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

Clone the Boxes. Returns: Boxes

Print information about the annotation file. :return:

Print information about the annotation file. :return:

Makes a function retry itself after encountering pytorch's CUDA OOM error. It will first retry after calling `torch.cuda.empty_cache()`.

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

Args: prob (float): probability of flip. horizontal (boolean): whether to apply horizontal flipping verti

Return an activation function given a string

Get ann ids that satisfy given filter conditions. default skips that filter :param vidIds (int array) : get anns for given vids

Get ann ids that satisfy given filter conditions. default skips that filter :param vidIds (int array) : get anns for given vids

Load anns with the specified ids. :param ids (int array) : integer ids specifying anns :return: anns (object array) : l

Load anns with the specified ids. :param ids (int array) : integer ids specifying anns :return: anns (object array) : l

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

Register a dataset in YTVIS's json annotation format for instance tracking. Args: name (str): the name that identifies a dataset

Convert the model into training mode while keep layers freezed.

Args: backbone: a backbone module, must follow detectron2's backbone interface sem_seg_head: a module that predicts s

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features t

Args: dim (int): Number of input channels. num_heads (int): Number of attention heads in each ViT block.

Return an activation function given a string

Return an activation function given a string

Add config for MASK_FORMER.

Args: frames (List[np.ndarray]): a list of images of shape (H, W, C) (in BGR order). This is the format used by O

NOTE: this interface is experimental. Args: input_shape: shapes (channels and stride) of the input features c

Derive the desired score numbers from summarized COCOeval. Args: coco_eval (None or COCOEval): None represents no predict

Evaluate the coco results using COCOEval API.

A context which ignores CUDA OOM exception from pytorch.

Randomly modifies given color to produce a slightly different color than the color given. Args: color (tuple[double]): a

Positionally encode points that are normalized to [0,1].

Convert annotation which can be polygons, uncompressed RLE to RLE. :return: binary mask (numpy 2D array)

Convert annotation which can be polygons, uncompressed RLE to RLE. :return: binary mask (numpy 2D array)

Build a dataloader for object detection with some default features. This interface is experimental. Args: dataset (list or torch

Build a pixel decoder from `cfg.MODEL.MASK_FORMER.PIXEL_DECODER_NAME`.

We estimate uncerainty as L1 distance between 0.0 and the logit prediction in 'logits' for the foreground class in `classes`. Args:

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

Filter out empty instances in an `Instances` object. Args: instances (Instances): by_box (bool): whether to filter out insta

Filter out empty instances in an `Instances` object. Args: instances (Instances): by_box (bool): whether to filter out insta

Positionally encode points that are not normalized to [0,1].

filtering parameters. default skips that filter. :param catNms (str array) : get cats for given cat names :param supNms (str

filtering parameters. default skips that filter. :param catNms (str array) : get cats for given cat names :param supNms (str