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

Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print('self = {}'.for

Assign gt to bboxes. The assignment is done in following steps 1. compute iou between all bbox (bbox of all pyramid levels) and gt

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

Create random AssignResult for tests or debugging. Kwargs: num_preds: number of predicted boxes num_gts: num

initialize conv/fc bias value according to giving probablity

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

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

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),

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

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

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

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

Create a superset of inputs needed to run test or train batches. Args: input_shape (tuple): input batch dimensions

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

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

Grab configs necessary to create a detector. These are deep copied to allow for safe modification of parameters without influencing other tes

Map bboxes from the original image scale to testing scale

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

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

Assign gt to bboxes. This method assign a gt bbox to every bbox (proposal/anchor), each bbox will be assigned with -1, 0, or a positi

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload

Returns a dictionary of info about the object

Matrix NMS for multi-class masks. Args: seg_masks (Tensor): shape (n, h, w) cate_labels (Tensor): shape (n), mask labels in desce

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

Print a log message. Args: msg (str): The message to be logged. logger (logging.Logger | str | None): The logger to be used. Some

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

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

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

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

Build a module from config dict. Args: cfg (dict): Config dict. It should at least contain the key "type". registry (:obj:`Regist

Calculate a proportional bbox region. The bbox center are fixed and the new h' and w' is h * ratio and w * ratio. Args: bbox (Tensor

Directly extract features from the backbone+neck

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

Get class names of a dataset.

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

Initialize a detector from config file. Args: config (str or :obj:`mmcv.Config`): Config file path or the config object.

converting number to string :param float params_num: number :returns str: number >>> params_to_string(1e9) '1000.0 M' >>> params

Converting the points set into bounding box. :param pts: the input points sets (fields), each points set (fields) is repr

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

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

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

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

Async inference image(s) with the detector. Args: model (nn.Module): The loaded detector. imgs (str/ndarray or list[str/ndarray])

Map bboxes from testing scale to original image scale

Calculate overlap between two set of bboxes. If ``is_aligned`` is ``False``, then calculate the ious between each bbox of bboxes1 and bboxes2

Async context manager that waits for work to complete on given CUDA streams.

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

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

Directly extract features from the backbone+neck