mlr_pipeops_augment_resized_crop: Resized Crop Augmentation

In mlr3torch: Deep Learning with 'mlr3'

Resized Crop Augmentation

Description

Calls torchvision::transform_resized_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.

Construction

po("augment_resized_crop"")

Parameters

Id	Type	Default	Levels	Range
top	integer	-		(-\infty, \infty)
left	integer	-		(-\infty, \infty)
height	integer	-		(-\infty, \infty)
width	integer	-		(-\infty, \infty)
size	untyped	-		-
interpolation	integer	2		[0, 3]
stages	character	-	train, predict, both	-
affect_columns	untyped	selector_all()		-

mlr3torch documentation built on Aug. 26, 2025, 5:09 p.m.