Package: kerastuneR 0.1.0.7

Turgut Abdullayev

kerastuneR: Interface to 'Keras Tuner'

'Keras Tuner' <https://keras-team.github.io/keras-tuner/> is a hypertuning framework made for humans. It aims at making the life of AI practitioners, hypertuner algorithm creators and model designers as simple as possible by providing them with a clean and easy to use API for hypertuning. 'Keras Tuner' makes moving from a base model to a hypertuned one quick and easy by only requiring you to change a few lines of code.

Authors:Turgut Abdullayev [aut, cre], Google Inc. [cph]

kerastuneR_0.1.0.7.tar.gz
kerastuneR_0.1.0.7.zip(r-4.5)kerastuneR_0.1.0.7.zip(r-4.4)kerastuneR_0.1.0.7.zip(r-4.3)
kerastuneR_0.1.0.7.tgz(r-4.4-any)kerastuneR_0.1.0.7.tgz(r-4.3-any)
kerastuneR_0.1.0.7.tar.gz(r-4.5-noble)kerastuneR_0.1.0.7.tar.gz(r-4.4-noble)
kerastuneR_0.1.0.7.tgz(r-4.4-emscripten)kerastuneR_0.1.0.7.tgz(r-4.3-emscripten)
kerastuneR.pdf |kerastuneR.html
kerastuneR/json (API)

# Install 'kerastuneR' in R:
install.packages('kerastuneR', repos = c('https://eagerai.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/eagerai/kerastuner/issues

On CRAN:

hyperparameter-tuninghypertuningkeraskeras-tunertensorflowtrial

26 exports 32 stars 2.55 score 99 dependencies 46 scripts 522 downloads

Last updated 5 months agofrom:d9ab72f540. Checks:OK: 7. Indexed: yes.

TargetResultDate
Doc / VignettesOKSep 10 2024
R-4.5-winOKSep 10 2024
R-4.5-linuxOKSep 10 2024
R-4.4-winOKSep 10 2024
R-4.4-macOKSep 10 2024
R-4.3-winOKAug 11 2024
R-4.3-macOKAug 11 2024

Exports:BaseTunerBayesianOptimizationcallback_tunerfit_tunerget_best_modelsHyperbandHyperModel_classHyperParametersHyperResNetHyperXceptioninstall_kerastunerkeras_tuner_versionload_modelObjectiveOracleplot_keras_modelplot_tunerPyClassRandomSearchresults_summarysave_modelsearch_summaryTensorBoardtfTuner_classuse_python

Dependencies:askpassassertthatbackportsbase64encbroombslibcachemclicolorspacecommonmarkconfigcorrplotcountrycodecpp11crayoncrosstalkcurldata.tabledigestdplyrecharts4revaluatefansifarverfastmapfontawesomefsgenericsggplot2gluegtableherehighrhtmltoolshtmlwidgetshttpuvhttrisobandjquerylibjsonliteknitrlabelinglaterlatticelazyevallifecyclemagickmagrittrMASSMatrixmemoisemgcvmimemunsellnlmeopensslpillarpkgconfigplotlypngprocessxpromisespspurrrR6rappdirsRColorBrewerRcppRcppTOMLreticulaterjsonRJSONIOrlangrmarkdownrprojrootrstudioapisassscalesshinysourcetoolsstringistringrsystensorflowtfautographtfrunstibbletidyjsontidyrtidyselecttinytexutf8vctrsviridisLitewhiskerwithrxfunxtableyaml

Bayesian Optimization

Rendered fromBayesianOptimisation.Rmdusingknitr::rmarkdownon Sep 10 2024.

Last update: 2024-04-13
Started: 2020-02-02

HyperModel subclass

Rendered fromHyperModel_subclass.Rmdusingknitr::rmarkdownon Sep 10 2024.

Last update: 2024-04-13
Started: 2020-01-08

Introduction to kerastuneR

Rendered fromIntroduction.Rmdusingknitr::rmarkdownon Sep 10 2024.

Last update: 2022-01-10
Started: 2020-01-01

KerasTuner best practices

Rendered frombest_practice.Rmdusingknitr::rmarkdownon Sep 10 2024.

Last update: 2024-04-13
Started: 2020-10-04

MNIST hypertuning

Rendered fromMNIST.Rmdusingknitr::rmarkdownon Sep 10 2024.

Last update: 2024-04-13
Started: 2020-01-02

Readme and manuals

Help Manual

Help pageTopics
Base TunerBaseTuner
Bayesian OptimizationBayesianOptimization
Tuner Callbackcallback_tuner
Searchfit_tuner
Get best modelsget_best_models
HyperbandHyperband
HyperModelHyperModel_class
HyperParametersHyperParameters
HyperResNetHyperResNet
HyperXceptionHyperXception
Install Keras Tunerinstall_kerastuner
Version of Keras Tunerkeras_tuner_version
Load modelload_model
ObjectiveObjective
OracleOracle
Plot Keras modelplot_keras_model
Plot the tuner results with 'plotly'plot_tuner
RandomSearchRandomSearch
Results summaryresults_summary
Save modelsave_model
Search summarysearch_summary
TensorBoardTensorBoard
TunerTuner_class