Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the

Save checkpoint to file. The checkpoint will have 3 fields: ``meta``, ``state_dict`` and ``optimizer``. By default ``meta`` will contain vers

Scan a directory to find the interested files. Args: dir_path (str | obj:`Path`): Path of the directory. suffix (str | tuple(str)

Scatter inputs to target gpus. The only difference from original :func:`scatter` is to add support for :type:`~mmcv.parallel.DataContainer`.

Scatters tensor across multiple GPUs.

shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir

shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir

Draw `result` over `img`. Args: img (str or Tensor): The image to be displayed. result (Tensor): The semantic segment

Time since the last checking. Either :func:`since_start` or :func:`since_last_check` is a checking operation. Returns (float

Test with single GPU. Args: model (nn.Module): Model to be tested. data_loader (utils.data.Dataloader): Pytorch data loader.

Singlestep solver DPM-Solver-3 from time `s` to time `t`. Args: x: A pytorch tensor. The initial value at time `s`.

Start the timer.

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be

Track the progress of tasks execution with a progress bar. Tasks are done with a simple for-loop. Args: func (callable): The functio

update the current loss scale value when overflow happens.

Wrap the FP32 model to FP16. If you are using PyTorch >= 1.6, torch.cuda.amp is used as the backend, otherwise, original mmcv implementation

Zero out the parameters of a module and return it.

Returns a diagonal matrix of size [n, n]. The diagonal are all "-inf". This is for avoiding calculating the overlapped element in the Criss-C

Add children for a registry. The ``registry`` will be added as children based on its scope. The parent registry could build objects f

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

Check branches configuration.

Build :obj:`ConcatDataset by.

Convert trainId to id for cityscapes.

Convert segmentation label to onehot. Args: seg_label (Tensor): Segmentation label of shape (N, H, W). num_classes (i

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

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

Dump the initialization information to a file named `initialization.log.json` in workdir. Args: logger_name (str): The na

Evaluation in Cityscapes protocol. Args: results (list): Testing results of the dataset. logger (logging.Logger | str

Expand onehot labels to match the size of prediction.

Fuse conv and bn into one module. Args: conv (nn.Module): Conv to be fused. bn (nn.Module): BN to be fused. Returns:

Finds a loader that supports the given path. Falls back to the local loader if no other loader is found. Args: path (str)

Generate the shear matrix for transformation. Args: magnitude (int | float): The magnitude used for shear. direction (str): The f

Generate the translate matrix. Args: offset (int | float): The offset used for translate. direction (str): The translate directio

Check if params contain NaN.

Initialize ``auxiliary_head``

Initialize ``decode_head``