Official Website:autokeras

AutoKeras: An AutoML system based on Keras. It is developed byDATA Labat Texas A&M University. The goal of AutoKeras is to make machine learning accessible to everyone.

Learning resources

• A short example.

importautokerasasak

clf=ak.ImageClassifier()
clf.fit(x_train,y_train)
results=clf.predict(x_test)

• Official website tutorials.
• The book ofAutomated Machine Learning in Action.
• The LiveProjects ofImage Classification with AutoKeras.

Installation

To install the package, please use thepipinstallation as follows:

pip3 install autokeras

Please follow theinstallation guidefor more details.

Note:Currently, AutoKeras is only compatible withPython >= 3.7andTensorFlow >= 2.8.0.

Community

Ask your questions on ourGitHub Discussions.

Contributing Code

Here is how we manage our project.

We pick the critical issues to work on fromGitHub issues. They will be added to thisProject. Some of the issues will then be added to themilestones, which are used to plan for the releases.

Refer to ourContributing Guideto learn the best practices.

Thank all the contributors!

Cite this work

Haifeng Jin, François Chollet, Qingquan Song, and Xia Hu. "AutoKeras: An AutoML Library for Deep Learning."the Journal of machine Learning research6 (2023): 1-6. (Download)

Biblatex entry:

@article{JMLR:v24:20-1355,
author={Haifeng Jin and François Chollet and Qingquan Song and Xia Hu},
title={AutoKeras: An AutoML Library for Deep Learning},
journal={Journal of Machine Learning Research},
year={2023},
volume={24},
number={6},
pages={1--6},
url={http://jmlr.org/papers/v24/20-1355.html}
}

Acknowledgements

The authors gratefully acknowledge the D3M program of the Defense Advanced Research Projects Agency (DARPA) administered through AFRL contract FA8750-17-2-0116; the Texas A&M College of Engineering, and Texas A&M University.