avalanche.benchmarks.datasets.CORe50Dataset

class avalanche.benchmarks.datasets.CORe50Dataset(root: ~pathlib.Path | str | None = None, *, train=True, transform=None, target_transform=None, loader=<function default_loader>, download=True, mini=False, object_level=True)[source]

CORe50 Pytorch Dataset

__init__(root: ~pathlib.Path | str | None = None, *, train=True, transform=None, target_transform=None, loader=<function default_loader>, download=True, mini=False, object_level=True)[source]

Creates an instance of the CORe50 dataset.

Parameters:

root – root for the datasets data. Defaults to None, which means that the default location for ‘core50’ will be used.
train – train or test split.
transform – eventual transformations to be applied.
target_transform – eventual transformation to be applied to the targets.
loader – the procedure to load the instance from the storage.
download – boolean to automatically download data. Default to True.
mini – boolean to use the 32x32 version instead of the 128x128. Default to False.
object_level – if the classification is objects based or category based: 50 or 10 way classification problem. Default to True (50-way object classification problem)

Methods

__init__([root, train, transform, ...])

Creates an instance of the CORe50 dataset.

Attributes

`root`	The path to the dataset.
`download`	If True, the dataset will be downloaded (only if needed).
`verbose`	If True, some info about the download process will be printed.