Skip to main content

Everyday toolbox for Keras

Project description

# keras-toolbox

[![PyPI version](]( [![License ](](LICENSE)

Your every day Keras toolbox.

The spirit of this library is to add some features missing from Keras and that make your workflow more smooth and easier. If these features start to be widely used it could be a good idea to propose them as a PR in the Keras repo.

Current features are :

  • `Monitor` callbacks to easily get information about your model training. Current callbacks allow to write the state in a file as a JSON or to send the state to a Telegram user ID.
  • Visualization functions : some functions to easily visualize weights and feature maps form a specific layer or all the layers.
  • Augmentation functions : trying to replace the Keras augmentation API but the code is very crappy at the moment.

## Dependencies

  • Python 3 only (it’s time to move)
  • the classics numpy, pandas, scipy
  • Keras
  • matplotlib for the visualization
  • python-telegram-bot for the TelegramMonitor callback

## Documentation

The project is not big enough to write a proper doc for now. See this [Notebook](doc/example.ipynb) for a short documentation.

## Author

## License

MIT license. See [LICENSE](LICENSE).

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

keras-toolbox-0.1.2.tar.gz (7.4 kB view hashes)

Uploaded source

Built Distribution

keras_toolbox-0.1.2-py2.py3-none-any.whl (8.9 kB view hashes)

Uploaded 3 5

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page