tfhub: Interface to 'TensorFlow' Hub

'TensorFlow' Hub is a library for the publication, discovery, and consumption of reusable parts of machine learning models. A module is a self-contained piece of a 'TensorFlow' graph, along with its weights and assets, that can be reused across different tasks in a process known as transfer learning. Transfer learning train a model with a smaller dataset, improve generalization, and speed up training.

Version: 0.8.0
Imports: reticulate (≥, tensorflow (≥, magrittr, rstudioapi (≥ 0.7)
Suggests: testthat (≥ 2.1.0), knitr, tfestimators, keras, rmarkdown, callr, recipes, tibble, abind, fs, pins, magick
Published: 2020-05-22
Author: Daniel Falbel [aut, cre], JJ Allaire [aut], RStudio [cph, fnd], Google Inc. [cph]
Maintainer: Daniel Falbel <daniel at>
License: Apache License 2.0
NeedsCompilation: no
SystemRequirements: TensorFlow >= 2.0 (
Materials: README
CRAN checks: tfhub results


Reference manual: tfhub.pdf
Vignettes: TensorFlow Hub with Keras
Key concepts
Package source: tfhub_0.8.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): tfhub_0.8.0.tgz, r-release (x86_64): tfhub_0.8.0.tgz, r-oldrel: tfhub_0.8.0.tgz
Old sources: tfhub archive


Please use the canonical form to link to this page.