mlr_tasks_cifar: CIFAR Classification Tasks

In mlr3torch: Deep Learning with 'mlr3'

CIFAR Classification Tasks

Description

The CIFAR-10 and CIFAR-100 datasets. A subset of the 80 million tiny images dataset with noisy labels was supplied to student labelers, who were asked to filter out incorrectly labeled images. The images are have datatype torch_long().

CIFAR-10 contains 10 classes. CIFAR-100 contains 100 classes, which may be partitioned into 20 superclasses of 5 classes each. The CIFAR-10 and CIFAR-100 classes are mutually exclusive. See Chapter 3.1 of the technical report for more details.

The data is obtained from torchvision::cifar10_dataset() (or torchvision::cifar100_dataset()).

Format

R6::R6Class inheriting from mlr3::TaskClassif.

Construction

tsk("cifar10")
tsk("cifar100")

Download

The task's backend is a DataBackendLazy which will download the data once it is requested. Other meta-data is already available before that. You can cache these datasets by setting the mlr3torch.cache option to TRUE or to a specific path to be used as the cache directory.

Properties

• Task type: “classif”

• Properties: “multiclass”

• Has Missings: no

• Target: “class”

• Features: “image”

• Data Dimension: 60000x4

References

Krizhevsky, Alex (2009). “Learning Multiple Layers of Features from Tiny Images.” Master's thesis, Department of Computer Science, University of Toronto.

Examples

task_cifar10 = tsk("cifar10")
task_cifar100 = tsk("cifar100")
print(task_cifar10)
print(task_cifar100)

mlr3torch documentation built on April 4, 2025, 3:03 a.m.