Create an :class:`Instances` object used by the models, from instance annotations in the dataset dict. Args: annos (list[dict]):

Create an :class:`Instances` object used by the models, from instance annotations in the dataset dict. Compared to `annotations_to_instan

Apply a list of :class:`TransformGen` on the input image, and returns the transformed image and a list of transforms. We cannot simply c

Returns: int: the dimension of each anchor box.

Returns: int: the dimension of each anchor box.

Interface for Python inline is needed to prevent multiple function definitions when this header is included by different cpps

Returns: DatasetEvaluator or None It is not implemented by default.

Build a mask head defined by `cfg.MODEL.ROI_INVISIBLE_MASK_HEAD.NAME`.

Args: cfg: a detectron2 CfgNode Returns: backbone (Backbone): backbone module, must be a subclass of :class:`Backbone`.

Args: cfg: a detectron2 CfgNode Returns: backbone (Backbone): backbone module, must be a subclass of :class:`Backbone`.

Returns: iterable It now calls :func:`detectron2.data.build_detection_test_loader`. Overwrite it if you'd like a

Create a list of :class:`TransformGen` from config. Now it includes resizing and flipping. Returns: list[TransformGen]

Concatenates a list of RotatedBoxes into a single RotatedBoxes Arguments: boxes_list (list[RotatedBoxes]) Retur

Args: instance_lists (list[Instances]) Returns: Instances

Concatenates a list of PolygonMasks into a single PolygonMasks Arguments: polymasks_list (list[PolygonMasks]) R

Raise an error if the image does not match the size specified in the dict.

Parse cityscapes annotation files to a dict. Args: files (tuple): consists of (image_file, instance_id_file, label_id_file, json_fil

Args: rgb (bool): whether to return RGB colors or BGR colors. maximum (int): either 255 or 1 Returns: ndarray: a flo

Args: dataset_names (list[str]): list of dataset names Returns: ndarray[int]: a vector of size=#keypoints, storing the

Crop each mask by the given box, and resize results to (mask_size, mask_size). This can be used to prepare training targets for Mask

Draw instance-level prediction results on an image. Args: frame (ndarray): an RGB image of shape (H, W, C), in the range

Draw panoptic prediction results on an image. Args: panoptic_seg (Tensor): of shape (height, width) where the values are

Args: sem_seg (ndarray or Tensor): semantic segmentation of shape (H, W), each value is the integer label.