keras: R Interface to 'Keras'

Interface to 'Keras' <https://keras.io>, a high-level neural networks 'API'. 'Keras' was developed with a focus on enabling fast experimentation, supports both convolution based networks and recurrent networks (as well as combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

Version:	2.16.0
Depends:	R (≥ 3.6)
Imports:	generics (≥ 0.0.1), reticulate (≥ 1.31), tensorflow (≥ 2.13.0.9000), tfruns (≥ 1.0), magrittr, zeallot, glue, methods, R6, rlang
Suggests:	ggplot2, testthat (≥ 2.1.0), knitr, rmarkdown, callr, tfdatasets, withr, png, jpeg
Published:	2025-08-18
DOI:	10.32614/CRAN.package.keras
Author:	Tomasz Kalinowski [ctb, cph, cre], Daniel Falbel [ctb, cph], JJ Allaire [aut, cph], François Chollet [aut, cph], RStudio [ctb, cph, fnd], Google [ctb, cph, fnd], Yuan Tang [ctb, cph], Wouter Van Der Bijl [ctb, cph], Martin Studer [ctb, cph], Sigrid Keydana [ctb]
Maintainer:	Tomasz Kalinowski <tomasz at posit.co>
BugReports:	https://github.com/rstudio/keras3/issues
License:	MIT + file LICENSE
URL:	https://tensorflow.rstudio.com/, https://github.com/rstudio/keras3/tree/r2
NeedsCompilation:	no
Materials:	NEWS
In views:	HighPerformanceComputing, ModelDeployment
CRAN checks:	keras results

Documentation:

Reference manual:

keras.html , keras.pdf

Vignettes:

Using Pre-Trained Models (source, R code) Writing Custom Keras Layers (source, R code) Writing Custom Keras Models (source, R code) Frequently Asked Questions (source, R code) Guide to the Functional API (source, R code) Guide to Keras Basics (source, R code) Getting Started with Keras (source, R code) Saving and serializing models (source, R code) Guide to the Sequential Model (source, R code) Training Callbacks (source, R code) Training Visualization (source, R code)

Downloads:

Package source:	keras_2.16.0.tar.gz
Windows binaries:	r-devel: keras_2.16.0.zip, r-release: keras_2.16.0.zip, r-oldrel: keras_2.16.0.zip
macOS binaries:	r-release (arm64): keras_2.16.0.tgz, r-oldrel (arm64): keras_2.16.0.tgz, r-release (x86_64): keras_2.16.0.tgz, r-oldrel (x86_64): keras_2.16.0.tgz
Old sources:	keras archive

Reverse dependencies:

Reverse depends:	DeepPINCS, deepregression, deeptrafo, GenProSeq, LDNN, MantaID, ttgsea, VAExprs
Reverse imports:	ARMALSTM, autokeras, codacore, codez, cramR, CRISPRseek, criticality, decompDL, deepredeff, EEMDlstm, FuncNN, gnn, imageseg, iSubGen, janus, LilRhino, MBMethPred, ML2Pvae, mnda, neuralGAM, orthos, PLEXI, ProcData, processpredictR, roseRF, rTLsDeep, snap, soundClass, SpatialDDLS, SPORTSCausal, tfaddons, tfNeuralODE, tfprobability, TraceAssist, transformerForecasting, TSdeeplearning, TSLSTM, TSLSTMplus, tsLSTMx, TSPred
Reverse suggests:	AnnotationHub, bamlss, bundle, cloudml, condvis2, counterfactuals, CytoMethIC, dimRed, drake, fastml, flowml, iml, infinityFlow, innsight, lime, mlflow, mrbin, nn2poly, parsnip, pdp, PhysicalActivity, PortfolioTesteR, qeML, regtools, RNAmodR.ML, seriation, survivalmodels, targets, tfhub, vetiver, vivid

Linking:

Please use the canonical form https://CRAN.R-project.org/package=keras to link to this page.