Default Measure of a Generic Torch Task

This is a simple placeholder measure and extracts the actual value from the $default_measure of a TaskTorch.

See also

Other Measure: mlr_measures_torch

Super class

mlr3::Measure -> MeasureTorchDefault

Methods

Public methods

• MeasureTorchDefault$new()

• MeasureTorchDefault$clone()

Inherited methods

• mlr3::Measure$aggregate()
• mlr3::Measure$format()
• mlr3::Measure$help()
• mlr3::Measure$obs_loss()
• mlr3::Measure$print()
• mlr3::Measure$score()

---

MeasureTorchDefault$new()

Creates a new instance of this R6 class.

Usage

MeasureTorchDefault$new()

---

MeasureTorchDefault$clone()

The objects of this class are cloneable with this method.

Usage

MeasureTorchDefault$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

d = data.frame(x = rnorm(10), y = rnorm(10))
task = as_task_torch(d, target = "y",
  default_measure = msr_torch("mse", function(truth, response) mean((truth - response)^2)))
msr("torch.default")
#> 
#> ── <MeasureTorchDefault> (torch.default): Default Measure for a TaskTorch ──────
#> • Packages: mlr3
#> • Range: [-Inf, Inf]
#> • Minimize: NA
#> • Average: macro
#> • Parameters: list()
#> • Properties: requires_task and obs_loss
#> • Predict type: response
#> • Predict sets: test
#> • Aggregator: mean()