mlr_pipeops_augment_color_jitter: Color Jitter Augmentation
In mlr3torch: Deep Learning with 'mlr3'

mlr_pipeops_augment_color_jitter

R Documentation

Color Jitter Augmentation

Description

Calls torchvision::transform_color_jitter, 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_color_jitter"")

Parameters

Id	Type	Default	Levels	Range
brightness	numeric	0		`[0, \infty)`
contrast	numeric	0		`[0, \infty)`
saturation	numeric	0		`[0, \infty)`
hue	numeric	0		`[0, \infty)`
stages	character	-	train, predict, both	-
affect_columns	untyped	selector_all()		-