keras3: 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:	1.4.0
Depends:	R (≥ 4.0)
Imports:	generics (≥ 0.0.1), reticulate (≥ 1.42.0), tensorflow (≥ 2.16.0), tfruns (≥ 1.5.2), magrittr, zeallot, fastmap, glue, cli, rlang, dotty
Suggests:	ggplot2, testthat (≥ 2.1.0), knitr, rmarkdown, callr, tfdatasets, withr, png, jsonlite, purrr, rstudioapi, R6, jpeg
Published:	2025-05-04
DOI:	10.32614/CRAN.package.keras3
Author:	Tomasz Kalinowski [aut, cph, cre], Daniel Falbel [ctb, cph], JJ Allaire [aut, cph], François Chollet [aut, cph], Posit Software, PBC [cph, fnd], Google [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://keras3.posit.co/, https://github.com/rstudio/keras3
NeedsCompilation:	no
Materials:	NEWS
CRAN checks:	keras3 results

Documentation:

Reference manual:

keras3.html , keras3.pdf

Vignettes:

Customizing what happens in 'fit()' with TensorFlow (source) Multi-GPU distributed training with TensorFlow (source) Distributed training with Keras 3 (source) The Functional API (source) Getting Started with Keras (source) Introduction to Keras for engineers (source) Introduction to Keras for Researchers (source) Making new layers and models via subclassing (source) The Sequential model (source) Save, serialize, and export models (source) Training & evaluation with the built-in methods (source) Transfer learning & fine-tuning (source) Understanding masking & padding (source) Writing a training loop from scratch in TensorFlow (source) Writing your own callbacks (source)

Downloads:

Package source:	keras3_1.4.0.tar.gz
Windows binaries:	r-devel: keras3_1.4.0.zip, r-release: keras3_1.4.0.zip, r-oldrel: keras3_1.4.0.zip
macOS binaries:	r-release (arm64): keras3_1.4.0.tgz, r-oldrel (arm64): keras3_1.4.0.tgz, r-release (x86_64): keras3_1.4.0.tgz, r-oldrel (x86_64): keras3_1.4.0.tgz
Old sources:	keras3 archive

Reverse dependencies:

Reverse imports:	immApex, kerasnip, reservr
Reverse suggests:	embed, kerastuneR, tensorflow, tfdatasets

Linking:

Please use the canonical form https://CRAN.R-project.org/package=keras3 to link to this page.