https://github.com/yusuketomoto/chainer-char-rnn

karpathy's char-rnn (https://github.com/karpathy/char-rnn) implementation by Chainer
https://github.com/yusuketomoto/chainer-char-rnn

Last synced: 11 days ago
JSON representation

karpathy's char-rnn (https://github.com/karpathy/char-rnn) implementation by Chainer

• Host: GitHub
• URL: https://github.com/yusuketomoto/chainer-char-rnn
• Owner: yusuketomoto
• License: mit
• Created: 2015-06-30T09:22:39.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2017-11-13T13:42:18.000Z (about 7 years ago)
• Last Synced: 2024-08-02T12:21:53.016Z (3 months ago)
• Language: Python
• Size: 3 MB
• Stars: 167
• Watchers: 15
• Forks: 62
• Open Issues: 14
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# chainer-char-rnn

karpathy's [char-rnn](https://github.com/karpathy/char-rnn) implementation by [Chainer](https://github.com/pfnet/chainer)

## Requirement

- [Chainer](https://github.com/pfnet/chainer)

```

$ pip install chainer

```

## Train

Start training the model using `train.py`, for example

```

$ python train.py

```

The `--data_dir` flag specifies the dataset to use. By default it is set to `data/tinyshakespeare` which consists of a subset of works of Shakespeare.

**Your own data**: If you'd like to use your own data create a single file `input.txt` and place it into a folder in `data/`. For example, `data/some_folder/input.txt`.

## Sampling

Given a checkpoint file (such as those written to cv) we can generate new text. For example:

```

$ python sample.py \

--vocabulary data/tinyshakespeare/vocab.bin \

--model cv/some_checkpoint.chainermodel \

--primetext some_text --gpu -1

```

## References

- Original implementation: https://github.com/karpathy/char-rnn

- Blog post: http://karpathy.github.io/2015/05/21/rnn-effectiveness/