Skip to content

semipy.datasets.get_svhn

    semipy.datasets.cifar.get_svhn(num_labelled: int = 73257,
                                   num_unlabelled: int = 0,
                                   valid_proportion: float = 0.0,
                                   path: str = './data',
                                   augmentation: bool = False,
                                   include_labelled: bool = False,
                                   use_extra: bool = False) -> dict

Downloads SVHN dataset from torchvision and transforms it into a Semi-Supervised dataset (with labelled and unlabelled samples).

Parameters

  • num_labelled (int) - Number of labelled items to include in the dataset. Default: 73 257
  • num_unlabelled (int) - Number of unlabelled items to include in the dataset. Default: 0
  • valid_proportion (float) - Size of the validation set defined by a proportion with respect to the number of labelled items. Default: 0.0
  • path (str) - Path to download and store data samples. Default: './data'
  • augmentation (bool) - To use augmentation or not when sampling in the dataset. Default: False
  • include_labelled (bool) - To include labelled items into unlabelled set as additional data. Default: False
  • use_extra (bool) - To use the 'extra' dataset from SVHN (531 131 samples in addition) or not. Default: False