CityscapesDataModule

class torch_uncertainty.datamodules.segmentation.CityscapesDataModule(root, batch_size, crop_size=1024, inference_size=(1024, 2048), val_split=None, num_workers=1, pin_memory=True, persistent_workers=True)

DataModule for the Cityscapes dataset.

Parameters:

• root (str or Path) – Root directory of the datasets.

• batch_size (int) – Number of samples per batch.

• crop_size (sequence or int, optional) – Desired input image and segmentation mask sizes during training. If crop_size is an int instead of sequence like \((H, W)\), a square crop \((\text{size},\text{size})\) is made. If provided a sequence of length \(1\), it will be interpreted as \((\text{size[0]},\text{size[1]})\). Defaults to 1024.

• inference_size (sequence or int, optional) – Desired input image and segmentation mask sizes during inference. If size is an int, smaller edge of the images will be matched to this number, i.e., \(\text{height}>\text{width}\), then image will be rescaled to \((\text{size}\times\text{height}/\text{width},\text{size})\). Defaults to (1024,2048).

• val_split (float or None, optional) – Share of training samples to use for validation. Defaults to None.

• num_workers (int, optional) – Number of dataloaders to use. Defaults to 1.

• pin_memory (bool, optional) – Whether to pin memory. Defaults to True.

• persistent_workers (bool, optional) – Whether to use persistent workers. Defaults to True.

Note

This datamodule injects the following transforms into the training and validation/test datasets:

Training transforms:

from torchvision.transforms import v2

v2.Compose([
    v2.ToImage(),
    RandomRescale(min_scale=0.5, max_scale=2.0, antialias=True),
    v2.RandomCrop(size=crop_size, pad_if_needed=True),
    v2.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5),
    v2.RandomHorizontalFlip(),
    v2.ToDtype({
        tv_tensors.Image: torch.float32,
        tv_tensors.Mask: torch.int64,
        "others": None
    }, scale=True),
    v2.Normalize(mean=[0.485, 0.456, 0.406],
                std=[0.229, 0.224, 0.225])
])

Validation/Test transforms:

from torchvision.transforms import v2

v2.Compose([
    v2.ToImage(),
    v2.Resize(size=inference_size, antialias=True),
    v2.ToDtype({
        tv_tensors.Image: torch.float32,
        tv_tensors.Mask: torch.int64,
        "others": None
    }, scale=True),
    v2.Normalize(mean=[0.485, 0.456, 0.406],
                std=[0.229, 0.224, 0.225])
])

This behavior can be modified by overriding self.train_transform and self.test_transform after initialization.