Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to r

Apply transformation `pred_bboxes` to `boxes`. Args: bboxes (torch.Tensor): Basic boxes. Shape (B, N, 5) or (N, 5) pre

Calculate the length of line. Args: point1 (List): [x,y] point2 (List): [x,y] Returns: length (float)

Directly extract features from the backbone+neck.

Initialize weights of the head.

Limit the range of angles. Args: angle (ndarray): shape(n, ). angle_range (Str): angle representations. Returns: angl

Convert oriented bounding boxes to polygons. Args: obbs (ndarray): [x_ctr,y_ctr,w,h,angle] version (Str): angle representations.

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

Transform outputs for a single batch item into bbox predictions. Args: cls_score_list (list[Tensor]): Box scores for a single sca

Filter predicted bounding boxes at each position of the feature maps. Only one bounding boxes with highest score will be left at each

Convert polygons to oriented bounding boxes. Args: polys (ndarray): [x0,y0,x1,y1,x2,y2,x3,y3] version (Str): angle representation

This function will be used in S2ANet, whose num_anchors=1. Args: cls_scores (list[Tensor]): Box scores for each scale level

Create rotation matrix.

Calculate the distance between two points. Args: point1 (torch.Tensor): shape(n, 2). point2 (torch.Tensor): shape(n, 2). Retu

Evaluate mAP of a dataset. Args: det_results (list[list]): [[cls1_det, cls2_det, ...], ...]. The outer list indicates images,

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

Draw bboxes and class labels (with scores) on an image. Args: img (str or ndarray): The image to be displayed. bboxes (ndarray):

Compute losses of the head. Args: cls_scores (list[Tensor]): Box scores for each scale level Has shape (N, num_an

Convert obboxes to polygons. Args: obboxes (torch.Tensor): Oriented bboxes. Returns: polygons (torch.Tensor)

Random select some elements from the gallery. If `gallery` is a Tensor, the returned indices will be a Tensor; If `gallery` is a ndar

Convert detection results to a list of numpy arrays. Args: bboxes (torch.Tensor): shape (n, 6) labels (torch.Tensor): shape (n, )

Compute the areas of polygons. Args: pts (torch.Tensor) Returns: areas (torch.Tensor)

Initialize layers of feature refine module.

Initialize layers of the head.

Generate the submission of full images. Params: results (list): Testing results of the dataset. out_folder (str, opti

Randomly sample some negative samples.

Randomly sample some positive samples.

Compute overlaps of polygons. Args: bboxes1 (torch.Tensor): shape (m, 5) bboxes2 (torch.Tensor): shape (n, 5) mode (str,

coords should be a N * 2 array-like, containing N couples of (x, y) points

img should be a numpy array, formatted as Height * Width * Nchannels

Performs non-maximum suppression in a batched fashion. Modified from https://github.com/pytorch/vision/blob /505cd6957711af790211896d32b40291

Compute deltas of proposals w.r.t. gt. We usually compute the deltas of x, y, w, h, a of proposals w.r.t ground truth bboxes to get regre

Compute deltas of proposals w.r.t. gt. We usually compute the deltas of x, y, w, h, a of proposals w.r.t ground truth bboxes to get regre

Compute deltas of proposals w.r.t. gt. We usually compute the deltas of x, y, w, h, a of proposals w.r.t ground truth bboxes to get regre

Compute deltas of proposals w.r.t. gt. We usually compute the deltas of x, y, w, h, a of proposals w.r.t ground truth bboxes to get regre

Compute deltas of proposals w.r.t. gt. We usually compute the deltas of x, y, w, h, a of proposals w.r.t ground truth bboxes to get regre

Compute deltas of proposals w.r.t. gt. We usually compute the deltas of x, y, w, h, a of proposals w.r.t ground truth bboxes to get regre

Calculate the convex areas of polygons according to pts and masks. Args: pts (torch.Tensor) masks (torch.Tensor) Returns:

convex sort function.

Apply deltas to shift/scale base boxes. Typically the rois are anchor or proposed bounding boxes and the deltas are network outputs used to sh

Apply deltas to shift/scale base boxes. Typically the rois are anchor or proposed bounding boxes and the deltas are network outputs used to sh

Apply deltas to shift/scale base boxes. Typically the rois are anchor or proposed bounding boxes and the deltas are network outputs used to sh

Apply deltas to shift/scale base boxes. Typically the rois are anchor or proposed bounding boxes and the deltas are network outputs used to sh

Apply deltas to shift/scale base boxes. Typically the rois are anchor or proposed bounding boxes and the deltas are network outputs used to sh

Apply deltas to shift/scale base boxes. Typically the rois are anchor or proposed bounding boxes and the deltas are network outputs used to sh

Get box regression transformation deltas that can be used to transform the ``bboxes`` into the ``gt_bboxes``. Args: bboxes

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

Evaluate and show results. Args: dataset (Dataset): A PyTorch dataset. results (list): Det results from test results

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

Format the results to submission text (standard format for DOTA evaluation). Args: results (list): Testing results of the

Forward function.

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

Get the best begin points of polygons. Args: coordinate (ndarray): shape(n, 9). Returns: reorder coordinate (ndarray): shape(

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

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

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

Initialize weights of feature refine module.