Merging patch bboxes into full image. Params: results (list): Testing results of the dataset.

NMS for multi-class bboxes. Args: multi_bboxes (torch.Tensor): shape (n, #class*4) or (n, 4) multi_scores (torch.Tensor): shape (

Interface for Python inline is needed to prevent multiple function definitions when this header is included by different cpps

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

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

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

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

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

Convert oriented bounding boxes to polygons. Args: obbs (ndarray): [x_ctr,y_ctr,w,h,angle] Returns: polys (ndarray): [x0,y0,x

Convert oriented bounding boxes to polygons. Args: obbs (ndarray): [x_ctr,y_ctr,w,h,angle] Returns: polys (ndarray): [x0,y0,x

Convert oriented bounding boxes to polygons. Args: obbs (ndarray): [x_ctr,y_ctr,w,h,angle] Returns: polys (ndarray): [x0,y0,x

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 (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: hbb

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

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

Compute the NMS of oriented bboxes in batches.

Compute the NMS of oriented bboxes.

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

Parse information from a line in a requirements text file.

Convert polygons to horizontal bboxes.

Convert polygons to oriented bounding boxes. Args: polys (ndarray): [x0,y0,x1,y1,x2,y2,x3,y3] Returns: obbs (ndarray): [x_ctr

Convert polygons to oriented bounding boxes. Args: polys (ndarray): [x0,y0,x1,y1,x2,y2,x3,y3] Returns: obbs (ndarray): [x_ctr

Convert polygons to oriented bounding boxes. Args: polys (ndarray): [x0,y0,x1,y1,x2,y2,x3,y3] Returns: obbs (ndarray): [x_ctr

Convert polygons to oriented bounding boxes. (r3det version) Args: polys (torch.Tensor): [x0,y0,x1,y1,x2,y2,x3,y3] Returns:

Convert polygons to oriented bounding boxes. Args: polys (torch.Tensor): [x0,y0,x1,y1,x2,y2,x3,y3] Returns: obbs (torch.Tenso

Convert polygons to oriented bounding boxes. Args: polys (torch.Tensor): [x0,y0,x1,y1,x2,y2,x3,y3] Returns: obbs (torch.Tenso

Calculate the intersection points and the mask of whether points is inside the lines. Reference: https://en.wikipedia.org/wiki/Line%E2

Compute the NMS of polygons.

Compute the IoU of polygons.

Calculate overlap between two set of polygons. Args: polygons1 (torch.Tensor): shape (m, 8). polygons2 (torch.Tensor): shape (n,

Print mAP and results of each class. A table will be printed to show the gts/dets/recall/AP of each class and the mAP. Args: mea

Check whether the anchors are inside the border. Args: flat_ranchors (torch.Tensor): Flatten anchors, shape (n, 5). valid_flags (

Compute the IoU of oriented bboxes.

Calculate overlap between two set of bboxes. Args: bboxes1 (torch.Tensor): shape (B, m, 5) in <cx, cy, w, h, a> format or emp

Calculate overlap between two set of bboxes. Args: bboxes1 (torch.Tensor): shape (B, m, 5) in <cx, cy, w, h, a> format or emp

Calculate overlap between two set of bboxes. Args: bboxes1 (torch.Tensor): shape (B, m, 5) in <cx, cy, w, h, a> format or emp

Compute NMS of oriented bboxes.

Sample positive and negative bboxes. This is a simple implementation of bbox sampling given candidates, assigning results and ground

Calculate IoU between 2D bboxes. Args: bboxes1 (torch.Tensor): bboxes have shape (m, 5) in <cx, cy, w, h, a> forma

Calculate IoU between 2D bboxes. Args: bboxes1 (torch.Tensor): bboxes have shape (m, 5) in <cx, cy, w, h, a> forma

Calculate IoU between 2D bboxes. Args: bboxes1 (torch.Tensor): bboxes have shape (m, 5) in <cx, cy, w, h, a> forma

Call function of PolyRandomRotate.

Total number of samples of data.

str: a string describing the module

str: a string describing the module