Predict: Predict values from a keras model

In kerasR: R Interface to the Keras Deep Learning Library

Predict values from a keras model

Description

Once compiled and trained, this function returns the predictions from a keras model. The function keras_predict returns raw predictions, keras_predict_classes gives class predictions, and keras_predict_proba gives class probabilities.

Usage

keras_predict(model, x, batch_size = 32, verbose = 1)

keras_predict_classes(model, x, batch_size = 32, verbose = 1)

keras_predict_proba(model, x, batch_size = 32, verbose = 1)

Arguments

model	a keras model object, for example created with Sequential()
x	input data
batch_size	integer. Number of samples per gradient update.
verbose	0 for no logging to stdout, 1 for progress bar logging, 2 for one log line per epoch.

Author(s)

Taylor B. Arnold, [e-mail]

References

Chollet, Francois. 2015. Keras: Deep Learning library for Theano and TensorFlow.

See Also

Other model functions: LoadSave, Sequential, keras_compile, keras_fit

Examples

if(keras_available()) {
  X_train <- matrix(rnorm(100 * 10), nrow = 100)
  Y_train <- to_categorical(matrix(sample(0:2, 100, TRUE), ncol = 1), 3)
  
  mod <- Sequential()
  mod$add(Dense(units = 50, input_shape = dim(X_train)[2]))
  mod$add(Dropout(rate = 0.5))
  mod$add(Activation("relu"))
  mod$add(Dense(units = 3))
  mod$add(ActivityRegularization(l1 = 1))
  mod$add(Activation("softmax"))
  keras_compile(mod,  loss = 'categorical_crossentropy', optimizer = RMSprop())
  
  keras_fit(mod, X_train, Y_train, batch_size = 32, epochs = 5,
            verbose = 0, validation_split = 0.2)
  dim(keras_predict(mod, X_train))
  mean(keras_predict(mod, X_train) == (apply(Y_train, 1, which.max) - 1))
}

kerasR documentation built on Aug. 17, 2022, 5:06 p.m.