Hello there,
I’m prety sure of the answer as I been searching alot, but I still want to make sure I’m not mistaken…
In openNMT-py, we are able to know the predict score for each sentence piece translated by the model (in the log_file), but I haven’t been able to achieve the same thing with openNMT-tf.
Am I missing anything, or it’s not something available with openNMT-tf?
Best regards,
Samuel