Keras seq2seq example save issue

Asked Sep 06 '18 at 05:22

Active Sep 06 '18 at 07:35

Viewed 493 times

Hello everyone!

I just tried keras seq2seq example(link).

It works well, but the problem happens when I try to save the trained model.

I had never fixed the code. Is there anyone who already know about this issue?

Please help me!

Error:

/home/anaconda3/envs/tensorflow/lib/python3.5/site-packages/keras/engine/network.
py:872: UserWarning: Layer lstm_2 was passed non-serializable keyword arguments: 
{'initial_state': [<tf.Tensor 'lstm_1/while/Exit_2:0' shape=(?, 128) dtype=float32>
, <tf.Tensor 'lstm_1/while/Exit_3:0' shape=(?, 128) dtype=float32>]}. They will 
not be included in the serialized model (and thus will be missing at 
deserialization time).'. They will not be included '

edited Sep 06 '18 at 07:35

asked Sep 06 '18 at 05:22

INDI

that's just a warning, are you actually unable to deserialize and run the model? – Tommaso Pasini Sep 06 '18 at 13:59
Oh, you were right. It was possible to load and run the model and the result is same. I think I had cold feet. Thanks :) – INDI Sep 07 '18 at 06:03

Keras seq2seq example save issue

0 Answers0