Why use a tuple in model.fit about tf2.0_deepfm HOT 2 OPEN

Because the input x of "model.fit()" must like follow:
x: Input data. It could be:
- A Numpy array (or array-like), or a list of arrays
(in case the model has multiple inputs).
- A TensorFlow tensor, or a list of tensors
(in case the model has multiple inputs).
- A dict mapping input names to the corresponding array/tensors,
if the model has named inputs.
- A tf.data dataset. Should return a tuple
of either (inputs, targets) or
(inputs, targets, sample_weights).
- A generator or keras.utils.Sequence returning (inputs, targets)
or (inputs, targets, sample weights).

from tf2.0_deepfm.

Yes. I understand. Thank you. I am also wondering your inputs X; it consists of train_feature_index.values and train_feature_value.values. Why would you separate two sets of inputs from the dataset, instead of one record one set of features (i.e., generally one input) ?

from tf2.0_deepfm.