Module to calculate the accuracy. Args: topk (tuple, optional): The criterion used to calculate the accuracy. Def

Total number of samples of data.

The length is multiplied by ``times``

Run forward function and calculate loss for decode head in training.

Initialize ``decode_head``

ADE20K class names for external use.

ADE20K palette for external use.

After train epoch hook.

After train epoch hook.

After train epoch hook.

After train epoch hook.

Test with augmentations. Only rescale=True is supported.

Calculate the binary CrossEntropy loss. Args: pred (torch.Tensor): The prediction with shape (N, 1). label (torch.Tensor): The le

Build backbone.

Build head.

Build neck.

Estimate uncertainty based on seg logits. For each location of the prediction ``seg_logits`` we estimate uncertainty as the difference betwee

Cityscapes class names for external use.

Cityscapes palette for external use.

Classify each pixel.

The wrapper function for :func:`F.cross_entropy`

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.

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

Extra repr.

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.