This repository has been archived by the owner on Sep 6, 2022. It is now read-only.

How to predict unlabeling test data? #4

Open

qute012 opened this issue Feb 14, 2020 · 0 comments

qute012 commented Feb 14, 2020

Hi. I'm Studying Speech Recognition. I have some question.
This model takes 4 inputs, below code.

self.model = tf.keras.Model(inputs=[input_data, labels, input_length, label_length], outputs=[loss_out])

If this model predicts test case that is unlabeled, i can't give 'labels', 'label_length' as inputs.
How can i do?

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.