support for dictionary-type loss functions without explicitly declaring None

[WJiang0123]

In previous versions of Keras, when providing a loss function as a dictionary for models with multiple outputs, the compileLoss function would automatically assign a default value for outputs without a defined loss. The relevant code was:

                if name in loss:
                    if loss[name]:
                        flat_losses.append(get_loss(loss[name], yt, yp))
                    else:
                        flat_losses.append(None)
                else:
                    flat_losses.append(None)

However, in the latest version, flat_losses is now simply:
flat_losses = tree.flatten(loss)
Is there a way to reintroduce support for dictionary-type loss functions without explicitly declaring None for undefined losses? This change reduces flexibility in using dictionary-based loss definitions.

[fchollet]

Thanks, this is a reasonable ask. Would you be able to open a PR for the change?