1D cosine window.

Concat multi-level feature maps by image. [feature_level0, feature_level1...] -> [feature_image0, feature_image1...] Convert the shape of eac

Make plugins for ResNet ``stage_idx`` th stage. Currently we support to insert ``context_block``, ``empirical_attention_block``, ``no

Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mod

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

Prepare an example input image for ``generate_inputs_and_wrap_model``. Args: input_config (dict): customized config describing the exampl

sample numbers uniformly between a and b. args: a - lower bound b - upper bound shape - shape of the output tensor r

Dump the detection results to a COCO style json file. There are 3 types of results: proposals, bbox predictions, mask predictions, an

Main conjugate gradient method. args: num_iter: Number of iterations. x: Initial guess. Assumed zero if None.

Split side-aware features aligned with orders of bucketing targets.

See :func:`BaseInstanceMasks.to_tensor`.

Generate list of trackers. args: name: Name of tracking method. parameter_name: Name of parameter file. run_ids: A single

Convert ``xyxy`` style bounding boxes to ``xywh`` style for COCO evaluation. Args: bbox (numpy.ndarray): The bounding box

args: datasets - List of datasets to be used for training p_datasets - List containing the probabilities by which eac

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

Box head forward function used in both training and testing. Returns all regression, classification results and a intermediate feature.

Decode init_proposal_bboxes according to the size of images and expand dimension of init_proposal_features to batch_size. Args:

Gather feature according to index. Args: feat (Tensor): Target feature map. ind (Tensor): Target coord index.

Initialize classification conv layers of the head.

Initialize bbox regression conv layers of the head.

Mask head forward function used in both training and testing.

Run forward function and calculate loss for mask head in training.

Get anchor centers from anchors. Args: anchors (Tensor): Anchor list with shape (N, 4), "xyxy" format. Returns:

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. img (str | ndarray): Either image files

Test det bboxes with test time augmentation. Args: feats (list[Tensor]): the outer list indicates test-time augme

Decode bounding box based on distances. Args: points (Tensor): Shape (n, 2), [x, y]. bbox (Tensor): Shape (n, 4), "xyxy" format

The key correspondence from bboxes to labels, masks and segmentations.

Convert bbox coordinates from (x1, y1, x2, y2) to (cx, cy, w, h). Args: bbox (Tensor): Shape (n, 4) for bboxes. Returns: Ten

Builder of IoU calculator.

Build neck.

Classification-Aware Regression Loss (CARL). Args: cls_score (Tensor): Predicted classification scores. labels (Tensor): Targets

Check if norm layer is in correct train state.

Collect the information of the running environments.

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

Convert the torch forward outputs containing tuple or list to a list only containing torch.Tensor. Args: output (list(Tensor) | tuple

see :func:`BaseInstanceMasks.crop`

Compute region similarity as the Jaccard Index. :param fg_mask: (ndarray): binary segmentation map. :param gt_mask: (ndarray): binary annota

Map from level to values.

Calculate recalls. Args: gts (list[ndarray]): a list of arrays of shape (n, 4) proposals (list[ndarray]): a list of arrays of sha

Directly extract features from the backbone+neck.

Flattens predictions in the batch (binary case) Remove labels equal to 'ignore'

Format the results to json (standard format for COCO evaluation). Args: results (list[tuple | numpy.ndarray]): Testing results of

Args: img (Tensor): Input images of shape (N, C, H, W). Typically these should be mean centered and std scaled.

Count the annotation mask pixels per object, per frame, in all sequences in a dataset :param dset_name: Dataset name, for prin

Get category ids of repeat dataset by index. Args: idx (int): Index of data. Returns: list[int]: All categor

Get COCO category ids by index. Args: idx (int): Index of data. Returns: list[int]: All categories in the im

Estimate target bounding box using the predicted segmentation probabilities

A wrapper for computing ATSS and FCOS targets for points in multiple images. Args: cls_scores (list[Tensor]): Box iou-awa