Models, Datasets and Transformations for Images R package torchvision version 0.9.0 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. Software 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 Tomasz Kalinowski <tomasz@posit.co> Comprehensive R Archive Network (CRAN) 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 [cph, fnd] (ROR: <https://ror.org/03wc8by49>) MIT + file LICENSE (https://CRAN.R-project.org/package=torchvision/LICENSE) 2026-04-22 application/tgz https://CRAN.R-project.org/package=torchvision doi:10.32614/CRAN.package.torchvision