Skip to main content

leveraging aisara algorithm for effective hyperparameter tuning

Project description

  • aisaratuners is an open-source optimization library to automate and expedite hyperparameter search. aisaratuners has two modules, aisara_general_tuner.py which is a framework agnostic, and aisara_keras_tuner.py which is tailored for Karas API.

  • aisaratuners leverages AiSara algorithm, Latin hypercube sampling, and the concept of search space reduction for fast reach of the optimum hyperparameters.

[AiSara Hyperparameter Tuning API](https://rapidapi.com/aisara-technology-aisara-technology-default/api/aisara-hyperparameter-tuning)

[Medium article](https://aisaradeepwadi.medium.com/advance-keras-hyperparameter-tuning-with-aisaratuners-library-78c488ab4d6a)

[video description](https://www.youtube.com/watch?v=pFuyb7q28vg&feature=youtu.be&ab_channel=AiSaraEnquiry)

[Deep Wadi (AiSara) Sdn. Bhd.](https://www.aisara.ai/)

Change Log

1.4.9 (19/11/2020) 1.5.0 (20/1/2022) ——————-

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

aisaratuners-1.5.0.tar.gz (18.6 kB view details)

Uploaded Source

Built Distribution

aisaratuners-1.5.0-py3-none-any.whl (18.9 kB view details)

Uploaded Python 3

File details

Details for the file aisaratuners-1.5.0.tar.gz.

File metadata

  • Download URL: aisaratuners-1.5.0.tar.gz
  • Upload date:
  • Size: 18.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.8.1 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7

File hashes

Hashes for aisaratuners-1.5.0.tar.gz
Algorithm Hash digest
SHA256 f9d03cc37d7ba3cc3ad0ed2e072e3ba049f571cf9d4cc04e60b33cdc52d6fb0e
MD5 ecc6e5e9fb35aa36b0383ec0bc0698ff
BLAKE2b-256 3cfaeda6fac58ec463a1ed850acb26cf5ff0cf4e2cbdd8c9dbc72a776b46104f

See more details on using hashes here.

File details

Details for the file aisaratuners-1.5.0-py3-none-any.whl.

File metadata

  • Download URL: aisaratuners-1.5.0-py3-none-any.whl
  • Upload date:
  • Size: 18.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.8.1 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.7

File hashes

Hashes for aisaratuners-1.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7416a7b2070f2a8f61a90cdc685fad1b1961c1299709a4e50a513f53fdd739ce
MD5 3faa5d27caacacbf39de5dbadcbdeb13
BLAKE2b-256 0050637af39289eb848df613a8795dbcf5c19d8ea6ba87b82d51d5710b7499d9

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page