ImageFolder — Torchvision 0.22 documentation (original) (raw)

class torchvision.datasets.ImageFolder(root: ~typing.Union[str, ~pathlib.Path], transform: ~typing.Optional[~typing.Callable] = None, target_transform: ~typing.Optional[~typing.Callable] = None, loader: ~typing.Callable[[str], ~typing.Any] = <function default_loader>, is_valid_file: ~typing.Optional[~typing.Callable[[str], bool]] = None, allow_empty: bool = False)[source]¶

A generic data loader where the images are arranged in this way by default:

root/dog/xxx.png root/dog/xxy.png root/dog/[...]/xxz.png

root/cat/123.png root/cat/nsdf3.png root/cat/[...]/asd932_.png

This class inherits from DatasetFolder so the same methods can be overridden to customize the dataset.

Parameters:

• root (str or pathlib.Path) – Root directory path.
• transform (callable , optional) – A function/transform that takes in a PIL image or torch.Tensor, depends on the given loader, and returns a transformed version. E.g, transforms.RandomCrop
• target_transform (callable , optional) – A function/transform that takes in the target and transforms it.
• loader (callable , optional) – A function to load an image given its path.
• is_valid_file (callable , optional) – A function that takes path of an Image file and check if the file is a valid file (used to check of corrupt files)
• allow_empty – If True, empty folders are considered to be valid classes. An error is raised on empty folders if False (default).