CRAN/E | keras3

keras3

R Interface to 'Keras'

Installation

About

Interface to 'Keras' , 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.

keras.posit.co/
github.com/rstudio/keras
Bug report File report

Key Metrics

Version 0.2.0
R ≥ 4.0
Published 2024-04-18 14 days ago
Needs compilation? no
License MIT
License File
CRAN checks keras3 results

Downloads

Yesterday 108 0%
Last 7 days 724 -28%
Last 30 days 2.306 +283%
Last 90 days 3.146
Last 365 days 3.146

Maintainer

Maintainer

Tomasz Kalinowski

tomasz@posit.co

Authors

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

Material

NEWS
Reference manual
Package source

Vignettes

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

macOS

r-prerel

arm64

r-release

arm64

r-oldrel

arm64

r-prerel

x86_64

r-release

x86_64

Windows

r-prerel

x86_64

r-release

x86_64

r-oldrel

x86_64

Old Sources

keras3 archive

Depends

R ≥ 4.0

Imports

generics ≥ 0.0.1
reticulate ≥ 1.35.0.9000
tensorflow ≥ 2.15.0.9000
tfruns ≥ 1.5.2
magrittr
zeallot
fastmap
glue
cli
rlang

Suggests

ggplot2
testthat ≥ 2.1.0
knitr
rmarkdown
callr
tfdatasets
withr
png
jsonlite
purrr
rstudioapi
R6
jpeg

Reverse Suggests

kerastuneR
tensorflow