The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

torchvision: Models, Datasets and Transformations for Images

Provides access to datasets, models and preprocessing facilities for deep learning with images. Integrates seamlessly with the 'torch' package and its API borrows heavily from the 'PyTorch' vision package.

Version: 0.9.0
Depends: R (≥ 3.5)
Imports: torch (≥ 0.5.0), fs, rlang, rappdirs, utils, jpeg, tiff, magrittr, png, abind, jsonlite, withr, cli, glue, zeallot
Suggests: arrow, magick, prettyunits, testthat, coro, R.matlab, xml2, knitr, rmarkdown, torchvisionlib
Published: 2026-04-22
DOI: 10.32614/CRAN.package.torchvision
Author: Tomasz Kalinowski [ctb, cre], Daniel Falbel [aut, cph], Christophe Regouby [ctb], Akanksha Koshti [ctb], Derrick Richard [ctb], ANAMASGARD [ctb], Chandraveer Singh [ctb], Posit Software, PBC ROR ID [cph, fnd]
Maintainer: Tomasz Kalinowski <tomasz at posit.co>
BugReports: https://github.com/mlverse/torchvision/issues
License: MIT + file LICENSE
URL: https://torchvision.mlverse.org, https://github.com/mlverse/torchvision
NeedsCompilation: no
Materials: README, NEWS
CRAN checks: torchvision results

Documentation:

Reference manual: torchvision.html , torchvision.pdf
Vignettes: RF100 Dataset Catalog (source, R code)

Downloads:

Package source: torchvision_0.9.0.tar.gz
Windows binaries: r-release: torchvision_0.9.0.zip, r-oldrel: torchvision_0.9.0.zip
macOS binaries: r-release (arm64): torchvision_0.9.0.tgz, r-oldrel (arm64): torchvision_0.9.0.tgz, r-release (x86_64): torchvision_0.9.0.tgz, r-oldrel (x86_64): torchvision_0.9.0.tgz
Old sources: torchvision archive

Reverse dependencies:

Reverse imports: cito, geodl, torchdatasets
Reverse suggests: bundle, gofigR, LBBNN, luz, mlr3torch

Linking:

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

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.