search

guillaume-chevalier / seq2seq-signal-prediction

Signal forecasting with a Sequence-to-Sequence (seq2seq) Recurrent Neural Network (RNN) model in TensorFlow - Guillaume Chevalier
Apache License 2.0
1.08k stars 294 forks source link

How to predict after training #19

Open behnam-samadi opened 4 years ago

behnam-samadi commented 4 years ago

Hi @guillaume-chevalier Thank you very much for open sourcing this awesome project. Unfortunately I have no experience with tensorflow2 and neuraxle. In order to use your code with my sequential data, I replaced the data_inputs and expected_outputs in seq2seq.py with my own data. The training procedure was done and losses were decreasing but my question is that is there a way to use trained model for prediction on new samples? and what about saving model to use it later for inference Thanks for pointing me in the right direction.

guillaume-chevalier commented 4 years ago

Saving will soon be documented here, although it is not already the case: https://www.neuraxle.org/stable/examples/index.html

CC: @alexbrillant