README

AutoKeras is an open source software library for automated machine learning (AutoML). It is developed by DATA Lab at Texas A&M University and community contributors. The ultimate goal of AutoML is to provide easily accessible deep learning tools to domain experts with limited data science or machine learning background. AutoKeras provides functions to automatically search for architecture and hyperparameters of deep learning models.

Dependencies

Installation

install.packages("autokeras")

if (!require("remotes")) {
  install.packages("remotes")
}
remotes::install_github("r-tensorflow/autokeras")

library("autokeras")
install_autokeras()

Docker

docker pull jcrodriguez1989/r-autokeras:1.0.0
docker run -it jcrodriguez1989/r-autokeras:1.0.0 /bin/bash

To run the docker image, and share the current folder (in home machine) to the /data path (in the docker machine), then do:

docker run -it -v ${PWD}:/data jcrodriguez1989/r-autokeras:1.0.0 /bin/bash
ls /data # once when the docker image is running

Examples

CIFAR-10 dataset

library("keras")

# Get CIFAR-10 dataset, but not preprocessing needed
cifar10 <- dataset_cifar10()
c(x_train, y_train) %<-% cifar10$train
c(x_test, y_test) %<-% cifar10$test

library("autokeras")

# Create an image classifier, and train 10 different models
clf <- model_image_classifier(max_trials = 10) %>%
  fit(x_train, y_train)

# And use it to evaluate, predict
clf %>% evaluate(x_test, y_test)

clf %>% predict(x_test[1:10, , , ])

# Get the best trained Keras model, to work with the keras R library
(keras_model <- export_model(clf))

IMDb dataset

library("keras")

# Get IMDb dataset
imdb <- dataset_imdb(num_words = 1000)
c(x_train, y_train) %<-% imdb$train
c(x_test, y_test) %<-% imdb$test

# AutoKeras procceses each text data point as a character vector,
# i.e., x_train[[1]] "<START> this film was just brilliant casting..",
# so we need to transform the dataset.
word_index <- dataset_imdb_word_index()
word_index <- c(
  "<PAD>", "<START>", "<UNK>", "<UNUSED>",
  names(word_index)[order(unlist(word_index))]
)
x_train <- lapply(x_train, function(x) {
  paste(word_index[x + 1], collapse = " ")
})
x_test <- lapply(x_test, function(x) {
  paste(word_index[x + 1], collapse = " ")
})

x_train <- matrix(unlist(x_train), ncol = 1)
x_test <- matrix(unlist(x_test), ncol = 1)
y_train <- array(unlist(y_train))
y_test <- array(unlist(y_test))

library("autokeras")

# Create a text classifier, and train 10 different models
clf <- model_text_classifier(max_trials = 10) %>%
  fit(x_train, y_train)

# And use it to evaluate, predict
clf %>% evaluate(x_test, y_test)

clf %>% predict(x_test[1:10])