Keras API in R

We learned about the Keras API in Chapter 3. In R, this API is implemented with the keras R package. The keras R package implements most of the functionality of the Keras Python interface, including both the sequential API and the functional API.

As an example, we provide a walkthrough of the MLP Model for classifying handwritten digits from the MNIST dataset at the following link: https://keras.rstudio.com/articles/examples/mnist_mlp.html.

Note

You can follow along with the code in the Jupyter R notebook ch-17c_Keras_in_R.

1. First, load the library:

library(keras)

2. Define the hyper-parameters:

batch_size <- 128
num_classes <- 10
epochs <- 30

3. Prepare the data:

# The data, shuffled and split between train and test sets
c(c(x_train, y_train), c(x_test, y_test)) %<-% dataset_mnist()

x_train <- array_reshape(x_train, c(nrow(x_train), 784))
x_test <- array_reshape(x_test, c(nrow(x_test), 784))

# Transform RGB values into [0,1] range
x_train <- x_train / 255
x_test &lt...