Expand the tensor `v` to the dim `dims`. Args: `v`: a PyTorch tensor with shape [N]. `dim`: a `int`. Returns: a P

Load model from file. Args: path (str): file path

Build normalization layer. Args: cfg (dict): The norm layer config, which should contain: - type (str): Layer type.

Build convolution layer. Args: cfg (None or dict): The conv layer config, which should contain: - type (str): Layer type.

Convert a version string into a tuple of integers. This method is usually used for comparing two versions. For pre-release versions: alpha <

Create a 1D, 2D, or 3D convolution module.

Register a module. A record will be added to `self._module_dict`, whose key is the class name or the specified name, and value is the

Loads the loss_scaler state dict. Args: state_dict (dict): scaler state.

Transform inputs for decoder. Args: inputs (list[Tensor]): List of multi-level img features. Returns: Tensor

Classify each pixel with fc.

Check whether a file path exists. Args: filepath (str or Path): Path to be checked whether exists. Returns:

Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].

Returns the state of the scaler as a :class:`dict`.

Call all hooks. Args: fn_name (str): The function name in each hook to be called, such as "before_train_epoch".

Compute sigma_t of a given continuous-time label t in [0, T].

Read the next frame. If the next frame have been decoded before and in the cache, then return it directly, otherwise decode, cache an

Build a module from config dict. Args: cfg (dict): Config dict. It should at least contain the key "type". registry (:obj:`Regist

Compute log(alpha_t) of a given continuous-time label t in [0, T].

Convert the model to the noise prediction model or the data prediction model.

Print a log message. Args: msg (str): The message to be logged. logger (logging.Logger | str | None): The logger to be used.

Remove a file. Args: filepath (str, Path): Path to be removed.

Load checkpoint from a file or URI. Args: model (Module): Module to load checkpoint. filename (str): Accept local filepath, URL,

Whether the input is an string instance. Note: This method is deprecated since python 2 is no longer supported.

Convert a ``filepath`` to standard format of petrel oss. If the ``filepath`` is concatenated by ``os.path.join``, in a Windows enviro

Map ``filepath`` to a string path whose prefix will be replaced by :attr:`self.path_mapping`. Args: filepath (str): Path

Get the current training iteration step.

Check whether a file path is a file. Args: filepath (str or Path): Path to be checked whether it is a file. Returns:

Register a hook into the hook list. The hook will be inserted into a priority queue, with the specified priority (See :class:`Priorit

Recursively convert Tensor in inputs from src_type to dst_type. Args: inputs: Inputs that to be casted. src_type (torch.dtype): S

Infer a suitable file client based on the URI and arguments. Args: file_client_args (dict, optional): Arguments to instantiate a

Check if a module is a module wrapper. The following 3 modules in MMCV (and their subclasses) are regarded as module wrappers: DataParallel,

nn.Module: the normalization layer named "norm1"

nn.Module: the normalization layer named "norm2"

Zero out the parameters of a module and return it.

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

Multiple with alpha and add beat with clip.

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

Update the `_params_init_info` in the module if the value of parameters are changed. Args: module (obj:`nn.Module`): The module of Py

Check whether a file path is a directory. Args: filepath (str or Path): Path to be checked whether it is a direct

Concatenate all file paths. Join one or more filepath components intelligently. The return value is the concatenation of filepath and

Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and