Returns the field called `name`.

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

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

Clone the Boxes. Returns: Boxes

Update features in memory bank. Args: ind (Tensor): Indices for the batch of features. feature (Tensor): Batch of fea

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

Get a copy of the default config. Returns: a detectron2 CfgNode instance.

Args: filepath (str): a string that contains the absolute path, including the file name, where the visualized ima

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

Make this block not trainable. This method sets all parameters to `requires_grad=False`, and convert all BatchNorm layers to

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

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

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

If `resume==True` and `cfg.OUTPUT_DIR` contains the last checkpoint (defined by a `last_checkpoint` file), resume from the file. Resu

Returns: ndarray: the visualized image of shape (H, W, 3) (RGB) in uint8 type. The shape is scale

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

Build normalization layer. Args: cfg (dict): cfg should contain: type (str): identify norm layer type. layer args

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

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

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

Build the whole model architecture, defined by ``cfg.MODEL.META_ARCHITECTURE``. Note that it does not load any weights from ``cfg``.

Returns: str: a yaml string representation of the config

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

Build convolution layer. Args: cfg (None or dict): Cfg should contain: type (str): Identify conv layer type. laye

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

Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x_center, y_center, width, height, an

Create a parser with some common arguments used by detectron2 users. Args: epilog (str): epilog passed to ArgumentParser describing

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

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

Returns: torch.nn.Module: It now calls :func:`detectron2.modeling.build_model`. Overwrite it if you'd like a dif

Perform some basic common setups at the beginning of a job, including: 1. Set up the detectron2 logger 2. Log basic information about en

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

Launch multi-gpu or distributed training. This function must be called on all machines involved in the training. It will spawn child proc

A wrapper around :function:`torch.nn.functional.grid_sample` to support 3D point_coords tensors. Unlike :function:`torch.nn.functional.grid_s

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

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

Same as torchvision.ops.boxes.batched_nms, but safer.

A contextmanager, under which the Instances class in detectron2 is replaced by a statically-typed scriptable class, defined by `fields`.

Remove the field called `name`.

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

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

Transpose/reshape a tensor from (N, (Ai x K), H, W) to (N, (HxWxAi), K)

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

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

Draw instance-level prediction results on an image. Args: predictions (Instances): the output of an instance detection/s

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

Given two lists of rotated boxes of size N and M, compute the IoU (intersection over union) between __all__ N x M pairs of boxes. The

Return the base directory for configurations

Build a module. Args: cfg (dict, list[dict]): The config of modules, it is either a dict or a list of configs. regist

Build a proposal generator from `cfg.MODEL.PROPOSAL_GENERATOR.NAME`. The name can be "PrecomputedProposals" to use no proposal generator.

Args: binary_mask (ndarray): numpy array of shape (H, W), where H is the image height and W is the image width. E

Compare the "keep" result of two nms call. They are allowed to be different in terms of edit distance due to floating point precision iss

Performs non-maximum suppression (NMS) on the rotated boxes according to their intersection-over-union (IoU). Rotated NMS iteratively re

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

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 ord

Return semantic segmentation predictions in the original resolution. The input images are often resized when entering semantic segmentor. Mo

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

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

RoiAlign with scale 1.0 and 0 sample ratio.

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload