avalanche.benchmarks.datasets.CLEARDataset

class avalanche.benchmarks.datasets.CLEARDataset(root: str | Path | None = None, *, data_name: str = 'clear10', download: bool = True, verbose: bool = False)[source]

CLEAR Base Dataset for downloading / loading metadata

__init__(root: str | Path | None = None, *, data_name: str = 'clear10', download: bool = True, verbose: bool = False)[source]

Creates an instance of the CLEAR dataset. This base class simply download and unzip the CLEAR dataset.

This serves as a base class for _CLEARImage/_CLEARFeature dataset.

Parameters:
  • root – The directory where the dataset can be found or downloaded. Defaults to None, which means that the default location for str(data_name) will be used.

  • data_name – Data module name with the google drive url and md5

  • download – If True, the dataset will be downloaded if needed.

Methods

__init__([root, data_name, download, verbose])

Creates an instance of the CLEAR dataset.

Attributes