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

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.

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

IsLittleEndian */

PyObjectCall2Args */

SliceObject */

RaiseArgTupleInvalid */

CodeObjectCache */

Create sample results that can be passed to BBoxHead.get_target

Import a module from albumentations. Inherits some of `build_from_cfg` logic. Args: cfg (dict): Config dict. It should at

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

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

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

Run code concurrently in different streams. :param streamqueue: asyncio.Queue instance. Queue tasks define the pool of streams used for conc

Simple version of the ``kwarray.ensure_rng`` Args: rng (int | numpy.random.RandomState | None): if None, then defaults t

Base on the previous bboxes and regression values, we compute the regressed bboxes and generate the grids on the bboxes.

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

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

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

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

Dictionary mapper. Renames keys according to keymap provided. Args: d (dict): old dict keymap (dict)

Change from point offset to point coordinate.

Compute corresponding GT box and classification targets for proposals. Args: points_list (list[list]): Multi level points of each image.

Print time spent by CPU and GPU. Useful as a temporary context manager to find sweet spots of code suitable for async implementation.

Simple version of ``kwimage.Boxes.random`` Returns: Tensor: shape (n, 4) in x1, y1, x2, y2 format. References: https://

Set random seed. Args: seed (int): Seed to be used. deterministic (bool): Whether to set the deterministic option for

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.

BufferFormatCheck */