Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Creates a dataset with the specified parameters. Args: dataset_str: A dataset string description (e.g. ImageNet:split=TRAIN).

Dump model and checkpointables to a file. Args: name (str): name of the file. kwargs (dict): extra arbitrary

Build loss.

Creates a data loader with the specified parameters. Args: dataset: A dataset (third party, LaViDa or WebDataset). batch_siz

Setup logging. Args: output: A file name or a directory to save log files. If None, log files will not be saved. If outp

Returns: True if distributed training is enabled

Add prefix for dict. Args: inputs (dict): The input dict with str keys. prefix (str): The prefix to add. Returns: d

Build Match Cost.

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 depth estimation map of the same size as input.

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

Removes extra outputs and hyper-parameters

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher

Inference with slide/whole style. Args: img (Tensor): The input image of shape (N, 3, H, W). img_meta (dict): Image i

Inference with slide/whole style. Args: img (Tensor): The input image of shape (N, 3, H, W). img_meta (dict): Image i

Inference with slide/whole style. Args: img (Tensor): The input image of shape (N, 3, H, W). img_meta (dict): Image i

Create configs and perform basic setups.

@disp: np array (H,W) @invalid_thres: > thres is invalid

Wrapper for grid_sample, uses pixel coordinates

cross_entropy. The wrapper function for :func:`F.cross_entropy` Args: pred (torch.Tensor): The prediction with shape (N, 1). labe

Prediction each pixel.