Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow
Python
Latest commit 1ff5c53 Jan 8, 2017 @vnikme vnikme committed on GitHub Merge pull request #71 from sherjilozair/vnik/removewarnings
Change global variables initializers from deprecated to new ones.

README.md

char-rnn-tensorflow

Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow.

Inspired from Andrej Karpathy's char-rnn.

Requirements

Basic Usage

To train with default parameters on the tinyshakespeare corpus, run python train.py.

To sample from a checkpointed model, python sample.py.

Roadmap

  • Add explanatory comments
  • Expose more command-line arguments
  • Compare accuracy and performance with char-rnn