Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mbartoli/docker-char-rnn
Docker container for use with Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
https://github.com/mbartoli/docker-char-rnn
Last synced: 1 day ago
JSON representation
Docker container for use with Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
- Host: GitHub
- URL: https://github.com/mbartoli/docker-char-rnn
- Owner: mbartoli
- Created: 2015-07-01T18:32:58.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2019-01-19T19:16:16.000Z (almost 6 years ago)
- Last Synced: 2024-08-02T05:11:20.853Z (3 months ago)
- Size: 3.91 KB
- Stars: 9
- Watchers: 2
- Forks: 5
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# docker-char-nn
Docker container for use with Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
## Usage
Run `docker run -it mbartoli/char-rnn`
### Persistent checkpoint
1. Create a folder `cv` to persist training data with `mkdir cv`.
2. Mount the folder into the container and run it:
```docker run -v $(pwd)/cv:/home/char-rnn/cv -it mbartoli/char-rnn```
3. Train your char-rnn
### Custom training data
1. Create a folder containing some training data.
```mkdir -p data/my-training-data```
2. Run the container with the new training data and `cv` folder mounted
```docker run -v $(pwd)/cv:/home/char-rnn/cv -v $(pwd)/data/my-training-data:/home/char-rnn/data/my-training-data -it mbartoli/char-rnn```
3. Train your char-rnn
## Training and sampling
See the [documentation](https://github.com/karpathy/char-rnn) on how to train and sample your char-rnn.
## More Information
Docker Hub: [mbartoli/char-nn](https://hub.docker.com/r/mbartoli/char-rnn/)
[https://github.com/karpathy/char-rnn](https://github.com/karpathy/char-rnn)
[http://karpathy.github.io/2015/05/21/rnn-effectiveness/](http://karpathy.github.io/2015/05/21/rnn-effectiveness/)