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

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

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

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

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

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

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

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

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

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

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

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

Due to some issues with `torch.distributed.barrier()`, we have to implement this ugly barrier function.

Map bboxes from the original image scale to testing scale

Get class names of a dataset.

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

Dispatch to either CPU or GPU NMS implementations.

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

3x3 convolution with padding

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

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

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

Test only det bboxes without augmentation.

Filter images too small.