Draw oriented bounding boxes on the axes. Args: ax (matplotlib.Axes): The input axes. bboxes (ndarray): The input bounding boxes

Performs one iteration of the expectation-maximization algorithm by calling the respective subroutines. Args: x (torch.Te

enn Average Pooling. Args: inplanes (int): The number of input channel. kernel_size (int, optional): The size of kernel.

enn Interpolate.

enn convolution with trivial input featurn. Args: in_channels (List[int]): Number of input channels per scale. out_channels (int)

Evaluate output shape.

Compute the points features similarity for points-wise correlation. Args: points_features (torch.tensor): sampling point feature

Filter the box whose center point is outside or whose side length is less than 5.

Forward features from the upstream network. Args: feats (tuple[Tensor]): Features from the upstream network, each is

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

Transform network output for a batch into bbox predictions. Args: cls_scores (list[Tensor]): Box scores for each scale level

Compute corresponding GT box and classification targets for proposals. Args: proposals_list (list[list]): Multi level poi

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

Get horizontal bboxes from polygons. Args: gt_rbboxes (torch.Tensor): Groundtruth polygons, shape (k, 8). Returns: gt_rect_b

get_horizontal_bboxes from polygons. Args: gt_rbboxes (torch.Tensor): Groundtruth polygons, shape (k, 8). Returns:

get_horizontal_bboxes from polygons. Args: gt_rbboxes (torch.Tensor): Groundtruth polygons, shape (k, 8). Returns:

Get the indices of ORConv2d.

Get multiscale patch sizes and steps. Args: sizes (list): A list of patch sizes. steps (list): A list of steps to slide patches.

Get the offset of AlignConv.

Computes the log-likelihood of the data under the model. Args: x (torch.Tensor): (T, n, 1, d) sum_data (bool,optional

Get sliding windows. Args: info (dict): Dict of image's width and height. sizes (list): List of window's sizes. gaps (lis

Get sliding windows. Args: info (dict): Dict of image's width and height. sizes (list): List of window's sizes. gaps (lis

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

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

Get version of mmrotate.

Args: info (dict): Dict of bbox annotations. windows (np.array): information of sliding windows. iof_thr (float): Thresh

Args: info (dict): Dict of bbox annotations. windows (np.array): information of sliding windows. iof_thr (float): Thresh

Convert horizontal bounding boxes to oriented bounding boxes. Args: hbbs (torch.Tensor): [x_lt,y_lt,x_rb,y_rb] version (Str): ang

Convert horizontal bounding boxes to oriented bounding boxes. Args: hbbs (torch.Tensor): [x_lt,y_lt,x_rb,y_rb] Returns: obbs

Convert horizontal bounding boxes to oriented bounding boxes. Args: hbbs (torch.Tensor): [x_lt,y_lt,x_rb,y_rb] Returns: obbs

Convert horizontal bounding boxes to oriented bounding boxes. Args: hbbs (torch.Tensor): [x_lt,y_lt,x_rb,y_rb] Returns: obbs

inference patches with the detector. Split huge image(s) into patches and inference them with the detector. Finally, merge patch results on o

Initialize assigner and sampler.

Initialize assigner and sampler for each stage.

Initialize ``bbox_head``. Args: bbox_roi_extractor (dict): Config of ``bbox_roi_extractor``. bbox_head (dict): Config

Initialize box head and box roi extractor. Args: bbox_roi_extractor (dict): Config of box roi extractor. bbox_head (d

Kalman filter IoU loss. Args: pred (torch.Tensor): Predicted bboxes. target (torch.Tensor): Corresponding gt bboxes. pred

Kullback-Leibler Divergence loss. Args: pred (torch.Tensor): Convexes with shape (N, 9, 2). target (torch.Tensor): Polygons with

Compute Kullback-Leibler Divergence between two Gaussian distribution. Args: g1 (dict[str, torch.Tensor]): Gaussian distr

Compute overlaps between polygons and points by Kullback-Leibler Divergence loss. Args: gt_rbboxes (torch.Tensor): Ground

