Hello 正杰 康,
I am not exactly sure what kind of data you’re working with, but I found this example which seems to be along the lines of what you’re trying to implement: https://www.mathworks.com/help/deeplearning/ug/sequence-to-sequence-classification-using-deep-learning.html
The data is in the form of a cell array, where each cell has a matrix of features and their values. The output cell array size depends on the size of the test cell array being passed when the model is called to predict the values.
Hope this helps!
