Calculates accuracy

Evaluates the model by calculating its accuracy.

eval_accuracy(model, test_ds, dev)

Arguments

model	net, nn_module, neural network model we want to evaluate
test_ds	dataset object from torch used for making test predictions and evaluation
dev	device used for calculations (cpu or gpu)

Value

double, accuracy of provided model

Examples

if (FALSE) {

dev        <- "cpu"
# presaved torch model
model      <- torch_load(system.file("extdata","clf2",package="fairpan"))

# presaved output of `preprocess` function
processed  <- torch_load(system.file("extdata","processed",package="fairpan"))

dsl        <- dataset_loader(processed$train_x, processed$train_y,
                             processed$test_x, processed$test_y,
                             batch_size = 5, dev = dev)

eval_accuracy(model, dsl$test_ds, dev)
}