PipeOpPreprocTorchAugmentRandomResizedCrop

Calls torchvision::transform_random_resized_crop, see there for more information on the parameters. The preprocessing is applied row wise (no batch dimension).

Format

R6Class inheriting from PipeOpTaskPreprocTorch.

Parameters

Id	Type	Default	Levels	Range
size	untyped	-		-
scale	untyped	c(0.08, 1)		-
ratio	untyped	c(3/4, 4/3)		-
interpolation	integer	2		\([0, 3]\)
stages	character	-	train, predict, both	-
affect_columns	untyped	selector_all()		-