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

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

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

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

Clone the Boxes. Returns: Boxes

Set multiple metadata with kwargs.

Alias of ``pop``.

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

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

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

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

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

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

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

Convert an instance to the destination type using some registered converter. Does recursive lookup for base classes, so there's no ne

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

Register sampler for a field Args: prediction_attr (str): field to replace with a sampled value gt_attr (Optiona

Prepends the provided path with a base path prefix if: 1) base path is not None; 2) path is a local path

Set the field named `name` to `value`. The length of `value` must be the number of instances, and must agree with other exist

Helper for building a conv2d layer.

Args: shape: (h, w) tuple or a int interp: PIL interpolation method

Bilinear interpolation method to be used for upscaling Args: tensor_nchw (tensor): tensor of shape (N, C, H, W)

Args: name (str): the name that identifies a dataset, e.g. "coco_2014_train". func (callable): a callable which takes

Computes the area of all the boxes. Returns: torch.Tensor: a vector with areas of each box.

Extract ground truth values z_gt for valid point indices and estimated values z_est using bilinear interpolation over top-left (y_lo,

Tracing friendly way to cast tensor to another tensor's device. Device will be treated as constant during tracing, scripting the casting proc

Args: boxes (Boxes, RotatedBoxes or ndarray): either a :class:`Boxes`, or an Nx4 numpy array of XYXY_ABS format f

Returns: str: a yaml string representation of the config

Args: tensors: a tuple or list of `torch.Tensor`, each of shape (Hi, Wi) or (C_1, ..., C_K, Hi, Wi) where K >= 1.

Args: io: (str or binary file-like object): input file to load data from Returns: An instance of `DensePoseTr

Given two lists of boxes of size N and M, compute the IoU (intersection over union) between **all** N x M pairs of boxes. The box order m

Initialize the detectron2 logger and set its verbosity level to "DEBUG". Args: output (str): a file name or a directory to save log.

User should either: (1) Call this function to increment storage.iter when needed. Or (2) Set `storage.iter` to the correct iteration

Apply transformation `deltas` (dx, dy, dw, dh) to `boxes`. Args: deltas (Tensor): transformation deltas of shape (N, k*4

Resize the output instances. The input images are often resized when entering an object detector. As a result, we often need the outputs

Find boxes that are non-empty. A box is considered empty, if either of its side is no larger than threshold. Returns:

Fake segmentation loss used when no suitable ground truth data was found in a batch. The loss has a value 0 and is primarily used to

like `get_fields` in the Instances object, but return each field in tensor representations

Returns: HistoryBuffer: the scalar history for name

A 'as_tuple=True' version of torch.nonzero to support torchscript. because of https://github.com/pytorch/pytorch/issues/38718

Preparation for a new round of evaluation. Should be called before starting a round of evaluation.

Get squared Euclidean Distance Matrix Computes pairwise squared Euclidean distances between points Args: pts1: Tensor [M x D], M

Args: start_iter, max_iter (int): See docs above

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

If one size (or aspect ratio) is specified and there are multiple feature maps, we "broadcast" anchors of that single size (or aspect ratio)

Depending on the brightness_factor, gives a lighter or darker color i.e. a color with less or more saturation than the original color

Inverse of ``locate()``. Args: t: any object with ``__module__`` and ``__qualname__``

Same as torchvision.ops.boxes.batched_nms, but with float().

Build a backbone from `cfg.MODEL.BACKBONE.NAME`. Returns: an instance of :class:`Backbone`

Create a small table using the keys of small_dict as headers. This is only suitable for small dictionaries. Args: small_dict (di

Returns the config for a default multi-step LR scheduler such as "1x", "3x", commonly referred to in papers, where every 1x has the total len