avalanche.benchmarks.datasets.CUB200

class avalanche.benchmarks.datasets.CUB200(root: typing.Optional[typing.Union[str, pathlib.Path]] = None, *, train=True, transform=None, target_transform=None, loader=<function default_loader>, download=True)[source]

Basic CUB200 PathsDataset to be used as a standard PyTorch Dataset. A classic continual learning benchmark built on top of this dataset can be found in ‘benchmarks.classic’, while for more custom benchmark design please use the ‘benchmarks.generators’.

__init__(root: typing.Optional[typing.Union[str, pathlib.Path]] = None, *, train=True, transform=None, target_transform=None, loader=<function default_loader>, download=True)[source]
Parameters
  • root – root dir where the dataset can be found or downloaded. Defaults to None, which means that the default location for ‘CUB_200_2011’ will be used.

  • train – train or test subset of the original dataset. Default to True.

  • transform – eventual input data transformations to apply. Default to None.

  • target_transform – eventual target data transformations to apply. Default to None.

  • loader – method to load the data from disk. Default to torchvision default_loader.

  • download – default set to True. If the data is already downloaded it will skip the download.

Methods

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

param root

root dir where the dataset can be found or downloaded.

register_datapipe_as_function(function_name, ...)

register_function(function_name, function)

Attributes

filename

functions

gdrive_url

images_folder

official_url

tgz_md5