continual_dataset

Classes

class datasets.utils.continual_dataset.ContinualDataset(args)

Bases: object

A base class for defining continual learning datasets.

NAME

the name of the dataset

Type:

str

SETTING

the setting of the dataset

Type:

str

N_CLASSES_PER_TASK

the number of classes per task

Type:

int

N_TASKS

the number of tasks

Type:

int

N_CLASSES

the number of classes

Type:

int

SIZE

the size of the dataset

Type:

Tuple[int]

train_loader

the training loader

Type:

DataLoader

test_loaders

the test loaders

Type:

List[DataLoader]

i

the current task

Type:

int

c_task

the current task

Type:

int

args

the arguments which contains the hyperparameters

Type:

Namespace

AVAIL_SCHEDS = ['multisteplr']

NAME: str

N_CLASSES: int

N_CLASSES_PER_TASK: int

N_TASKS: int

SETTING: str

SIZE: Tuple[int]

static get_backbone()

Returns the backbone to be used for the current dataset.

Return type:

Module

static get_batch_size()

Returns the batch size to be used for the current dataset.

get_data_loaders()

Creates and returns the training and test loaders for the current task. The current training loader and all test loaders are stored in self. :return: the current training and test loaders

Return type:

Tuple[DataLoader, DataLoader]

static get_denormalization_transform()

Returns the transform used for denormalizing the current dataset.

Return type:

Module

get_epochs()

Returns the number of epochs to be used for the current dataset.

static get_loss()

Returns the loss to be used for the current dataset.

Return type:

Module

classmethod get_minibatch_size()

Returns the minibatch size to be used for the current dataset.

static get_normalization_transform()

Returns the transform used for normalizing the current dataset.

Return type:

Module

get_offsets(task_idx=None)

Compute the start and end class index for the current task.

Parameters:

task_idx (int) – the task index

Returns:

the start and end class index for the current task

Return type:

tuple

static get_scheduler(model, args)

Returns the scheduler to be used for the current dataset.

Return type:

_LRScheduler

static get_transform()

Returns the transform to be used for the current dataset.

Return type:

Module

Functions

datasets.utils.continual_dataset.store_masked_loaders(train_dataset, test_dataset, setting)

Divides the dataset into tasks.

datasets.utils.continual_dataset.train_dataset

the training dataset

Type:

Dataset

datasets.utils.continual_dataset.test_dataset

the test dataset

Type:

Dataset

datasets.utils.continual_dataset.setting

the setting of the dataset

Type:

ContinualDataset

Returns:

the training and test loaders

Return type:

Tuple[DataLoader, DataLoader]