Concatenates a list of Boxes into a single Boxes Arguments: boxes_list (list[Boxes]) Returns: Boxes

Convert all tensor to np.narray in data.

Convert all tensors to CPU in data.

Access an attribute and return its value if exists. Otherwise return default.

Clip (in place) the boxes by limiting x coordinates to the range [0, width] and y coordinates to the range [0, height]. Args

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

Update a new data sample.

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

Convert all tensors to GPU in data.

Detach all tensors in data.

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

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

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

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

Run evaluation for each partition.

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 torch tensor to numpy.ndarray. Args: x (Tensor | Sequence[Tensor]): A single tensor or a sequence of tensors

Create a dummy batch of model inputs and data samples.

Clone the Boxes. Returns: Boxes

Args: norm (str or callable): either one of BN, SyncBN, FrozenBN, GN; or a callable that takes a channel number and returns

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

Initialize model weights.

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:

pop property in data and metainfo as the same as python.

Creates an EfficientNet model. Ref impl: https://github.com/tensorflow/tpu/blob/master/models/official/efficientnet/efficientnet_model.py Pap

Encode keypoints into root heatmaps and keypoint displacement fields. Note that the original keypoint coordinates should be in the inp

Process one batch of data samples and predictions. The processed results should be stored in ``self.results``, which will be used to c

Args: predictions: D2 Instances for predictions of the current frame Return: D2 Instances for predictions of

Special method for set union field, used as property.setter functions.

Set multiple metadata with kwargs.

Efficient version of torch.cat that avoids a copy if there is only a single element in a list

Save a config object to a yaml file. Note that when the config dictionary contains complex objects (e.g. lambda), it can't be

Decode the keypoint coordinates from heatmaps and displacements. The decoded keypoint coordinates are in the input image space. Args:

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

Add a scalar `value` to the `HistoryBuffer` associated with `name`. Args: smoothing_hint (bool): a 'hint' on whether thi

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

Args: box: can be a k-tuple, k-list or an Nxk array/tensor, where k = 4 or 5 from_mode, to_mode (BoxMode) Re

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

nn.Module: the normalization layer named "norm1"

nn.Module: the normalization layer named "norm2"

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

Create a dummy data sample in COCO style.

Returns: The :class:`EventStorage` object that's currently being used. Throws an error if no :class:`EventStorage` is currently e

Load data from json/yaml/pickle files. This method provides a unified api for loading data from serialized files. Note: In v1.3.16 a

Load meta information of pose dataset and check its integrity. Args: metainfo (dict): Raw data of pose meta information, which should

This function is a replacement of .to(another_device) such that it allows the casting to be traced properly by explicitly calling the underly

Classify each pixel with fc.

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

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

Calculate the pose accuracy of PCK for each individual keypoint and the averaged accuracy across all keypoints for coordinates. Note:

Load a config file. Args: filename: absolute path or relative path w.r.t. the current working directory keys

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

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

Get the expansion of a residual block. The block expansion will be obtained by the following order: 1. If ``expansion`` is given, just retur

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