Convert a list of bboxes to roi format. Args: bbox_list (list[Tensor]): a list of bboxes corresponding to a batch of images.

Build convolution layer Args: cfg (None or dict): cfg should contain: type (str): identify conv layer type. laye

Build normalization layer Args: cfg (dict): cfg should contain: type (str): identify norm layer type. layer args

Convert detection results to a list of numpy arrays. Args: bboxes (Tensor): shape (n, 5) labels (Tensor): shape (n, ) num

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

Get segmentation masks from mask_pred and bboxes. Args: mask_pred (Tensor or ndarray): shape (n, #class+1, h, w).

Random select some elements from the gallery. It seems that Pytorch's implementation is slower than numpy so we use numpy to randperm

Map bboxes from the original image scale to testing scale

Calculate the ious between each bbox of bboxes1 and bboxes2. Args: bboxes1(ndarray): shape (n, 4) bboxes2(ndarray): shape (k, 4)

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

Merge augmented mask prediction. Args: aug_masks (list[ndarray]): shape (n, #class, h, w) img_shapes (list[ndarray]): shape (3, )

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

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

Convert targets by image to targets by feature level. [target_img0, target_img1] -> [target_level0, target_level1, ...]

Unmap a subset of item (data) back to the original set of items (of size count)

Add shared or separable branch convs -> avg pool (optional) -> fcs

Decode distance prediction to bounding box. Args: points (Tensor): Shape (n, 2), [x, y]. distance (Tensor): Distance from the giv

Get class names of a dataset.

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

Dispatch to either CPU or GPU NMS implementations. The input can be either a torch tensor or numpy array. GPU NMS will be used if the input i

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

Compute regression and classification targets for anchors. Args: anchor_list (list[list]): Multi level anchors of each image. val

Flip bboxes horizontally. Args: bboxes(Tensor or ndarray): Shape (..., 4*k) img_shape(tuple): Image shape. Returns:

Map bboxes from testing scale to original image scale

initialize conv/fc bias value according to giving probablity

Build optimizer from configs. Args: model (:obj:`nn.Module`): The model with parameters to be optimized. optimizer_cfg (dict): Th

Evaluate mAP of a dataset. Args: det_results (list): a list of list, [[cls1_det, cls2_det, ...], ...] gt_bboxes (list): ground tr

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

Get points according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. dtype (t

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

Show RPN proposals on the image. Although we assume batch size is 1, this method supports arbitrary batch size.

Filter images too small.