Parse bbox and mask annotation. Args: ann_info (list[dict]): Annotation info of an image. with_mask (bool): Whether t

Register a module. Args: module (:obj:`nn.Module`): Module to be registered.

Set flag according to image aspect ratio. Images with aspect ratio greater than 1 will be set as group 1, otherwise group 0.

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

Calculate average precision (for single or multiple scales). Args: recalls (ndarray): shape (num_scales, num_dets) or (num_dets, )

Flip bboxes horizontally. Args: bboxes(ndarray): shape (..., 4*k) img_shape(tuple): (height, width)

inject deep into distutils to customize how the dispatch to cc/nvcc works. If you subclass UnixCCompiler, it's not trivial to get your subclas

Calculate recalls. Args: gts(list or ndarray): a list of arrays of shape (n, 4) proposals(list or ndarray): a list of arrays of s

Get det results and gt information of a certain class.

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

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

Merge augmented proposals (multiscale, flip, etc.) Args: aug_proposals (list[Tensor]): proposals from different testing schem

Prepare an image for testing (multi-scale and flipping)

Print mAP and results of each class. Args: mean_ap(float): calculated from `eval_map` results(list): calculated from `eval_map`

Print recalls in a table. Args: recalls(ndarray): calculated from `bbox_recalls` proposal_nums(ndarray or list): top N proposals

Randomly select a scale from a list of scales or scale ranges. Args: img_scales (list[tuple]): Image scale or scale range. mode (

Refine bboxes during training. Args: rois (Tensor): Shape (n*bs, 5), where n is image number per GPU, and bs is t

Regress the bbox for the predicted class. Used in Cascade R-CNN. Args: rois (Tensor): shape (n, 4) or (n, 5) label (T

Check proposal_nums and iou_thrs and set correct format.