brails.processors.FoundationClassifier.npid.npid_datasets package

class brails.processors.FoundationClassifier.npid.npid_datasets.CIFAR100Instance(root: str | Path, train: bool = True, transform: Callable | None = None, target_transform: Callable | None = None, download: bool = False)

Bases: CIFAR10Instance

CIFAR100Instance Dataset.

This is a subclass of the CIFAR10Instance Dataset.

base_folder = 'cifar-100-python'
data: Any
filename = 'cifar-100-python.tar.gz'
test_list = [['test', 'f0ef6b0ae62326f3e7ffdfab6717acfc']]
tgz_md5 = 'eb9058c3a382ffc7106e4002c42a8d85'
train_list = [['train', '16019d7e3df5f24257cddd939b257f8d']]
url = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
class brails.processors.FoundationClassifier.npid.npid_datasets.CIFAR10Instance(root: str | Path, train: bool = True, transform: Callable | None = None, target_transform: Callable | None = None, download: bool = False)

Bases: CIFAR10

CIFAR10Instance Dataset.

class brails.processors.FoundationClassifier.npid.npid_datasets.CombinedMaskDataset(other_data_path=None, csv_root_folder=None, data_csv=None, transform=None, mask_images=True, attribute=None)

Bases: Dataset

: Slightly hackish way to train on masks quick

loader(path)
class brails.processors.FoundationClassifier.npid.npid_datasets.ImageFolderInstance(root: str | ~pathlib.Path, transform: ~typing.Callable | None = None, target_transform: ~typing.Callable | None = None, loader: ~typing.Callable[[str], ~typing.Any] = <function default_loader>, is_valid_file: ~typing.Callable[[str], bool] | None = None, allow_empty: bool = False)

Bases: ImageFolder

: Folder datasets which returns the index of the image as well:

class brails.processors.FoundationClassifier.npid.npid_datasets.MNISTInstance(root: str | Path, train: bool = True, transform: Callable | None = None, target_transform: Callable | None = None, download: bool = False)

Bases: MNIST

MNIST Instance Dataset.

class brails.processors.FoundationClassifier.npid.npid_datasets.MaskFolderInstance(*args, **kwargs)

Bases: ImageFolder

: Slightly hackish way to train on masks quick

Submodules