Shortcuts

StanfordCars

class torchvision.datasets.StanfordCars(root: Union[str, Path], split: str = 'train', transform: Optional[Callable] = None, target_transform: Optional[Callable] = None, download: bool = False)[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, but it is broken. Follow the instructions in download argument to obtain and use the dataset offline.

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 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. The dataset seems to be available on Kaggle so you can try to manually download and configure it using these instructions, or use an integrated dataset on Kaggle. In both cases, first download and configure the dataset locally, and use the dataset with "download=False".

Special-members:

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

Returns pil_image and class_id for given index

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources