Skip to content

Latest commit

 

History

History
26 lines (16 loc) · 752 Bytes

README.md

File metadata and controls

26 lines (16 loc) · 752 Bytes

Code char rnn in Keras

A Simple POC.

Multi-layer recurrent neural networks for training and sampling from texts, inspired by karpathy/char-rnn and ekzhang/char-rnn.

Trained on a dataset of python code functions.

Requirements

This code is written in Python 3, and it requires the Keras deep learning library.

pip install -r requirements.txt

Usage

To train the model with default settings use:

$ python train.py

To use the model use the 'inference.ipynb' notebook.

The dataset can be downloaded from here