# https://blog.rstudio.com/2017/09/05/keras-for-r/

library(keras)
#
#install_keras()


mnist <- dataset_mnist()
x_train <- mnist$train$x
y_train <- mnist$train$y
x_test <- mnist$test$x
y_test <- mnist$test$y


# reshape
dim(x_train) <- c(nrow(x_train), 784)
dim(x_test) <- c(nrow(x_test), 784)
# rescale
x_train <- x_train / 255
x_test <- x_test / 255

y_train <- to_categorical(y_train, 10)
y_test <- to_categorical(y_test, 10)


batch_size = 128
num_classes = 10
epochs = 20


model <- keras_model_sequential() 
model %>% 
  layer_dense(units = 512, activation = "relu", input_shape = c(784)) %>% 
  layer_dropout(rate = 0.2) %>% 
  layer_dense(units = 512, activation = "relu") %>%
  layer_dropout(rate = 0.2) %>%
  layer_dense(units = num_classes, activation = "softmax")

summary(model)

model %>% compile(
  loss = "categorical_crossentropy",
  optimizer = optimizer_rmsprop(),
  metrics = c("accuracy")
)


history <- model %>% fit(
  x_train, y_train, 
  epochs = epochs, batch_size = batch_size, 
  verbose = 1,
  validation_split = 0.2
)

score = model %>% evaluate(x_test, y_test, verbose=0)
print(paste('Test loss:', score$loss))
print(paste('Test accuracy:', score$acc))

plot(history)


y_pred = model %>% predict_classes(x_test)