mlr_pipeops_augment_random_crop {mlr3torch}R Documentation

Random Crop Augmentation

Description

Calls torchvision::transform_random_crop, see there for more information on the parameters. The preprocessing is applied to each element of a batch individually.

Format

R6Class inheriting from PipeOpTaskPreprocTorch.

Parameters

Id Type Default Levels
size untyped -
padding untyped NULL
pad_if_needed logical FALSE TRUE, FALSE
fill untyped 0L
padding_mode character constant constant, edge, reflect, symmetric
stages character - train, predict, both
affect_columns untyped selector_all()

[Package mlr3torch version 0.2.1 Index]