The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
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.
Check out the AutoKeras blogpost at the RStudio TensorFlow for R blog.
Install the current released version of {autokeras}
from
CRAN:
install.packages("autokeras")
Or install the development version from GitHub:
if (!require("remotes")) {
install.packages("remotes")
}::install_github("r-tensorflow/autokeras") remotes
Then, use the install_autokeras()
function to install
TensorFlow:
library("autokeras")
install_autokeras()
autokeras
R package has a configured Docker image.
Steps to run it:
From a bash console:
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 ${PWD}:/data jcrodriguez1989/r-autokeras:1.0.0 /bin/bash
ls /data # once when the docker image is running
library("keras")
# Get CIFAR-10 dataset, but not preprocessing needed
<- dataset_cifar10()
cifar10 c(x_train, y_train) %<-% cifar10$train
c(x_test, y_test) %<-% cifar10$test
library("autokeras")
# Create an image classifier, and train 10 different models
<- model_image_classifier(max_trials = 10) %>%
clf fit(x_train, y_train)
# And use it to evaluate, predict
%>% evaluate(x_test, y_test) clf
%>% predict(x_test[1:10, , , ]) clf
# Get the best trained Keras model, to work with the keras R library
<- export_model(clf)) (keras_model
library("keras")
# Get IMDb dataset
<- dataset_imdb(num_words = 1000)
imdb c(x_train, y_train) %<-% imdb$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.
<- dataset_imdb_word_index()
word_index <- c(
word_index "<PAD>", "<START>", "<UNK>", "<UNUSED>",
names(word_index)[order(unlist(word_index))]
)<- lapply(x_train, function(x) {
x_train paste(word_index[x + 1], collapse = " ")
})<- lapply(x_test, function(x) {
x_test paste(word_index[x + 1], collapse = " ")
})
<- matrix(unlist(x_train), ncol = 1)
x_train <- matrix(unlist(x_test), ncol = 1)
x_test <- array(unlist(y_train))
y_train <- array(unlist(y_test)) y_test
library("autokeras")
# Create a text classifier, and train 10 different models
<- model_text_classifier(max_trials = 10) %>%
clf fit(x_train, y_train)
# And use it to evaluate, predict
%>% evaluate(x_test, y_test) clf
%>% predict(x_test[1:10]) clf
# Get the best trained Keras model, to work with the keras R library
export_model(clf)
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.