https://github.com/adriangb/scikeras

Scikit-Learn API wrapper for Keras.
https://github.com/adriangb/scikeras

data-science deep-learning deep-neural-networks keras machine-learning python scikit-learn tensorflow wrappers

Last synced: 4 days ago
JSON representation

Scikit-Learn API wrapper for Keras.

• Host: GitHub
• URL: https://github.com/adriangb/scikeras
• Owner: adriangb
• License: mit
• Created: 2020-04-10T21:40:36.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2024-12-12T21:51:51.000Z (about 1 month ago)
• Last Synced: 2025-01-12T10:00:37.426Z (11 days ago)
• Topics: data-science, deep-learning, deep-neural-networks, keras, machine-learning, python, scikit-learn, tensorflow, wrappers
• Language: Python
• Homepage: https://www.adriangb.com/scikeras/
• Size: 41.3 MB
• Stars: 243
• Watchers: 4
• Forks: 50
• Open Issues: 49
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Citation: CITATION.cff

Awesome Lists containing this project

README

        
# Scikit-Learn Wrapper for Keras

[![Build Status](https://github.com/adriangb/scikeras/workflows/Tests/badge.svg)](https://github.com/adriangb/scikeras/actions?query=workflow%3ATests+branch%3Amaster)

[![Coverage Status](https://codecov.io/gh/adriangb/scikeras/branch/master/graph/badge.svg)](https://codecov.io/gh/adriangb/scikeras)

[![Docs](https://github.com/adriangb/scikeras/workflows/Build%20Docs/badge.svg)](https://www.adriangb.com/scikeras/)

Scikit-Learn compatible wrappers for Keras Models.

## Why SciKeras

SciKeras is derived from and API compatible with the now deprecated / removed `tf.keras.wrappers.scikit_learn`.

An overview of the differences as compared to the TF wrappers can be found in our

[migration](https://www.adriangb.com/scikeras/stable/migration.html) guide.

## Installation

This package is available on PyPi:

```bash

# Tensorflow

pip install scikeras[tensorflow]

```

Note that `pip install scikeras[tensorflow]` is basically equivalent to `pip install scikeras tensorflow`

and is offered just for convenience. You can also install just SciKeras with

`pip install scikeras`, but you will need a version of tensorflow installed at

runtime or SciKeras will throw an error when you try to import it.

The current version of SciKeras depends on `scikit-learn>=1.4.1post1` and `Keras>=3.2.0`.

### Migrating from `keras.wrappers.scikit_learn`

Please see the [migration](https://www.adriangb.com/scikeras/stable/migration.html) section of our documentation.

## Documentation

Documentation is available at [https://www.adriangb.com/scikeras/](https://www.adriangb.com/scikeras/).

## Contributing

See [CONTRIBUTING.md](https://github.com/adriangb/scikeras/blob/master/CONTRIBUTING.md)