Input LSTM for multidimensional time series

Question

I am trying to use LSTM for time series predictions for multidimensional data. I have 50,000 samples with 15 sizes. I want to use appearance 10. What will be the input form of the LSTM layer. Will it

(samples,look back,dimension) = (50000,10,15) 

or

 (samples,dimension, look back) = (50000,15,10) 

I am using Keras.

Answer 1

As you can read in the Keras Documentation:

Input forms

3D tensor with form (batch_size, timesteps, input_dim) .

So, the “time” dimension is the first. Since your time size is 10, your input form will be (50000,10,15)

Hope this helps :-)