集合由包含矩阵的列表组成，而来自mlbench的数据集是一个数据框
第四列包含无法从mlbench数据集进行预处理的分类变量“ chas”，而可以从keras数据集进行预处理。为了将苹果与苹果进行比较，我已从两个数据集中删除了此列。
为了比较这两个数据集，我将来自keras的训练和测试集合并为1个数据集。在此之后，我将来自keras的合并数据集与mlbench和summary（）进行了比较，并且每个特征（最小值，最大值，中位数，均值）都相同。
由于来自keras的数据集已经在测试和训练之间划分（80-20），因此我只能对深度学习过程使用一个训练集。该训练集的validation_mae约为2.5。看到此图：
如果我将mlbench中的数据分区为0.8，以构造一个大小相似的训练集，运行深度学习代码并执行几次，则我永远不会达到2.5左右的validation_mae。范围在4到6之间。此图为输出示例：
有人知道造成这种差异的原因是什么吗？
来自keras的数据集的代码：
library(keras)
dataset <- dataset_boston_housing()
c(c(train_data, train_targets), c(test_data, test_targets)) %<-% dataset
train_data <- train_data[,-4]
test_data <- test_data[,-4]
mean <- apply(train_data, 2, mean)
std <- apply(train_data, 2, sd)
train_data <- scale(train_data, center = mean, scale = std)
test_data <- scale(test_data, center = mean, scale = std)
# After this line the code is the same for both code examples.
# =========================================
# Because we will need to instantiate the same model multiple times,
# we use a function to construct it.
build_model <- function() {
model <- keras_model_sequential() %>%
layer_dense(units = 64, activation = "relu",
input_shape = dim(train_data)[[2]]) %>%
layer_dense(units = 64, activation = "relu") %>%
layer_dense(units = 1)
model %>% compile(
optimizer = "rmsprop",
loss = "mse",
metrics = c("mae")
)
}
k <- 4
indices <- sample(1:nrow(train_data))
folds <- cut(1:length(indices), breaks = k, labels = FALSE)
num_epochs <- 100
all_scores <- c()
for (i in 1:k) {
cat("processing fold #", i, "\n")
# Prepare the validation data: data from partition # k
val_indices <- which(folds == i, arr.ind = TRUE)
val_data <- train_data[val_indices,]
val_targets <- train_targets[val_indices]
# Prepare the training data: data from all other partitions
partial_train_data <- train_data[-val_indices,]
partial_train_targets <- train_targets[-val_indices]
# Build the Keras model (already compiled)
model <- build_model()
# Train the model (in silent mode, verbose=0)
model %>% fit(partial_train_data, partial_train_targets,
epochs = num_epochs, batch_size = 1, verbose = 0)
# Evaluate the model on the validation data
results <- model %>% evaluate(val_data, val_targets, verbose = 0)
all_scores <- c(all_scores, results$mean_absolute_error)
}
all_scores
mean(all_scores)
# Some memory clean-up
k_clear_session()
num_epochs <- 500
all_mae_histories <- NULL
for (i in 1:k) {
cat("processing fold #", i, "\n")
# Prepare the validation data: data from partition # k
val_indices <- which(folds == i, arr.ind = TRUE)
val_data <- train_data[val_indices,]
val_targets <- train_targets[val_indices]
# Prepare the training data: data from all other partitions
partial_train_data <- train_data[-val_indices,]
partial_train_targets <- train_targets[-val_indices]
# Build the Keras model (already compiled)
model <- build_model()
# Train the model (in silent mode, verbose=0)
history <- model %>% fit(
partial_train_data, partial_train_targets,
validation_data = list(val_data, val_targets),
epochs = num_epochs, batch_size = 1, verbose = 1
)
mae_history <- history$metrics$val_mean_absolute_error
all_mae_histories <- rbind(all_mae_histories, mae_history)
}
average_mae_history <- data.frame(
epoch = seq(1:ncol(all_mae_histories)),
validation_mae = apply(all_mae_histories, 2, mean)
)
library(ggplot2)
ggplot(average_mae_history, aes(x = epoch, y = validation_mae)) + geom_line()
来自mlbench的数据集的代码（在带有“ =====”的行之后，代码与上面的代码相同：
library(dplyr)
library(mlbench)
library(groupdata2)
data(BostonHousing)
parts <- partition(BostonHousing, p = 0.2)
test_data <- parts[[1]]
train_data <- parts[[2]]
train_targets <- train_data$medv
test_targets <- test_data$medv
train_data$medv <- NULL
test_data$medv <- NULL
train_data$chas <- NULL
test_data$chas <- NULL
mean <- apply(train_data, 2, mean)
std <- apply(train_data, 2, sd)
train_data <- scale(train_data, center = mean, scale = std)
test_data <- scale(test_data, center = mean, scale = std)
library(keras)
