gpt4 book ai didi

r - 了解 R 中 rnn 模型的 Keras 预测输出

转载 作者:行者123 更新时间:2023-11-30 08:23:34 26 4
gpt4 key购买 nike

我正在通过执行有关预测温度的 tutorial 来尝试 R 中的 Keras 包。然而,该教程没有解释如何使用经过训练的 RNN 模型进行预测,我想知道如何做到这一点。为了训练模型,我使用了从教程中复制的以下代码:

dir.create("~/Downloads/jena_climate", recursive = TRUE)
download.file(
"https://s3.amazonaws.com/keras-datasets/jena_climate_2009_2016.csv.zip",
"~/Downloads/jena_climate/jena_climate_2009_2016.csv.zip"
)
unzip(
"~/Downloads/jena_climate/jena_climate_2009_2016.csv.zip",
exdir = "~/Downloads/jena_climate"
)

library(readr)
data_dir <- "~/Downloads/jena_climate"
fname <- file.path(data_dir, "jena_climate_2009_2016.csv")
data <- read_csv(fname)

data <- data.matrix(data[,-1])

train_data <- data[1:200000,]
mean <- apply(train_data, 2, mean)
std <- apply(train_data, 2, sd)
data <- scale(data, center = mean, scale = std)

generator <- function(data, lookback, delay, min_index, max_index,
shuffle = FALSE, batch_size = 128, step = 6) {
if (is.null(max_index))
max_index <- nrow(data) - delay - 1
i <- min_index + lookback
function() {
if (shuffle) {
rows <- sample(c((min_index+lookback):max_index), size = batch_size)
} else {
if (i + batch_size >= max_index)
i <<- min_index + lookback
rows <- c(i:min(i+batch_size, max_index))
i <<- i + length(rows)
}

samples <- array(0, dim = c(length(rows),
lookback / step,
dim(data)[[-1]]))
targets <- array(0, dim = c(length(rows)))

for (j in 1:length(rows)) {
indices <- seq(rows[[j]] - lookback, rows[[j]],
length.out = dim(samples)[[2]])
samples[j,,] <- data[indices,]
targets[[j]] <- data[rows[[j]] + delay,2]
}

list(samples, targets)
}
}

lookback <- 1440
step <- 6
delay <- 144
batch_size <- 128

train_gen <- generator(
data,
lookback = lookback,
delay = delay,
min_index = 1,
max_index = 200000,
shuffle = TRUE,
step = step,
batch_size = batch_size
)

val_gen = generator(
data,
lookback = lookback,
delay = delay,
min_index = 200001,
max_index = 300000,
step = step,
batch_size = batch_size
)

test_gen <- generator(
data,
lookback = lookback,
delay = delay,
min_index = 300001,
max_index = NULL,
step = step,
batch_size = batch_size
)

# How many steps to draw from val_gen in order to see the entire validation set
val_steps <- (300000 - 200001 - lookback) / batch_size

# How many steps to draw from test_gen in order to see the entire test set
test_steps <- (nrow(data) - 300001 - lookback) / batch_size

library(keras)

model <- keras_model_sequential() %>%
layer_flatten(input_shape = c(lookback / step, dim(data)[-1])) %>%
layer_dense(units = 32, activation = "relu") %>%
layer_dense(units = 1)

model %>% compile(
optimizer = optimizer_rmsprop(),
loss = "mae"
)

history <- model %>% fit_generator(
train_gen,
steps_per_epoch = 500,
epochs = 20,
validation_data = val_gen,
validation_steps = val_steps
)

我尝试使用下面的代码来预测温度。如果我是正确的,这应该给我每批的标准化预测温度。因此,当我对这些值进行非规范化并对其进行平均时,我得到了预测的温度。这是正确的吗?如果正确,则预测哪个时间(最新观察时间 + 延迟?)?

prediction.set <- test_gen()[[1]]
prediction <- predict(model, prediction.set)

此外,使用 keras::predict_generator() 和 test_gen() 函数的正确方法是什么?如果我使用以下代码:

model %>% predict_generator(generator = test_gen,
steps = test_steps)

它给出了这个错误:

error in py_call_impl(callable, dots$args, dots$keywords) : 
ValueError: Error when checking model input: the list of Numpy
arrays that you are passing to your model is not the size the model expected.
Expected to see 1 array(s), but instead got the following list of 2 arrays:
[array([[[ 0.50394005, 0.6441838 , 0.5990761 , ..., 0.22060473,
0.2018686 , -1.7336458 ],
[ 0.5475698 , 0.63853574, 0.5890239 , ..., -0.45618412,
-0.45030192, -1.724062...

最佳答案

注意:我对 R 语法的熟悉程度很低,因此遗憾的是我无法使用 R 为您提供答案。相反,我在答案中使用 Python。我希望你能轻松地将我的话翻译回 R。

<小时/>

... If I am correct, this should give me the normalized predicted temperature for every batch.

是的,没错。由于您已经使用标准化标签对其进行了训练,因此预测将被标准化:

data <- scale(data, center = mean, scale = std)

因此,您需要使用计算的平均值和标准差对值进行非规范化,以找到真正的预测:

pred = model.predict(test_data)
denorm_pred = pred * std + mean

... for which time is then predicted (latest observation time + delay?)

没错。具体来说,由于在此特定数据集中每十分钟记录一次新的观测值并且您设置了延迟=144,因此这意味着预测值是提前 24 小时的温度(即 144 * 10 = 1440分钟 = 24 小时)距离上次给定的观察。

Also, what is the correct way to use keras::predict_generator() and the test_gen() function?

predict_generator采用一个生成器,它仅提供测试样本作为输出,而不提供标签(因为我们在执行预测时不需要标签;在训练时需要标签,即 fit_generator() 和评估时)模型,即 evaluate_generator() )。这就是为什么错误提到您需要传递一个数组而不是两个数组。因此,您需要定义一个仅提供测试样本的生成器,或者在Python中,一种替代方法是将现有的生成器包装在另一个仅提供输入样本的函数中(我不知道您是否可以在R中执行此操作) ):

def pred_generator(gen):
for data, labels in gen:
yield data # discards labels

preds = model.predict_generator(pred_generator(test_generator), number_of_steps)

您需要提供另一个参数,即生成器覆盖测试数据中所有样本的步数。实际上我们有num_steps =total_number_of_samples/batch_size。例如,如果您有 1000 个样本,每次生成器生成 10 个样本,则需要使用生成器执行 1000/10 = 100 步骤。

奖励:要查看模型的性能如何,您可以使用现有的测试生成器(即 test_gen)来使用 evaluate_generator:

loss = model.evaluate_generator(test_gen, number_of_steps)

给定的loss也是标准化的,要对其进行非标准化(为了更好地了解预测误差),您只需将其乘以std(您不需要需要添加 mean 因为您使用的是 mae,即平均绝对误差,作为损失函数):

denorm_loss = loss * std

这会告诉您您的预测平均偏离多少。例如,如果您要预测温度,denorm_loss 为 5 意味着预测平均偏离 5 度(即低于或高于实际值)。

<小时/>

更新:对于预测,您可以使用 R 中的现有生成器定义新的生成器,如下所示:

pred_generator <- function(gen) {
function() { # wrap it in a function to make it callable
gen()[1] # call the given generator and get the first element (i.e. samples)
}
}

preds <- model %>%
predict_generator(
generator = pred_generator(test_gen), # pass test_gen directly to pred_generator without calling it
steps = test_steps
)

evaluate_generator(model, test_gen, test_steps)

关于r - 了解 R 中 rnn 模型的 Keras 预测输出,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/49032027/

26 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com