[英]Correct input_shape for an LSTM in kerasR
I see a lot of help for similar topics in python but I was using the R implementation and can't seem to replicate any of the suggested solutions. 我在python中的类似主题上看到了很多帮助,但是我使用的是R实现,似乎无法复制任何建议的解决方案。
I am attempting to setup an LSTM like so, 我试图像这样设置一个LSTM,
mod <- Sequential()
mod$add(LSTM(50, activation = 'relu', dropout = 0.25, input_shape = c(dim(X_train_scaled)[1], dim(X_train_scaled)[2]), return_sequences = TRUE))
mod$add(Dense(1))
keras_compile(mod, loss = 'mean_squared_error', optimizer = 'adam')
keras_fit(mod, X_train_scaled, Y_train, batch_size = 72, epochs = 10, verbose = 1, validation_split = 0.1)
However, when I run the keras_fit
I get the following error, 但是,当我运行
keras_fit
时,出现以下错误,
Error in py_call_impl(callable, dots$args, dots$keywords) : ValueError: Error when checking input: expected lstm_36_input to have 3 dimensions, but got array with shape (2000, 44)
The X_train is a numeric matrix with 2000 rows and 44 columns that represent 2000 timesteps and the values of 44 features at each timestep X_train是一个数字矩阵,具有2000行和44列,分别代表2000个时间步和每个时间步的44个要素的值
The Y_train is a numeric vector of length 2000 Y_train是长度为2000的数值向量
I should add that when I attempt to use a 3 dimensional value for the input_shape
so as to specify an input shape that follows the (samples, timesteps, features)
structure, I get an error like this when I add the LSTM layer to the model, 我应该补充一点,当我尝试对
input_shape
使用3维值以指定遵循(samples, timesteps, features)
结构的输入形状时,将LSTM层添加到模型中时会出现这样的错误,
Error in py_call_impl(callable, dots$args, dots$keywords) : ValueError: Input 0 is incompatible with layer lstm_37: expected ndim=3, found ndim=4
Your train matrix should be 3-dimensional (samples, timesteps, features)
. 您的训练矩阵应该是3维的
(samples, timesteps, features)
。 Then you have to use 2nd and 3rd dimensions for input_shape
: 然后,您必须将2nd和3rd维度用于
input_shape
:
input_shape = c(dim(X_train_scaled)[2], dim(X_train_scaled)[3])
Also, number of rows in your dataset is samples
, not timesteps
. 此外,数据集中的行数是
samples
,而不是timesteps
。 You can read more about samples
, timesteps
and features
here . 您可以在此处阅读有关
samples
, timesteps
和features
更多信息。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.