Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/keras-team/autokeras
AutoML library for deep learning
https://github.com/keras-team/autokeras
autodl automated-machine-learning automl deep-learning keras machine-learning neural-architecture-search python tensorflow
Last synced: about 1 month ago
JSON representation
AutoML library for deep learning
- Host: GitHub
- URL: https://github.com/keras-team/autokeras
- Owner: keras-team
- License: apache-2.0
- Created: 2017-11-19T23:18:20.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2024-03-20T22:02:13.000Z (3 months ago)
- Last Synced: 2024-04-25T15:05:46.644Z (about 2 months ago)
- Topics: autodl, automated-machine-learning, automl, deep-learning, keras, machine-learning, neural-architecture-search, python, tensorflow
- Language: Python
- Homepage: http://autokeras.com/
- Size: 43.4 MB
- Stars: 9,066
- Watchers: 302
- Forks: 1,400
- Open Issues: 135
-
Metadata Files:
- Readme: README.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
- Codeowners: .github/CODEOWNERS
Lists
- awesome-python-data-science - AutoKeras - AutoML library for deep learning. <img height="20" src="img/keras_big.png" alt="Keras compatible"> (Automated Machine Learning / Others)
- awesome-auto-ml - Auto-Keras - Accessible AutoML for deep learning. http://autokeras.com/ (Frameworks and libraries / :snake: Python)
- awesome-stars - keras-team/autokeras - AutoML library for deep learning (Python)
- awesome-mlops - AutoKeras - AutoKeras goal is to make machine learning accessible for everyone. (AutoML)
- awesome-stars - keras-team/autokeras - AutoML library for deep learning (Python)
- awesome-meteo - AutoKeras
- my-awesome-stars - keras-team/autokeras - AutoML library for deep learning (Python)
- awesome-llmops - autokeras - team/autokeras.svg?style=flat-square) | (AutoML / Profiling)
- AwesomeResponsibleAI - AutoKeras
- awesome-keras - autokeras - AutoML library for deep learning. (Core Libraries)
- awesome-machine-learning-resources - **[Library - team/autokeras?style=social) (Table of Contents)
- awesome-automl - I
- awesome-stars - keras-team/autokeras - AutoML library for deep learning (Python)
- awesome-stars - keras-team/autokeras
- awesome-python-machine-learning-resources - GitHub - 11% open · ⏱️ 25.08.2022): (超参数优化和AutoML)
- awesome-stars - keras-team/autokeras - AutoML library for deep learning (Python)
- awesome-stars - autokeras - team | 7622 | (Python)
- awesome-projects - autokeras - Accessible AutoML for deep learning. (Python)
- awesome-stars - autokeras - AutoML library for deep learning (Python)
- awesome-open-source-mlops - autokeras - team/autokeras.svg?style=social) - AutoML library for deep learning. (Scheduling)
- awesome-stars - autokeras - An AutoML system based on Keras (Python)
- awesome-list - AutoKeras - AutoML library for deep learning. (Deep Learning Framework / Auto ML & Hyperparameter Optimization)
- Awesome-LLMOps - autokeras - team/autokeras.svg?style=social) - AutoML library for deep learning. (Profiling)
- Awesome-Tensorflow2 - keras-team/autokeras
- awesome - autokeras - AutoML library for deep learning (Python)
- awesome-stars - autokeras - team | 9091 | (Python)
README
[](https://github.com/keras-team/autokeras/actions?query=workflow%3ATests+branch%3Amaster)
[](https://codecov.io/gh/keras-team/autokeras)
[](https://badge.fury.io/py/autokeras)
[](https://www.python.org/downloads/)
[](https://www.tensorflow.org/versions)
[](https://github.com/keras-team/autokeras/issues)
Official Website: [autokeras.com](https://autokeras.com)
##
AutoKeras: An AutoML system based on Keras.
It is developed by DATA Lab at Texas A&M University.
The goal of AutoKeras is to make machine learning accessible to everyone.
## Learning resources
* A short example.
```python
import autokeras as ak
clf = ak.ImageClassifier()
clf.fit(x_train, y_train)
results = clf.predict(x_test)
```
* [Official website tutorials](https://autokeras.com/tutorial/overview/).
* The book of [*Automated Machine Learning in Action*](https://www.manning.com/books/automated-machine-learning-in-action?query=automated&utm_source=jin&utm_medium=affiliate&utm_campaign=affiliate&a_aid=jin).
* The LiveProjects of [*Image Classification with AutoKeras*](https://www.manning.com/liveprojectseries/autokeras-ser).
 
 
## Installation
To install the package, please use the `pip` installation as follows:
```shell
pip3 install autokeras
```
Please follow the [installation guide](https://autokeras.com/install) for more details.
**Note:** Currently, AutoKeras is only compatible with **Python >= 3.7** and **TensorFlow >= 2.8.0**.
## Community
Ask your questions on our [GitHub Discussions](https://github.com/keras-team/autokeras/discussions).
## Contributing Code
Here is how we manage our project.
We pick the critical issues to work on from [GitHub issues](https://github.com/keras-team/autokeras/issues).
They will be added to this [Project](https://github.com/keras-team/autokeras/projects/3).
Some of the issues will then be added to the [milestones](https://github.com/keras-team/autokeras/milestones),
which are used to plan for the releases.
Refer to our [Contributing Guide](https://autokeras.com/contributing/) to learn the best practices.
Thank all the contributors!
[](https://github.com/keras-team/autokeras/graphs/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 research* 6 (2023): 1-6. ([Download](http://jmlr.org/papers/v24/20-1355.html))
Biblatex entry:
```bibtex
@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.