export_model: Export Model

In autokeras: R Interface to 'AutoKeras'

Description

Export the best trained Keras Model.
Actually, exporting the model as a Keras model is not working as expected, check out the bug https://github.com/keras-team/autokeras/issues/929 .

Usage

export_model(autokeras_model)

Arguments

autokeras_model

: A trained AutokerasModel instance.

Value

keras.Model instance. The best model found during the search, loaded with trained weights.

Examples

## Not run: 
library("keras")

# use the MNIST dataset as an example
mnist <- dataset_mnist()
c(x_train, y_train) %<-% mnist$train
c(x_test, y_test) %<-% mnist$test

library("autokeras")

# Initialize the image classifier
clf <- model_image_classifier(max_trials = 10) %>% # It tries 10 different models
  fit(x_train, y_train) # Feed the image classifier with training data

# Predict with the best model
(predicted_y <- clf %>% predict(x_test))

# Evaluate the best model with testing data
clf %>% evaluate(x_test, y_test)

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

## End(Not run)

autokeras documentation built on Jan. 17, 2021, 9:06 a.m.