mmlearn.datasets.llvip

LLVIP dataset.

Classes

LLVIPDataset

Low-Light Visible-Infrared Pair (LLVIP) dataset.
class LLVIPDataset(root_dir, train=True, transform=None)[source]

Low-Light Visible-Infrared Pair (LLVIP) dataset.

Loads pairs of RGB and THERMAL images from the LLVIP dataset.

Parameters:

  • root_dir (str) – Path to the root directory of the dataset. The directory should contain ‘visible’ and ‘infrared’ subdirectories.

  • train (bool, default=True) – Flag to indicate whether to load the training or test set.

  • transform (Optional[Callable[[PIL.Image], torch.Tensor]], optional, default=None) – A callable that takes in a PIL image and returns a transformed version of the image as a PyTorch tensor. This is applied to both RGB and thermal images.

__getitem__(idx)[source]

Return an example from the dataset.

Return type:

Example

__len__()[source]

Return the length of the dataset.

Return type:

int