continue_training {cito}R Documentation

Continues training of a model for additional periods

Description

Continues training of a model for additional periods

Usage

continue_training(
  model,
  epochs = 32,
  continue_from = NULL,
  data = NULL,
  device = "cpu",
  verbose = TRUE,
  changed_params = NULL
)

Arguments

model

a model created by dnn

epochs

additional epochs the training should continue for

continue_from

define which epoch should be used as starting point for training, 0 if last epoch should be used

data

matrix or data.frame if not provided data from original training will be used

device

device on which network should be trained on, either "cpu" or "cuda"

verbose

print training and validation loss of epochs

changed_params

list of arguments to change compared to original training setup, see dnn which parameter can be changed

Value

a model of class cito.dnn same as created by dnn

Examples


if(torch::torch_is_installed()){
library(cito)

set.seed(222)
validation_set<- sample(c(1:nrow(datasets::iris)),25)

# Build and train  Network
nn.fit<- dnn(Sepal.Length~., data = datasets::iris[-validation_set,], epochs = 32)

# continue training for another 32 epochs
nn.fit<- continue_training(nn.fit,epochs = 32)

# Use model on validation set
predictions <- predict(nn.fit, iris[validation_set,])
}


[Package cito version 1.0.0 Index]