SemanticSegmentationImageDataset

class SemanticSegmentationImageDataset

Bases: ImageDataset

Reads semantic segmentatioin images and labels from files.

Uses SemanticSegmentationDataReader to read the data.

__init__(img_dir: str, label_dir: str, *args, **kwargs)

Constructor.

Parameters:

• img_dir (str) – Directory containing images.

• label_dir (str) – Directory containing segmentation masks.

• *args – See ImageDataset.__init__().

• **kwargs – See ImageDataset.__init__().

Methods

__init__(img_dir, label_dir, *args, **kwargs)

Constructor.

__add__(other: Dataset[T_co]) → ConcatDataset[T_co]

Parameters:

other (Dataset[T_co]) –

Return type:

ConcatDataset[T_co]

__getitem__(key) → tuple[torch.Tensor, torch.Tensor]

Return type:

tuple[torch.Tensor, torch.Tensor]

__init__(img_dir: str, label_dir: str, *args, **kwargs)

Constructor.

Parameters:

• img_dir (str) – Directory containing images.

• label_dir (str) – Directory containing segmentation masks.

• *args – See ImageDataset.__init__().

• **kwargs – See ImageDataset.__init__().