CollaborativeCoding.dataloaders.svhn

Classes

SVHNDataset

An abstract class representing a Dataset.

Module Contents

class CollaborativeCoding.dataloaders.svhn.SVHNDataset(data_path: pathlib.Path, sample_ids: list, train: bool, transform=None, nr_channels=3)

Bases: torch.utils.data.Dataset

An abstract class representing a Dataset.

All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite __getitem__(), supporting fetching a data sample for a given key. Subclasses could also optionally overwrite __len__(), which is expected to return the size of the dataset by many Sampler implementations and the default options of DataLoader. Subclasses could also optionally implement __getitems__(), for speedup batched samples loading. This method accepts list of indices of samples of batch and returns list of samples.

Note

DataLoader by default constructs an index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.

data_path

indexes

split = 'train'

nr_channels = 3

transforms = None

num_classes

_create_h5py(path: str): Downloads the SVHN dataset to the specified directory. Args:

path (str): The directory where the dataset will be downloaded.

__len__(): Returns the number of samples in the dataset. Returns:

int: The number of samples.

__getitem__(index)

Retrieves the image and label at the specified index. Args:

index (int): The index of the sample to retrieve.

Returns:: tuple: A tuple containing the image and its corresponding label.