Print information about the VQA annotation file. :return:

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

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

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

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

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

Clone the Boxes. Returns: Boxes

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

Returns: str: a yaml string representation of the config

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

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

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

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

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

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

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.

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

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

Set multiple metadata with kwargs.

r""" Instantiate a PretrainedConfig from a pre-trained model configuration. Params: **pretrained_model_name_or_path**: either:

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

In-place transform all attributes of this class. By "in-place", it means after calling this method, accessing an attribute such

Append a new message.

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

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

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

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

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

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

Run inference on the given inputs. Args: batched_inputs (list[dict]): same as in :meth:`forward` detected_in

Helper for building a conv2d layer.

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

Create a random Nx4 boxes tensor, with coordinates < max_coord.

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

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

Alias of ``pop``.

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

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

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

Get a conversation template.

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

Args: predictions: return values of :meth:`forward()`. proposals (list[Instances]): proposals that match the features

Args:

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

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

Returns: bool: whether the field called `name` exists.

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

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

Save a configuration object to a directory, so that it can be re-loaded using the `from_pretrained(save_directory)` class method.

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

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

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

Create a ResNet instance from config. Returns: ResNet: a :class:`ResNet` instance.

Get the prompt for generation.

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

Put multiple scalars from keyword arguments. Examples: storage.put_scalars(loss=my_loss, accuracy=my_accuracy, smoothin

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