mlr_learners_torch_image function

Image Learner

Base Class for Image Learners. The features are assumed to be a single lazy_tensor column in RGB format.

Parameters

Parameters include those inherited from LearnerTorch and the param_set construction argument.

See Also

Other Learner: mlr_learners.mlp, mlr_learners.tab_resnet, mlr_learners.torch_featureless, mlr_learners_torch, mlr_learners_torch_model

Super classes

mlr3::Learner -> mlr3torch::LearnerTorch -> LearnerTorchImage

Methods

Public methods

• list("LearnerTorchImage$new()")

• list("LearnerTorchImage$clone()")

Method new()

Creates a new instance of this R6 class.

Usage

LearnerTorchImage$new(
  id,
  task_type,
  param_set = ps(),
  label,
  optimizer = NULL,
  loss = NULL,
  callbacks = list(),
  packages = "torchvision",
  man,
  properties = NULL,
  predict_types = NULL
)

Arguments

• id: (character(1))

   The id for of the new object.
  

• task_type: (character(1))

   The task type.
  

• param_set: (ParamSet)

   The parameter set.
  

• label: (character(1))

   Label for the new instance.
  

• optimizer: (TorchOptimizer)

   The torch optimizer.
  

• loss: (TorchLoss)

   The loss to use for training.
  

• callbacks: (list() of TorchCallbacks)

   The callbacks used during training. Must have unique ids. They are executed in the order in which they are provided
  

• packages: (character())

   The R packages this object depends on.
  

• man: (character(1))

   String in the format `[pkg]::[topic]` pointing to a manual page for this object. The referenced help package can be opened via method `$help()`.
  

• properties: (character())

   The properties of the object. See `mlr_reflections$learner_properties` for available values.
  

• predict_types: (character())

   The predict types. See `mlr_reflections$learner_predict_types` for available values.
  

Method clone()

The objects of this class are cloneable with this method.

Usage

LearnerTorchImage$clone(deep = FALSE)

Arguments

• deep: Whether to make a deep clone.