Load data from json/yaml/pickle files. This method provides a unified api for loading data from serialized files. ``load`` supports loading

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

Accumulate per image evaluation results and store the result in self.eval. :param p: input params for evaluation :return: Non

Assign gt to priors. The assignment is done in following steps 1. compute iou between all prior (prior of all pyramid levels) and gt

nn.Module: the normalization layer named "norm1"

Build body_models.

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

Calculate overlap between two set of bboxes. FP16 Contributed by https://github.com/open-mmlab/mmdetection/pull/4889 Note: Assume bbo

Classify each pixel with fc.

Compute and display summary metrics for evaluation results. Note this function can *only* be applied on the default parameter setting

Build loss.

Check whether the suffix of the path is allowed. Args: path_str (str): Path to check. allowed_suffix (List[str], opti

Get the registry record. Args: key (str): The class name in string format. Returns: class: The corresponding

Get tensor data from box type boxes. Args: boxes (Tensor or BaseBoxes): boxes with type of tensor or box type. If its type is

Initialize the given default scope. Args: scope (str): The name of the default scope.

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

Get part keypoints indices from specified part and convention. Args: part (str): part to search from convention (str): data type

Download data from ``filepath`` and write the data to local path. ``get_local_path`` is decorated by :meth:`contxtlib.contextmanager`. It can

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

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

Convert keypoints following the mapping correspondence between src and dst keypoints definition. Supported conventions by now: agora, coco, smplx,

Read data from a given ``filepath`` with 'rb' mode. Note: There are two types of return values for ``get``, one is ``bytes``

Check whether it is a sequence of some type. Args: seq (Sequence): The sequence to be checked. expected_type (type or tuple): Exp

Check whether a file path exists. Args: filepath (str or Path): Path to be checked whether exists. backend_args (dict, optional):

Export output video if need.

Get the drawn image. The format is RGB. Returns: np.ndarray: the drawn image which channel is RGB.

Get subclass instance by name if the name exists. If corresponding name instance has not been created, ``get_instance`` will create a

Check if a module is a model wrapper. The following 4 model in MMEngine (and their subclasses) are regarded as model wrappers: DataParallel,

Draw a confusion matrix by matplotlib. Modified from `Scikit-Learn <https://github.com/scikit-learn/scikit-learn/blob/dc580a8ef/sklea

Match the detection results with the ground_truth. Args: samples (dict[Image]): The detection result packaged by Image.

Reload ``chunk`` from self.tensor.

Initialize and get a logger by name. If the logger has not been initialized, this method will initialize the logger by adding one or two hand

Read data from a given ``filepath`` with 'r' mode. Args: filepath (str or Path): Path to read data. encoding (str): T

nn.Module: the normalization layer named "norm2"

Convert bbox coordinates from (cx, cy, w, h) to (x1, y1, x2, y2). Args: bbox (Tensor): Shape (n, 4) for bboxes. Returns: Ten

Returns a dictionary containing log scalars, runtime information and resumed keys, which should be resumed. The returned ``state_dict

Set self[key] to value. Only be called when using human_data[key] = val. Methods like update won't call __setitem__. In keypoints_comp

Build an instance. Build an instance by calling :attr:`build_func`. Args: cfg (dict): Config dict needs to be built.

Builder for drop out layers.

If a key contains 'keypoints', and f'{key}_mask' is in self.keys(), invalid zeros will be removed and f'{key}_mask' will be locked. R

Run evaluation for each partition.

Scan a directory to find the interested directories or files in arbitrary order. Note: :meth:`list_dir_or_file` returns t

Return a new data element with same type. If ``metainfo`` and ``data`` are None, the new data element will have same metainfo and data

Register a hook from its cfg. Args: hook_cfg (dict): Hook config. It should have at least keys 'type' and 'priority

Resize pos_embed weights. Args: pos_embed (torch.Tensor): Position embedding weights with shape [1, L, C]. src_shape

update progressbar. Args: num_tasks (int): Update step size.

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

Merge another dictionary into current dictionary. Args: other (dict): Another dictionary.

Get anchors according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. batch_i

Get keypoint index from specified convention with keypoint name. Args: name (str): keypoint name convention (str): data type from

Get part keypoints indices from specified part and convention. Args: part (str): part to search from convention (str): data type

A wrapper around :func:`grid_sample` to support 3D point_coords tensors Unlike :func:`torch.nn.functional.grid_sample` it assumes point_coords to

Print a log message.

Since teacher_model is registered as a plain object, it is necessary to put the teacher model to other device when calling ``to`` func

Check whether the suffix of the path is allowed. Args: path_str (str): Path to check. allowed_suffix (List[str], opti

Extract features from images.

Generate grid anchors in multiple feature levels. Args: featmap_sizes (list[tuple]): List of feature map sizes in

Check whether it is a list of some type. A partial method of :func:`is_seq_of`.

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

Unpack ``gt_instances``, ``gt_instances_ignore`` and ``img_metas`` based on ``batch_data_samples`` Args: batch_data_samples (List[:ob

Update runtime information. The key corresponding runtime information will be overwritten each time calling ``update_info``.

Get the average value of current window.

Encode deltas between bboxes and ground truth boxes.

Read an image. Args: img_or_path (ndarray or str or Path): Either a numpy array or str or pathlib.Path. If it is a numpy arra

Load a text file and parse the content as a list of strings. ``list_from_file`` supports loading a text file which can be storaged in differe

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

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

Full connected layer.

Check whether the object has a method. Args: method (str): The method name to check. obj (object): The object to check. Retu

_summary_ Args: keypoints (torch.Tensor): ..., 51

Check output folder or file. Args: output_path (str): could be folder or file. allowed_suffix (List[str], optional):

Get predictions of each enhanced data, a multiple predictions. Args: data (DataBatch): Enhanced data batch sampled from dataloade

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

initialize conv/fc bias value according to a given probability value.

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