多元LSTM的keras输入形状

我试图在keras中建立一个LSTM模型,其中有两个输入

y 是带形状的输出(100,10) x 是带形状的输入(100,20)

library(keras)

x_train_vec <- matrix(rnorm(2000), ncol = 20, nrow = 100)
x_train_arr <- array(data = x_train_vec, dim = c(nrow(x_train_vec), 1, 20))


y_train_vec <- matrix(rnorm(1000), ncol = 10, nrow = 100)
y_train_arr <- array(data = y_train_vec, dim = c(nrow(x_train_vec), 1, 10))


> dim(x_train_arr)
[1] 100   1  20
> dim(y_train_arr)
[1] 100   1  10

现在我想拟合LSTM模型

model <- keras_model_sequential()

model %>%
  layer_lstm(units            = 50, 
             input_shape      = c(1,10), 
             batch_size       = 1) %>% 
  layer_dense(units = 1)

model %>% 
  compile(loss = 'mae', optimizer = 'adam')

model %>% fit(x          = x_train_arr, 
              y          = y_train_arr, 
              batch_size = 1,
              epochs     = 10, 
              verbose    = 1, 
              shuffle    = FALSE)

但我有个错误:

py_call_impl中的错误(可调用,点$args,点$keywords):
值错误:检查输入时出错:期望lstm_21_输入具有 形状(1,10),但得到了形状为(1,20)的数组

如果将输入大小更改为c(1,20),则得到:

py_call_impl中的错误(可调用,点$args,点$keywords):
值错误:检查目标时出错:期望密集度为13的值为2 维度,但得到了形状为(100,1,10)的数组

我也玩不同的设置,但它从来没有工作。