model variable vs base_model

[roccolocko]

Hello ypwhs,
On the ctc code you are creating a model called model:
model = Model(input=[input_tensor, labels, input_length, label_length], output=[loss_out])

And that is the one you train, but when you make the prediction you use a the model called base_model.
y_pred = base_model.predict(X_test)

Why is that? Is it correct?
Shouldn't you use model.predict? If yes, what would be a correct way to call it, since is waiting for 4 parameters, what should it be sent on "labels", "input_length" and "label_length".

Thank you.

[syw2014]

@roccolocko Have you solved this problem?

[ypwhs]

Due to the limitations of keras, ctc loss must be built in the model, so in fact model is just a training model, base_model is the real model.

[syw2014]

@ypwhs Thank you for project and your reply, Got it !