Print information about the VQA annotation file. :return:

r"""Get an item from registry with key 'name' Args: name (string): Key whose value needs to be retrieved. default: If

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

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

Assume the first argument is the name of the argument.

Multiple with alpha and add beat with clip.

Build a pretrained model from default configuration file, specified by model_type. Args: - model_type (str): model type,

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

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

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

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 <

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

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

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

Classify each pixel with fc.

Download a file from a URL and cache it locally. If the file already exists, it is not downloaded again. If distributed, only the main proces

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

Load checkpoint as specified in the config file. If load_finetuned is True, load the finetuned model; otherwise, load the pretrained

Utility for deleting a directory. Useful for cleaning the storage space that contains various training artifacts like checkpoints, data etc.

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

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

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

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

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

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.

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

nn.Module: the normalization layer named "norm1"

nn.Module: the normalization layer named "norm2"

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.

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,

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

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

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

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

Common i/o utility to handle loading data from various file formats. Supported: .pkl, .pickle, .npy, .json For the npy files, we

A property to get the DDP-wrapped model on the device.

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