Resources, utils and test code for Recurrent Neural Networks (RNN).
Current main focus and coverage for this repository is around text-generation.
You can find two separate sets of resources, one related to model training and the other related to model serving and consuming (see also this Medium entry).
For training refer to:
In the src folder you will find instead implementation for the consuming middleware. It includes a basic class responsible for text pre and post-processing, a procedure for text generation (which builds upon multiple model calls and secondary requirements) and a proxy to handle different models.
- Karpathy’s article
- Crash Course in Recurrent Neural Networks
- Denny Britz tutorials
- Understanding LSTM
- A noob’s guide to implementing RNN-LSTM using Tensorflow
- Predicting sequences of vectors (regression) in Keras using RNN - LSTM
- Cornell Movie — Dialogs Corpus
- dataset_30000_published_crossword_puzzles
- short text corpus
- fortune cookies galore
Released under version 2.0 of the Apache License.