# After this line the code is the same for both code examples.
# =========================================
build_model <- function() {
model <- keras_model_sequential() %>%
layer_dense(units = 64, activation = "relu",
input_shape = dim(train_data)[[2]]) %>%
layer_dense(units = 64, activation = "relu") %>%
layer_dense(units = 1)
model %>% compile(
optimizer = "rmsprop",
loss = "mse",
metrics = c("mae")
)
}
k <- 4
indices <- sample(1:nrow(train_data))
folds <- cut(1:length(indices), breaks = k, labels = FALSE)
num_epochs <- 100
all_scores <- c()
for (i in 1:k) {
cat("processing fold #", i, "\n")
# Prepare the validation data: data from partition # k
val_indices <- which(folds == i, arr.ind = TRUE)
val_data <- train_data[val_indices,]
val_targets <- train_targets[val_indices]
# Prepare the training data: data from all other partitions
partial_train_data <- train_data[-val_indices,]
partial_train_targets <- train_targets[-val_indices]
# Build the Keras model (already compiled)
model <- build_model()
# Train the model (in silent mode, verbose=0)
model %>% fit(partial_train_data, partial_train_targets,
epochs = num_epochs, batch_size = 1, verbose = 0)
# Evaluate the model on the validation data
results <- model %>% evaluate(val_data, val_targets, verbose = 0)
all_scores <- c(all_scores, results$mean_absolute_error)
}
all_scores
mean(all_scores)
# Some memory clean-up
k_clear_session()
num_epochs <- 500
all_mae_histories <- NULL
for (i in 1:k) {
cat("processing fold #", i, "\n")
# Prepare the validation data: data from partition # k
val_indices <- which(folds == i, arr.ind = TRUE)
val_data <- train_data[val_indices,]
val_targets <- train_targets[val_indices]
# Prepare the training data: data from all other partitions
partial_train_data <- train_data[-val_indices,]
partial_train_targets <- train_targets[-val_indices]
# Build the Keras model (already compiled)
model <- build_model()
# Train the model (in silent mode, verbose=0)
history <- model %>% fit(
partial_train_data, partial_train_targets,
validation_data = list(val_data, val_targets),
epochs = num_epochs, batch_size = 1, verbose = 1
)
mae_history <- history$metrics$val_mean_absolute_error
all_mae_histories <- rbind(all_mae_histories, mae_history)
}
average_mae_history <- data.frame(
epoch = seq(1:ncol(all_mae_histories)),
validation_mae = apply(all_mae_histories, 2, mean)
)
library(ggplot2)
ggplot(average_mae_history, aes(x = epoch, y = validation_mae)) + geom_line()
谢谢！
最佳答案
在这里写，因为我无法发表评论...
我检查了mlbench数据集here，并说它包含原始波士顿数据集的14列和5列其他列。不确定您是否有错误的数据集，因为您声明数据集的列数没有差异。
另一个猜测可能是，第二个示例图来自停留在局部最小值中的模型。为了获得更多可比较的模型，您可能需要使用相同的种子，以确保权重等的inizializations是相同的以获得相同的结果。
希望这会有所帮助，随时问。
关于r - 这些数据集之间使用R进行深度学习会导致MALE结果差异的原因是什么？，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/58051377/