DomainCIFAR100ViT#

class capymoa.ocl.datasets.DomainCIFAR100ViT[source]#

Bases: SplitCIFAR100ViT

Domain incremental CIFAR-100 ViT variant with 20 classes per task.

This dataset has exactly 5 tasks. Each task contains one fine-grained class from each CIFAR-100 superclass (20 classes per task), while labels are remapped to the 20 superclass IDs.

Note that the groupings are subjective based on the original CIFAR-100’s coarse labels.

References:

  1. Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images.

__init__(
shuffle_data: bool = True,
seed: int = 0,
directory: Path = get_download_dir(),
auto_download: bool = True,
train_transform: Callable[[Any], Tensor] | None = None,
test_transform: Callable[[Any], Tensor] | None = None,
)[source]#

Create the DomainCIFAR100ViT scenario.

test_loaders(
batch_size: int,
**kwargs: Any,
) → Sequence[DataLoader[Tuple[Tensor, Tensor]]][source]#

Get the training streams for the scenario.

Parameters:

  • batch_size – Collects vectors in batches of this size.

  • kwargs – Additional keyword arguments to pass to the DataLoader.

Returns:

A data loader for each task.

train_loaders(
batch_size: int,
shuffle: bool = False,
**kwargs: Any,
) → Sequence[DataLoader[Tuple[Tensor, Tensor]]][source]#

Get the training streams for the scenario.

  • The order of the tasks is fixed and does not change between iterations. The datasets themselves are shuffled in __init__() if shuffle_data is set to True. This is because the order of data is important in online learning since the learner can only see each example once.

Parameters:

  • batch_size – Collects vectors in batches of this size.

  • kwargs – Additional keyword arguments to pass to the DataLoader.

Returns:

A data loader for each task.

classes = ['aquatic_mammals', 'fish', 'flowers', 'food_containers', 'fruit_and_vegetables', 'household_electrical_devices', 'household_furniture', 'insects', 'large_carnivores', 'large_man-made_outdoor_things', 'large_natural_outdoor_scenes', 'large_omnivores_and_herbivores', 'medium_mammals', 'non-insect_invertebrates', 'people', 'reptiles', 'small_mammals', 'trees', 'vehicles_1', 'vehicles_2']#
default_task_count: int = 5#

The default number of tasks in the dataset.

default_test_transform: Callable[[Any], Tensor] | None = None#

The default transform to apply to the dataset.

default_train_transform: Callable[[Any], Tensor] | None = None#

The default transform to apply to the dataset.

mean: Sequence[float] | None#

The mean of the features in the dataset used for normalization.

num_classes: int = 20#

The number of classes in the dataset.

schema: Schema#

A schema describing the format of the data.

shape: Sequence[int] = [768]#

The shape of each input example.

std: Sequence[float] | None#

The standard deviation of the features in the dataset used for normalization.

stream: Stream[LabeledInstance]#

Stream containing each task in sequence.

task_mask: Tensor#

A mask for the output for each task of shape (num_tasks, num_classes)

task_schedule: Sequence[Set[int]]#

A sequence of sets containing the classes for each task.

In online continual learning your learner may not have access to this attribute. It is provided for evaluation and debugging.