Error when 'X' size is different to 'y' for multi-input networks.

[ivsanro1]

Hello.

If my model is not a Sequential() one because it has several inputs, X is the tuple that contains the vectors (these vectors DO have the same lenght than 'y', but X does not). Do you have any plans of allowing this?

Thanks

[soroushj]

Hi @ivsanro1, sorry for my delayed response, and thank you for your feedback.

Support for models with multiple inputs and outputs sounds like a good idea. It's not my top priority at the moment, but I may implement it in the future.

Of course, PRs are welcome. A note for anyone who may want to implement this: If x or y are a list, tuple, or dictionary, they should be treated as multiple inputs or outputs. Otherwise, they are expected to be a NumPy array and a single input or output.