thomwolf / char-rnn.pytorch

PyTorch implementation of char-rnn (character-level language model)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

char-rnn.pytorch

A PyTorch implementation of char-rnn for character-level text generation. This is copied from the Practical PyTorch series.

Training

Download this Shakespeare dataset (from the original char-rnn) as shakespeare.txt. Or bring your own dataset — it should be a plain text file (preferably ASCII).

Run train.py with the dataset filename to train and save the network:

> python train.py shakespeare.txt

Training for 2000 epochs...
(... 10 minutes later ...)
Saved as shakespeare.pt

After training the model will be saved as [filename].pt.

Training options

Usage: train.py [filename] [options]

Options:
--model            Whether to use LSTM or GRU units    gru
--n_epochs         Number of epochs to train           2000
--print_every      Log learning rate at this interval  100
--hidden_size      Hidden size of GRU                  50
--n_layers         Number of GRU layers                2
--learning_rate    Learning rate                       0.01
--chunk_len        Length of training chunks           200
--batch_size       Number of examples per batch        100
--cuda             Use CUDA

Generation

Run generate.py with the saved model from training, and a "priming string" to start the text with.

> python generate.py shakespeare.pt --prime_str "Where"

Where, you, and if to our with his drid's
Weasteria nobrand this by then.

AUTENES:
It his zersit at he

Generation options

Usage: generate.py [filename] [options]

Options:
-p, --prime_str      String to prime generation with
-l, --predict_len    Length of prediction
-t, --temperature    Temperature (higher is more chaotic)
--cuda               Use CUDA

About

PyTorch implementation of char-rnn (character-level language model)

License:MIT License


Languages

Language:Python 100.0%