Keras installation in R

# install the Tensorflow R package
install.packages("tensorflow")

# configure R with a Python installation
library(reticulate)
path_to_python <- install_python()
virtualenv_create("r-reticulate", python = path_to_python)

# install Tensorflow
library(tensorflow)
install_tensorflow(envname = "r-reticulate")

# install Keras
install.packages("keras")
library(keras)
install_keras(envname = "r-reticulate")

# === TEST ===
# configure reticulate
library(reticulate)
use_virtualenv("r-reticulate")

# use Tensorflow
library(tensorflow)
tf$constant("Hello Tensorflow!")

# use Keras
network <- keras_model_sequential() %>%
  layer_dense(units = 8, activation = "relu", input_shape = c(4)) %>%
  layer_dense(units = 1, activation = "linear")
summary(network)

 

Reference
[1] https://tensorflow.rstudio.com/install/

TensorFlow for R - Quick start

[2] https://rstudio.github.io/reticulate/