Prabhsimran Singh

@nidhikamath91 apparently TF serving doesn't support stateful models. https://github.com/tensorflow/serving/issues/724

https://stackoverflow.com/questions/49471395/adding-support-for-stateful-rnn-models-within-the-tf-serving-api

@nidhikamath91 I don't think that's possible since it's an autoencoding RNN application.

@nidhikamath91 you can't feed tensors into input placeholders, just convert them to numpy arrays before doing so.

@nidhikamath91 yes you could try constructing the graph in such a way that you only need to feed the seed id into issue placeholder at runtime which in turn passes...