Reload ``reshape`` from self.tensor.

Cancatenates a box instance list into one single box instance. Similar to ``torch.cat``. Args: box_list (Sequence[T]): A

Reload ``view`` from self.tensor.

Reload ``unsqueeze`` from self.tensor.

Reload ``cpu`` from self.tensor.

Reload ``numpy`` from self.tensor.

Return the mean of the latest ``window_size`` values in log histories. If ``window_size is None`` or ``window_size > len(self._log_hi

Reload new_zeros from self.tensor.

Reload ``permute`` from self.tensor.

Reload ``repeat`` from self.tensor.

Reload ``transpose`` from self.tensor.

Return the attribute of the imported object. Returns: Any: attribute of the imported object.

Reload ``split`` from self.tensor.

Pop the value of the key. If class attribute ``lazy`` is True, the LazyObject will be built and returned. Args: key (str)

Reload ``new_zeros`` from self.tensor.

Yield the keys and values of the dictionary. If class attribute ``lazy`` is False, the value of ``LazyObject`` or ``LazyAttr`` will b

Reload ``flatten`` from self.tensor.

Override the `logging.Formatter.format`` method `. Output the message according to the specified log level. Args: record

Get the model's metainfo by the model name. Args: model_name (str): The name of model. Returns: modelindex.m

Concatenates a sequence of tensors along a new dimension. Similar to ``torch.stack``. Args: box_list (Sequence[T]): A seq

Get the buffer of a specific item. Args: item (str): The demanded item. ids (list[int], optional): The demanded ids.

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

Reload ``expand`` from self.tensor.

Reload ``numel`` from self.tensor.

Reload ``cuda`` from self.tensor.

Sets the module in evaluation mode. This has any effect only on certain modules. See documentations of particular modules for

Update a new data sample.

Returns a copy of the :class:`JitModelAnalysis` object, keeping all settings, but on a new model or new inputs. Args: new

Reload ``squeeze`` from self.tensor.

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

Returns parameters. Compatible with mmcv's build_parameters() Returns: opt_params: a list of body model parameters for optimizati

Returns: list: Contains all keys in data_fields.

Update the tracker. Args: kwargs (dict[str: Tensor | int]): The `str` indicates the name of the input variable. `

Concatenate two human_data. All keys will be kept it the returned human_data. If either value from human_data_0 or human_data_1 matches

Return the minimum value of the latest ``window_size`` values in log histories. If ``window_size is None`` or ``window_size > len(sel

Return the maximum value of the latest ``window_size`` values in log histories. If ``window_size is None`` or ``window_size > len(sel

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

dict: a dictionary of info about the object

Reload ``to`` from self.tensor.

Create new camera class which contains each input camera N times. Args: N: number of new copies of each camera. Returns:

Print a log message. Args: msg (str): The message to be logged. logger (Logger or str, optional): If the type of logger is

Modified from pytorch3d and add `model_type` in __class__.__init__.

Reload ``new_tensor`` from self.tensor.

Reload ``dim`` from self.tensor.

Apply same name function to all tensors in data_fields.

Reload ``detach`` from self.tensor.

Integrate test results.

Reload ``clone`` from self.tensor.

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

Loading information for evaluation. Args: record (dict): Label information or test results. The format might look

See :func:`BaseInstanceMasks.pad`.

Context manager to mark the base config. The pure Python-style configuration file allows you to use the import syntax. However, it is importa

Convert values in numpy.ndarray type to torch.Tensor, and move Tensors to the target device. All keys will exist in the returned dict.

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

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

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

Normalization.

Load data from npz_path and update them to self. Args: npz_path (str): Path to a dumped npz file.

Get latest created ``MMLogger`` instance. :obj:`MMLogger` can call :meth:`get_current_instance` before any instance has been created,

Reload ``dtype`` from self.tensor.

See :func:`BaseInstanceMasks.flip`.

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

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

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

Get the registry record. If `key`` represents the whole object name with its module information, for example, `mmengine.model.BaseMod

Convert all tensors to CPU in data.

See :func:`BaseInstanceMasks.resize`.

Reload ``new_full`` from self.tensor.

Modified from pytorch3d and add `model_type` in __class__.__init__.