how to train and test the deep neural network using cell array inputs and targets.

I want to train a deep neural network for predicting the formation of clusters. My inputs and targets are in cell array.

For example xtrain is 30x1 cell array in which each rows of the cell array has definite rows with different number of columns.In the same manner my ytrain is 30x1 cell array in which each rows of the cell array has definite rows with different number of columns.

I have done training the model. the model executes, but when I tried to test the model it doesnt give me the expected results.

Could anyone help me ito know whether the data format of inputs and targets are correct, if correct why I am unable to get the expected results based on training.

Thanks in advance.