Randomly generates the absolute crop size based on `crop_type` and `image_size`. Args: image_size (Tuple[int, int]): (h,

Get the pad_shape of each image based on data and pad_size_divisor.

Initialize ``auxiliary_head``

Initialize ``decode_head``

Initialize layers of the head.

Join ``self.data_root`` with ``self.data_prefix`` and ``self.ann_file``. Examples: >>> # self.data_prefix contains relati

Private function to load bounding box annotations. Args: results (dict): Result dict from :obj:``mmengine.BaseDataset``.

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

Private function to load label annotations. Args: results (dict): Result dict from :obj:``mmengine.BaseDataset``. Return

Private function to load mask annotations. Args: results (dict): Result dict from :obj:``mmengine.BaseDataset``.

Collect meta information from the dictionary of meta. Args: metainfo (dict): Meta information dict. If ``metainfo``

Private function to load bounding box annotations. Args: results (dict): Result dict from :obj:``mmengine.BaseDataset``.

Private function to load label annotations. Args: results (dict): Result dict from :obj:``mmengine.BaseDataset``. Return

Private function to load semantic segmentation annotations. Args: results (dict): Result dict from :obj:``mmcv.BaseDataset``.

Mask head forward function used in both training and testing. Args: x (tuple[Tensor]): Tuple of multi-level img features.

Pad masks according to ``results['pad_shape']``.

Private function to convert masks represented with polygon to bitmaps. Args: mask_ann (list | dict): Polygon mask annotat

Transform a single image's features extracted from the head into bbox results. Args: roi (Tensor): Boxes to be transforme

Transform a single image's features extracted from the head into bbox results. Args: roi (Tensor): Boxes to be transforme

Transform a single image's features extracted from the head into bbox results. Args: cls_score_list (list[Tensor]): Box s

Transform a single image's features extracted from the head into bbox results. Args: roi (Tensor): Boxes to be transforme

Transform a single image's features extracted from the head into bbox results. Args: roi (Tensor): Boxes to be transforme

Get segmentation masks from mask_preds and bboxes. Args: mask_preds (Tensor): Predicted foreground masks, has shape

Process gt_masks and filter invalid polygons. Args: results (dict): Result dict from :obj:``mmengine.BaseDataset``. Retu

Get random index. Returns: int: Random index from 0 to ``len(self)-1``

Randomly generate crop offset. Args: margin (Tuple[int, int]): The upper bound for the offset generated randomly.

Private function to randomly sample a scale from a list of tuples. Args: scales (list[tuple]): Images scale range for sampling.

Private function to randomly sample a scale from a tuple. A ratio will be randomly sampled from the range specified by ``ratio_range`

Private function to randomly sample an scale according to the type of ``scale``. Returns: tuple: The targeted scale of th

Record the homography matrix for the RandomFlip.

Record the homography matrix for the Resize.

Resize bounding boxes with ``results['scale_factor']``.

Resize masks with ``results['scale']``

Resize bounding boxes with ``results['scale_factor']``.

Generate the submission of full images. Args: id_list (list): Id of images. dets_list (list): Detection results of pe

Generate the submission of full images. Args: id_list (list): Id of images. dets_list (list): Detection results of pe

Sample negative samples.

Sample positive samples.

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Saves module state to `destination` dictionary. This method is modified from :meth:`torch.nn.Module._save_to_state_dict`. Args: modu

Update palette after loading metainfo. If length of palette is equal to classes, just return the palette. If palette is not defined,

Assign w.r.t. the overlaps of priors with gts. Args: overlaps (Tensor): Overlaps between k gt_bboxes and n bboxes,

Perform forward propagation and loss calculation of the bbox head on the features of the upstream network. Args: x (tuple

Brightness distortion. Args: img (np.ndarray): The input image. Returns: np.ndarray: Image after brightness c

Spatial Relative Positional Embeddings.

Spatial Relative Positional Embeddings.

Spatial Relative Positional Embeddings.

Spatial Relative Positional Embeddings.

Spatial Relative Positional Embeddings.

Spatial Relative Positional Embeddings.