Decorator: Raises ValueError when the number of output nodes is less than the number of input nodes.

Decorator: Raises ValueError for non square masks.

Builds the discriminator graph. Args: image: The current batch of images to classify as fake or real. labels: The corresponding label

TF-GAN compatible discriminator.

Embedded gaussian with temperature.

Embedded gaussian with temperature.

Placeholder for encode images with backbone and decode into a semantic segmentation map of the same size as input.

Encode images with backbone and decode into a semantic segmentation map of the same size as input.

Placeholder for encode images with backbone and decode into a semantic segmentation map of the same size as input.

Encode images with backbone and decode into a semantic segmentation map of the same size as input.

Abstract method that takes (rows, cols) as input and returns a dict that maps 1d numbers to 2d locations.

Evaluate the results. Args: results (list[tuple[torch.Tensor]] | list[str]]): per image pre_eval results or predi

Evaluation in Cityscapes/default protocol. Args: results (list): Testing results of the dataset. metric (str | list[s

Evaluate the results. Args: results (list[tuple[torch.Tensor]] | list[str]]): per image pre_eval results or predi

Evaluation in Cityscapes/default protocol. Args: results (list): Testing results of the dataset. metric (str | list[s

Extra repr.

Extra repr.

Format the results into dir (standard format for LoveDA evaluation). Args: results (list): Testing results of the dataset.

Place holder to format result to dataset specific output.

format result for every sample of ConcatDataset.

Format the results into dir (standard format for Cityscapes evaluation). Args: results (list): Testing results of the dat

Format the results into dir (standard format for LoveDA evaluation). Args: results (list): Testing results of the dataset.

Place holder to format result to dataset specific output.

format result for every sample of ConcatDataset.

Format the results into dir (standard format for Cityscapes evaluation). Args: results (list): Testing results of the dat

Calls either :func:`forward_train` or :func:`forward_test` depending on whether ``return_loss`` is ``True``. Note this setting will c

Forward function.

Forward function.

Forward function.

Forward function.

Forward function.

Forward function.

Args: x (tensor): input features with shape of (num_windows*B, N, C) mask (tensor | None, Optional): mask with shape