Skip to content

Latest commit

 

History

History
11 lines (7 loc) · 495 Bytes

README.md

File metadata and controls

11 lines (7 loc) · 495 Bytes

lor-prediction

Submission to Sirajology's coding challenge: https://www.youtube.com/watch?v=SJDEOWLHYVo

Generates sequences similar to passages in The Lord of The Rings using a LSTM neural network. Trained on Tolkiens trilogy

The three books are in the input.txt file The model can be trained and tested with the train_network and create_text jupyter notebooks respectivly

The results for training with 10 epochs using Google Datalab (cloud computing) is in the LOR_network.tflearn file.