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.

torchvision is an extension for torch providing image loading, transformations, common architectures for computer vision, pre-trained weights and access to commonly used datasets.
The CRAN release can be installed with:
install.packages("torchvision")
You can install the development version from GitHub with:
remotes::install_github("mlverse/torchvision@main")