使用keras的LTSM时间序列预测

Question

我正在尝试由keras在R（rstudio）中编写一个简单的LTSM模型，我想出了以下代码

scores <- model %>% evaluate(
  x_test, y_test,
  batch_size = batch_size
)

cat('Test score:', scores[[1]])
cat('Test accuracy', scores[[2]])

但是实际上，它在模型％>％fit上失败，并提示我：

 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 3 arrays: [array([[1.],
       [2.],
       [3.],
       [4.],
       [5.]], dtype=float32), array([[10.],
       [20.],
       [30.],
       [40.],
       [50.]], dtype=float32), array([[100.],
       [200.],
... 

我正在尝试编写一个能够预测3个输出时间序列数据的LTSM。