StanfordCars — Torchvision 0.22 documentation (original) (raw)

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

Stanford Cars Dataset

The Cars dataset contains 16,185 images of 196 classes of cars. The data is split into 8,144 training images and 8,041 testing images, where each class has been split roughly in a 50-50 split

The original URL is https://ai.stanford.edu/~jkrause/cars/car_dataset.html, the dataset isn’t available online anymore.

Note

This class needs scipy to load target files from .mat format.

Parameters:

• root (str or pathlib.Path) – Root directory of dataset
• split (string , optional) – The dataset split, supports "train" (default) or "test".
• 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.
• download (bool, optional) – This parameter exists for backward compatibility but it does not download the dataset, since the original URL is not available anymore.
• loader (callable , optional) – A function to load an image given its path. By default, it uses PIL as its image loader, but users could also pass intorchvision.io.decode_image for decoding image data into tensors directly.

Special-members:

__getitem__(idx: int) → Tuple[Any, Any][source]¶

Returns pil_image and class_id for given index