Generate base anchors of a single level. Args: base_sizes_per_level (list[tuple[int, int]]): Basic sizes of ancho

Generate buckets w.r.t bucket number and scale factor of proposals. Args: proposals (Tensor): Shape (n, 4) num_buckets (int): Num

Generates per block width from RegNet parameters. Args: initial_width ([int]): Initial width of the backbone width_sl

return x GiB.

Calculate absolute positional embeddings. If needed, resize embeddings and remove cls_token dimension for the original embeddings. Ar

Get anchors according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. img_met

Get annotation of dataset by index. Args: idx (int): Index of data. Returns: dict: Annotation info of specif

Get OpenImages annotation by index. Args: idx (int): Index of data. Returns: dict: Annotation info of specif

A wrapper for computing ATSS targets for points in multiple images. Args: cls_scores (list[Tensor]): Box iou-aware scores for eac

Transform network outputs of a batch into bbox results. Note: When score_factors is not None, the cls_scores are usually multiplied b

Transform network outputs for a batch into bbox predictions. Args: all_cls_scores_list (list[Tensor]): Classification outputs

Get a dict with class as key and img_ids as values, which will be used in :class:`ClassAwareSampler`. Returns: dict[list]

Get category ids by index. Args: idx (int): Index of data. Returns: list[int]: All categories in the image o

Get class names of current dataset. Args: classes (Sequence[str] | str | None): If classes is None, use default C

Get det results and gt information of a certain class. Args: det_results (list[list]): Same as `eval_map()`. annotations (list[di

Get cls targets for DDOD head. This method is almost the same as `AnchorHead.get_targets()`. Besides returning the targets as the par

Compute FCOS regression and classification targets for points in multiple images. Args: points (list[Tensor]): Points of

Get gt priorities according to their areas. Smaller gt has higher priority. Args: gt_bboxes (Tensor): Ground truth boxes

Get OpenImages annotation by index. Args: image_level_ann_file (str): CSV style image level annotation file path.

Set images original shape into data_infos.

Call function to collect indexes. Args: dataset (:obj:`MultiImageMixDataset`): The dataset. Returns: list: i

Get the layer id to set the different learning rates in ``layer_wise`` decay_type. Args: var_name (str): The key of the model.

Get the layer id to set the different learning rates. Args: var_name (str): The key of the model. num_max_layer (int): Maximum nu

Get image metas from pkl file.

Args: group_queries (int): Number of dn queries in one group.

Get the anchors of each scale level inside. Args: num_level_anchors (list[int]): Number of anchors of each scale

Run the model in onnxruntime env. Args: feat (list[Tensor]): A list of tensors from torch.rand, each is a 4D-tensor. Ret

Get the position embedding of proposal.

Get reg targets for DDOD head. This method is almost the same as `AnchorHead.get_targets()` when is_cls_assigner is False. Besides re

Get precessed :obj:`InstanceData` of multiple images.

Get ``num_points`` most uncertain points with random points during train. Sample points in [0, 1] x [0, 1] coordinate space based on

Get the stage id to set the different learning rates in ``stage_wise`` decay_type. Args: var_name (str): The key of the model.

Gets widths/stage_blocks of network at each stage. Args: widths (list[int]): Width in each stage. Returns: t

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Keys

Compute bucketing targets. Args: approx_list (list[list]): Multi level approxs of each image. inside_flag_list (list[l

Compute regression targets and each point inside or outside gt_bbox in multiple images. Args: points (list[Tensor]): Poin

Compute regression and classification targets in multiple images. Args: gt_bboxes (list[Tensor]): Ground truth bboxes for each im

Compute target maps for anchors in multiple images. Args: anchor_list (list[list[Tensor]]): Multi level anchors of each

Compute regression and classification targets for anchors in multiple images. Args: anchor_list (list[list[Tensor]]): Mul

Compute instance segmentation targets for each image. Args: mask_pred (Tensor): Predicted prototypes with shape (

Compute regression and classification targets for anchors. Args: anchor_list (list[list]): Multi level anchors of each image.

Compute regression and classification targets for anchors in multiple images. Args: cls_scores (Tensor): Classification p

Compute classification and mask targets for all images for a decoder layer. Args: cls_scores_list (list[Tensor]): Mask sc

Compute regression and classification targets for anchors in multiple images. Args: cls_scores_list (list[Tensor])： Class

Get targets for ATSS head. This method is almost the same as `AnchorHead.get_targets()`. Besides returning the targets as the parent

Get targets for GFL head. This method is almost the same as `AnchorHead.get_targets()`. Besides returning the targets as the parent m

Compute regression, classification and centerness targets for points in multiple images. Args: points (list[Tensor]): Poi

Generate corner targets. Including corner heatmap, corner offset. Optional: corner embedding, corner guiding shift, centripetal shif

Compute regression and classification targets for a batch image. Outputs from a single decoder layer of a single feature level are used.

Compute target of mask IoU. Mask IoU target is the IoU of the predicted mask (inside a bbox) and the gt mask of corresponding gt mask

Compute regression and classification targets for a batch image. Outputs from a single decoder layer of a single feature level are used.

Get widths and heights of bboxes and shapes of images. Returns: tuple[np.ndarray]: Array of bbox shapes and array of image

r"""`Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression <https://arxiv.org/abs/1902.09630>`_. Args:

A general separation scheme for gmm model. It separates a GMM distribution of candidate samples into three parts, 0 1 and uncertain a

General visualization GT and result function. Args: img (str | ndarray): The image to be displayed. annotation (dict): Ground truth a

Initialize assigner and sampler.

Initialize ``bbox_head``

Initialize layers of the DeformableDetrTransformer.

Initialize ``mask_head``

Initialize ``point_head``

Initialize random seed. If the seed is not set, the seed will be automatically randomized, and then broadcast to all processes to prevent som

Instance segmengation postprocess. Args: mask_cls (Tensor): Classfication outputs of shape (num_queries, cls_out_

IoU loss. Computing the IoU loss between a set of predicted bboxes and target bboxes. The loss is calculated as negative log of IoU. Arg

Returns a bool indicating if MLU is currently available.

Expectation part of EM algorithm(Expectation-Maximization)

r"""Loss function for knowledge distilling using KL divergence. Args: pred (Tensor): Predicted logits with shape (N, n + 1). soft