Compute Kullback-Leibler Divergence. Args: g1 (dict[str, torch.Tensor]): Gaussian distribution 1. g2 (torch.Tensor): Gaussian dis

Load DOTA dataset. Args: img_dir (str): Path of images. ann_dir (str): Path of annotations. nproc (int): number of proces

Load DOTA dataset. Args: img_dir (str): Path of images. ann_dir (str): Path of annotations. nproc (int): number of proces

Load and convert json_logs to log_dict, key is epoch, value is a sub dict keys of sub dict is different metrics, e.g. memory, bbox_mAP value of

Computes log-responses that indicate the (logarithmic) posterior belief (sometimes called responsibilities) that a data point was gene

Main function of publish model.

Main function of analyze logs.

Main function of image split.

Main function of image split.

Print config.

Build Reslayer.

Map masks to the huge image. Args: masks (list[np.ndarray]): masks need to be mapped. offset (np.ndarray): The offset to translat

Map rois to corresponding feature levels by scales. - scale < finest_scale * 2: level 0 - finest_scale * 2 <= scale < finest_scale *

Inference speed statistics. Args: cfg (object): Test config object. checkpoint (str): Checkpoint file path. max_iter (int

Merge augmented detection bboxes and scores. Args: aug_bboxes (list[Tensor]): shape (n, 4*#class) aug_scores (list[Te

Merging patch bboxes into full image. Args: results (list): Testing results of the dataset. nproc (int): number of pr

Merging patch bboxes into full image. Args: results (list): Testing results of the dataset. nproc (int): number of pr

Merging patch bboxes into full image. Args: results (list): Testing results of the dataset. nproc (int): number of pr

Merge patch results via nms. Args: results (list[np.ndarray] | list[tuple]): A list of patches results. offsets (np.ndarray): Pos

Converts MMRotate model (config + checkpoint) to TorchServe `.mar`. Args: config_file: In MMRotate config format.

Get normalizion layer's name.

Get normalizion layer's name.

Get normalizion layer's name.

nn.Module: normalization layer after the first convolution layer

Get normalizion layer's name.

Get normalizion layer's name.

nn.Module: normalization layer after the second convolution layer

Get normalizion layer's name.

nn.Module: normalization layer after the third convolution layer

Convert oriented bounding boxes to horizontal bounding boxes. Args: obbs (torch.Tensor): [x_ctr,y_ctr,w,h,angle] Returns: hb

Convert oriented bounding boxes to horizontal bounding boxes. Args: obbs (torch.Tensor): [x_ctr,y_ctr,w,h,angle] Returns: hb

Convert oriented bounding boxes to horizontal bounding boxes. Args: obbs (torch.Tensor): [x_ctr,y_ctr,w,h,angle] Returns: hb

Convert oriented bounding boxes to polygons. Args: obbs (torch.Tensor): [x_ctr,y_ctr,w,h,angle] Returns: polys (torch.Tensor

Convert oriented bounding boxes to polygons. Args: obbs (ndarray): [x_ctr,y_ctr,w,h,angle,score] Returns: polys (ndarray): [

Convert oriented bounding boxes to polygons. Args: obbs (ndarray): [x_ctr,y_ctr,w,h,angle,score] Returns: polys (ndarray): [

Convert oriented bounding boxes to polygons. Args: obbs (ndarray): [x_ctr,y_ctr,w,h,angle,score] Returns: polys (ndarray): [

Convert oriented bounding boxes to polygons. Args: obbs (torch.Tensor): [x_ctr,y_ctr,w,h,angle] Returns: polys (torch.Tensor

Convert oriented bounding boxes to horizontal bounding boxes. Args: obbs (torch.Tensor): [x_ctr,y_ctr,w,h,angle] Returns: hb

Convert oriented bounding boxes to horizontal bounding boxes. Args: obbs (torch.Tensor): [x_ctr,y_ctr,w,h,angle] Returns: hb

Convert oriented bounding boxes to horizontal bounding boxes. Args: obbs (torch.Tensor): [x_ctr,y_ctr,w,h,angle] Returns: hb

Parse parameters.

Parse parameters.

Parse parameters.