# rstudio/tensorflow

TensorFlow for R

Repository: https://github.com/rstudio/tensorflow
Canonical: https://ross.abutalabs.com/products/rstudio-tensorflow
Homepage: https://tensorflow.rstudio.com
Language: R
License: Apache-2.0
License Family: permissive
Last push: 2026-05-08T15:49:04+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 81, release rhythm 12, longevity 100
- inputs: {"age_days": 3663, "days_push": 117, "days_rel": 376, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1339, forks 314 (observed 2026-08-28T04:04:25.843791+00:00)

## What it is
An R package that provides full access to the TensorFlow API from R via reticulate, bridging R users to TensorFlow's Python implementation. It supports building and training deep learning models with Keras, eager execution, and GPU/TPU acceleration.

## Use cases
- train deep learning models in R
- use TensorFlow from R without writing Python
- build Keras neural networks in R
- image classification and segmentation in R
- time series forecasting with deep learning in R
- text classification and machine translation in R

## When to choose
- you're an R user who wants TensorFlow/Keras capabilities
- your data science workflow is R-based but needs deep learning
- you want automatic Python environment management via reticulate

## When to avoid
- you work primarily in Python and can use TensorFlow directly
- you need a pure-R ML implementation without Python dependencies
- you need frameworks other than TensorFlow, like PyTorch

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, sdk
- domain: machine-learning, deep-learning, data-science
- platform: python, cross-platform, windows
- tags: r-package, tensorflow-bindings, keras, reticulate, neural-networks, linux, macos, gpu

## Member repositories
- rstudio/tensorflow (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:25.843791+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:43:56.415165+00:00, confidence not recorded.
  - readme: https://github.com/rstudio/tensorflow (fetched 2026-08-28T04:04:25.843791+00:00, sha 198b0b38bb5e)
  - homepage: https://tensorflow.rstudio.com (fetched 2026-08-29T12:02:59.300275+00:00, sha fb9a6ac20f51)
  - site_page: https://tensorflow.rstudio.com/install (fetched 2026-08-29T12:02:59.309453+00:00, sha e3474fe89a20)
- Data as of 2026-08-30T08:39:29.467469+00:00.