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

Recursively instantiate objects defined in dictionaries by "_target_" and arguments. Args: cfg: a dict-like object with "_target

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

Clone the Boxes. Returns: Boxes

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

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

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

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

Set multiple metadata with kwargs.

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

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

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

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

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

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

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

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

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

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

Load content from the given config file and merge it into self. Args: cfg_filename: config filename allow_un

If input instances don't have ID, ID_period, lost_frame_count fields, this method is used to initialize these fields. Args:

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

Arguments: pred_logits, pred_deltas, pred_masks: Same as the output of: meth:`TensorMaskHead.forward`

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

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

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

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

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 random Nx4 boxes tensor, with coordinates < max_coord.

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

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

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

Returns: str: a yaml string representation of the config

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.

Helper for building a conv2d layer.

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

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

Similar to `build_detection_train_loader`, with default batch size = 1, and sampler = :class:`InferenceSampler`. This sampler coordinates all

Returns a config object for a model in model zoo. Args: config_path (str): config file name relative to detectron2's "configs/"

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

Register hooks to the trainer. The hooks are executed in the order they are registered. Args: hooks (list[Option

Alias of ``pop``.

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

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

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

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

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

Returns: HistoryBuffer: the scalar history for name

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

Load model from file. Args: path (str): file path

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

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

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

Draw annotations/segmentations in Detectron2 Dataset format. Args: dic (dict): annotation/segmentation data of one image

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

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

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

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

Args: input, other (Instances): size_as_tensor: compare image_size of the Instances as tensors (instead of tuples).

Build a dataloader for object detection with some default features. Args: dataset (list or torch.utils.data.Dataset): a list of data

Get frequency weight for each class sorted by class id. We now calcualte freqency weight using image_count to the power freq_weight_power.

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