{"id":13665837,"url":"https://github.com/r-tensorflow/autokeras","last_synced_at":"2025-10-26T13:31:13.338Z","repository":{"id":55009786,"uuid":"174017008","full_name":"r-tensorflow/autokeras","owner":"r-tensorflow","description":"Package: R Interface to AutoKeras","archived":false,"fork":false,"pushed_at":"2021-01-16T23:58:50.000Z","size":5324,"stargazers_count":73,"open_issues_count":5,"forks_count":14,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-01-08T00:02:53.447Z","etag":null,"topics":["autodl","automatic-machine-learning","automl","deep-learning","keras","machine-learning","r","tensorflow"],"latest_commit_sha":null,"homepage":"https://r-tensorflow.github.io/autokeras/","language":"R","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/r-tensorflow.png","metadata":{"files":{"readme":"README.Rmd","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-03-05T20:37:18.000Z","updated_at":"2024-02-06T13:43:15.000Z","dependencies_parsed_at":"2022-08-14T09:00:40.058Z","dependency_job_id":null,"html_url":"https://github.com/r-tensorflow/autokeras","commit_stats":null,"previous_names":["jcrodriguez1989/autokeras"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r-tensorflow%2Fautokeras","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r-tensorflow%2Fautokeras/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r-tensorflow%2Fautokeras/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/r-tensorflow%2Fautokeras/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/r-tensorflow","download_url":"https://codeload.github.com/r-tensorflow/autokeras/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":236567408,"owners_count":19169897,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["autodl","automatic-machine-learning","automl","deep-learning","keras","machine-learning","r","tensorflow"],"created_at":"2024-08-02T06:00:51.761Z","updated_at":"2025-10-26T13:31:12.679Z","avatar_url":"https://github.com/r-tensorflow.png","language":"R","funding_links":[],"categories":["R","Libraries"],"sub_categories":[],"readme":"---\ntitle: \"R Interface to AutoKeras\"\noutput: github_document\n---\n\n[![Travis Build Status](https://travis-ci.org/r-tensorflow/autokeras.svg?branch=master)](https://travis-ci.org/r-tensorflow/autokeras) \n[![Coverage status](https://img.shields.io/codecov/c/github/jcrodriguez1989/autokeras/master.svg)](https://codecov.io/github/jcrodriguez1989/autokeras?branch=master)\n[![lifecycle](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://www.tidyverse.org/lifecycle/#experimental)\n\n\n[AutoKeras](https://autokeras.com/) is an open source software library for \nautomated machine learning (AutoML). It is developed by\n[DATA Lab](https://people.engr.tamu.edu/xiahu/index.html) at Texas A\u0026M\nUniversity and community contributors. The ultimate goal of AutoML is to\nprovide easily accessible deep learning tools to domain experts with limited\ndata science or machine learning background. AutoKeras provides functions\nto automatically search for architecture and hyperparameters of deep\nlearning models.\n\nCheck out the [AutoKeras blogpost at the **RStudio TensorFlow for R blog**](https://blogs.rstudio.com/tensorflow/posts/2019-04-16-autokeras/).\n\n## Dependencies\n\n* [AutoKeras](https://autokeras.com/) requires Python \u003e= 3.5 .\n\n## Installation\n\nInstall the current released version of `{autokeras}` from [CRAN](https://cran.r-project.org/package=autokeras):\n\n```{r eval = FALSE}\ninstall.packages(\"autokeras\")\n```\n\nOr install the development version from GitHub:\n\n```{r eval = FALSE}\nif (!require(\"remotes\")) {\n  install.packages(\"remotes\")\n}\nremotes::install_github(\"r-tensorflow/autokeras\")\n```\n\nThen, use the `install_autokeras()` function to install TensorFlow:\n\n```{r eval = FALSE}\nlibrary(\"autokeras\")\ninstall_autokeras()\n```\n\n## Docker\n\n`autokeras` R package has a configured Docker image.\n\nSteps to run it:\n\nFrom a bash console:\n\n```{bash eval = FALSE}\ndocker pull jcrodriguez1989/r-autokeras:1.0.0\ndocker run -it jcrodriguez1989/r-autokeras:1.0.0 /bin/bash\n```\n\nTo run the docker image, and share the current folder (in home machine) to the `/data` path (in the docker machine), then do:\n\n```{bash eval = FALSE}\ndocker run -it -v ${PWD}:/data jcrodriguez1989/r-autokeras:1.0.0 /bin/bash\nls /data # once when the docker image is running\n```\n\n## Examples\n\n### CIFAR-10 dataset\n\n```{r eval = FALSE}\nlibrary(\"keras\")\n\n# Get CIFAR-10 dataset, but not preprocessing needed\ncifar10 \u003c- dataset_cifar10()\nc(x_train, y_train) %\u003c-% cifar10$train\nc(x_test, y_test) %\u003c-% cifar10$test\n```\n\n```{r eval = FALSE}\nlibrary(\"autokeras\")\n\n# Create an image classifier, and train 10 different models\nclf \u003c- model_image_classifier(max_trials = 10) %\u003e%\n  fit(x_train, y_train)\n```\n\n```{r eval = FALSE}\n# And use it to evaluate, predict\nclf %\u003e% evaluate(x_test, y_test)\n```\n\n```{r eval = FALSE}\nclf %\u003e% predict(x_test[1:10, , , ])\n```\n\n```{r eval = FALSE}\n# Get the best trained Keras model, to work with the keras R library\n(keras_model \u003c- export_model(clf))\n```\n\n### IMDb dataset\n\n```{r eval = FALSE}\nlibrary(\"keras\")\n\n# Get IMDb dataset\nimdb \u003c- dataset_imdb(num_words = 1000)\nc(x_train, y_train) %\u003c-% imdb$train\nc(x_test, y_test) %\u003c-% imdb$test\n\n# AutoKeras procceses each text data point as a character vector,\n# i.e., x_train[[1]] \"\u003cSTART\u003e this film was just brilliant casting..\",\n# so we need to transform the dataset.\nword_index \u003c- dataset_imdb_word_index()\nword_index \u003c- c(\n  \"\u003cPAD\u003e\", \"\u003cSTART\u003e\", \"\u003cUNK\u003e\", \"\u003cUNUSED\u003e\",\n  names(word_index)[order(unlist(word_index))]\n)\nx_train \u003c- lapply(x_train, function(x) {\n  paste(word_index[x + 1], collapse = \" \")\n})\nx_test \u003c- lapply(x_test, function(x) {\n  paste(word_index[x + 1], collapse = \" \")\n})\n\nx_train \u003c- matrix(unlist(x_train), ncol = 1)\nx_test \u003c- matrix(unlist(x_test), ncol = 1)\ny_train \u003c- array(unlist(y_train))\ny_test \u003c- array(unlist(y_test))\n```\n\n```{r eval = FALSE}\nlibrary(\"autokeras\")\n\n# Create a text classifier, and train 10 different models\nclf \u003c- model_text_classifier(max_trials = 10) %\u003e%\n  fit(x_train, y_train)\n```\n\n```{r eval = FALSE}\n# And use it to evaluate, predict\nclf %\u003e% evaluate(x_test, y_test)\n```\n\n```{r eval = FALSE}\nclf %\u003e% predict(x_test[1:10])\n```\n\n```{r eval = FALSE}\n# Get the best trained Keras model, to work with the keras R library\nexport_model(clf)\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr-tensorflow%2Fautokeras","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fr-tensorflow%2Fautokeras","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fr-tensorflow%2Fautokeras/lists"}