LSTM序列到序列的数据格式处理

输入数据是10000×1的元胞数组，每个元胞是21×100的矩阵，输出数据是10000×1的元胞数组，每个元胞是1×13的矩阵，这样是按照序列到序列来处理吗？如果是，数据格式又该如何改呢？

Answer 1

[Varun]

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!