autokeras

AutoML for deep learning

These details have not been verified by PyPI

Project links

Project description

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 for everyone.

Example

Here is a short example of using the package.

import autokeras as ak

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

For detailed tutorial, please check here.

Installation

To install the package, please use the pip installation as follows:

pip3 install autokeras

Please follow the installation guide for more details.

Note: Currently, AutoKeras is only compatible with Python >= 3.5 and TensorFlow >= 2.1.0.

Community

Request an invitation. Use the #autokeras channel for communication.

You can also follow us on Twitter @autokeras for the latest news.

Contributors

You can follow the Contributing Guide to become a contributor. Thank all the contributors!

Backers

We accept financial support on Open Collective. Thank every backer for supporting us!

Cite this work

Haifeng Jin, Qingquan Song, and Xia Hu. "Auto-keras: An efficient neural architecture search system." Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2019. (Download)

Biblatex entry:

@inproceedings{jin2019auto,
  title={Auto-Keras: An Efficient Neural Architecture Search System},
  author={Jin, Haifeng and Song, Qingquan and Hu, Xia},
  booktitle={Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
  pages={1946--1956},
  year={2019},
  organization={ACM}
}

DISCLAIMER

Please note that this is a pre-release version of the AutoKeras which is still undergoing final testing before its official release. The website, its software and all content found on it are provided on an "as is" and "as available" basis. AutoKeras does not give any warranties, whether express or implied, as to the suitability or usability of the website, its software or any of its content. AutoKeras will not be liable for any loss, whether such loss is direct, indirect, special or consequential, suffered by any party as a result of their use of the libraries or content. Any usage of the libraries is done at the user's own risk and the user will be solely responsible for any damage to any computer system or loss of data that results from such activities. Should you encounter any bugs, glitches, lack of functionality or other problems on the website, please let us know immediately so we can rectify these accordingly. Your help in this regard is greatly appreciated.

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.

Project details

These details have not been verified by PyPI

Project links

Release history Release notifications | RSS feed

2.0.0

Mar 20, 2024

1.1.0

Jan 28, 2023

1.0.20

Aug 31, 2022

1.0.19

Apr 30, 2022

1.0.18

Feb 18, 2022

1.0.17

Feb 3, 2022

1.0.17rc1 pre-release

Oct 20, 2021

1.0.17rc0 pre-release

Oct 18, 2021

1.0.16.post1

Nov 2, 2021

1.0.16

Aug 16, 2021

1.0.15

Jun 17, 2021

1.0.14

May 31, 2021

1.0.13

May 16, 2021

1.0.12

Nov 30, 2020

1.0.11

Nov 17, 2020

1.0.10

Oct 19, 2020

1.0.9

Sep 27, 2020

1.0.8

Aug 26, 2020

1.0.7

Aug 23, 2020

1.0.6

Aug 19, 2020

1.0.5

Jul 28, 2020

1.0.4

Jul 22, 2020

1.0.3

Jun 23, 2020

This version

1.0.2

Feb 21, 2020

1.0.1

Feb 1, 2020

1.0.0

Jan 16, 2020

1.0.0b0 pre-release

Dec 23, 2019

0.4.0

Apr 26, 2019

0.3.7

Feb 5, 2019

0.3.6

Jan 16, 2019

0.3.5

Dec 3, 2018

0.3.4

Nov 28, 2018

0.3.3

Nov 28, 2018

0.3.2

Nov 28, 2018

0.3.1

Nov 18, 2018

0.3.0

Nov 17, 2018

0.2.19

Nov 6, 2018

0.2.18

Oct 4, 2018

0.2.17

Oct 1, 2018

0.2.15

Sep 25, 2018

0.2.14

Sep 10, 2018

0.2.13

Sep 5, 2018

0.2.12

Sep 3, 2018

0.2.11

Aug 28, 2018

0.2.10

Aug 27, 2018

0.2.9

Aug 27, 2018

0.2.8

Aug 26, 2018

0.2.7

Aug 24, 2018

0.2.6

Aug 23, 2018

0.2.5

Aug 21, 2018

0.2.4

Aug 17, 2018

0.2.3

Aug 13, 2018

0.2.1

Aug 4, 2018

0.2.0

Aug 3, 2018

0.1.1

Jul 6, 2018

0.0.2

Dec 22, 2017

0.0.1

Nov 30, 2017

Download files

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

Source Distribution

autokeras-1.0.2.tar.gz (45.7 kB view details)

Uploaded Feb 21, 2020 Source

Built Distribution

autokeras-1.0.2-py3-none-any.whl (67.4 kB view details)

Uploaded Feb 21, 2020 Python 3

File details

Details for the file autokeras-1.0.2.tar.gz.

File metadata

Download URL: autokeras-1.0.2.tar.gz
Upload date: Feb 21, 2020
Size: 45.7 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/45.2.0 requests-toolbelt/0.9.1 tqdm/4.43.0 CPython/3.6.10

File hashes

Hashes for autokeras-1.0.2.tar.gz
Algorithm	Hash digest
SHA256	`a622fefb6de1f89a7ded015e6c487e9eaef00366d83fb52146f91e505782c34e`
MD5	`431b7e3ab3fdf6dbfcb35c6a14a50672`
BLAKE2b-256	`9bd74b06f7ab2e7d2f41d3867341b7e65e73c8b464901f7681f3d1c35f988f3d`

See more details on using hashes here.

Provenance

File details

Details for the file autokeras-1.0.2-py3-none-any.whl.

File metadata

Download URL: autokeras-1.0.2-py3-none-any.whl
Upload date: Feb 21, 2020
Size: 67.4 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/45.2.0 requests-toolbelt/0.9.1 tqdm/4.43.0 CPython/3.6.10

File hashes

Hashes for autokeras-1.0.2-py3-none-any.whl
Algorithm	Hash digest
SHA256	`54f3522efe7d0bdb980adaba7b79983586a61274c917e5103950aaff880bb5c6`
MD5	`e2609c64911e647fae0d00e161be1d7c`
BLAKE2b-256	`a8746588d79b8618c0f45ea2b3ace4959db2697029c8175bf1a0d2ed07c14761`