RetinanNet Head Config.

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

Expand an array of boxes by a given scale. Args: bboxes (Tensor): Shape (m, 4) scale (float): The scale factor of bboxes Ret

Test only det bboxes without augmentation. Args: x (tuple[Tensor]): Feature maps of all scale level. img_metas (list[

Generate grid anchors of a single level. Note: This function is usually called by method ``self.grid_priors``. Args:

str: a "nice" summary string describing this module

Assign gt to priors using SimOTA. Args: pred_scores (Tensor): Classification scores of one image, a 2D-Tensor with

Initialize conv layers of a single level head.

Check whether the `num_classes` in head matches the length of `CLASSES` in `dataset`. Args: runner (obj:`EpochBasedRunner

Crop image with a given center and size, then paste the cropped image to a blank image with two centers align. This function is equiv

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

Check whether the center of each box is in the patch. Args: patch (list[int]): The cropped area, [left, top, right, bottom].

Fuse global context feats with roi feats.

Get adaptive scales according to areas. The scale range is [0.5, 1.0]. When the area is less than ``'min_area'``, the scale is 0.5 while the

Transform outputs of a single image into bbox predictions. Args: cls_score_list (list[Tensor]): Box scores from all scale

Transform outputs for a single batch item into bbox predictions. Args: tl_heat (Tensor): Top-left corner heatmap for current leve

Get final border for the target size. This function generates a ``final_border`` according to image's shape. The area between ``final

Load a configuration as a python module.

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

Get model evaluation results.

Sample fine grained feats from each level feature map and concatenate them together. Args: x (tuple[Tensor]): Feature map

Get list of structured dict for logging bounding boxes to W&B. Args: bboxes (list): List of bounding box coordinates in

Get list of structured dict for logging masks to W&B. Args: masks (list): List of masks. labels (int): List of label

Initialize the W&B Tables for model evaluation.

Interpolate the `source` (4D) to the shape of the `target`.

Private function to load bounding box annotations. Args: results (dict): Result dict from :obj:`mmdet.CustomDataset`. Re

Private function to load label annotations. Args: results (dict): Result dict from :obj:`mmdet.CustomDataset`. Returns:

Log model checkpoint as W&B Artifact. Args: model_path (str): Path of the checkpoint to log. aliases (list): List of

Log the W&B Tables for model evaluation. The table will be logged multiple times creating new version. Use this to compare models at

Mask refining process with point head in testing. Args: x (tuple[Tensor]): Feature maps of all scale level. rois (Ten

Randomly sample an img_scale according to ``ratio_range`` and ``multiscale_mode``. If ``ratio_range`` is specified, a ratio will be s

Display or save image with groung truths and predictions from a model. Args: dataset (Dataset): A PyTorch dataset.

Convert instance segmentation results to COCO json style.

Swap the parameter of model with parameter in ema_buffer.

Add ground truth as assigned results. Args: gt_labels (torch.Tensor): Labels of gt boxes

Import a module from albumentations. It inherits some of :func:`build_from_cfg` logic. Args: cfg (dict): Config dict. It

Get offset for deformable conv based on anchor shape NOTE: currently support deformable kernel_size=3 and dilation=1 Args:

Test function with test time augmentation. Args: imgs (list[torch.Tensor]): List of multiple images img_metas (list[d

Attach a text label above each bar in *rects*, displaying its height.

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

Split batch bbox prediction back to each image.

Rescale bounding box w.r.t. scale_factor. Args: bboxes (Tensor): Shape (n, 4) for bboxes or (n, 5) for rois scale_factor (float):

Check whether the training dataset is compatible with head. Args: runner (obj:`EpochBasedRunner`): Epoch based Runner.

Check whether the dataset in val epoch is compatible with head. Args: runner (obj:`EpochBasedRunner`): Epoch based Runner.

Build DistributedDataParallel module by device type. If device is cuda, return a MMDistributedDataParallel model; if device is mlu, return a

build DataParallel module by device type. if device is cuda, return a MMDataParallel model; if device is mlu, return a MLUDataParallel model.

Build a model from config and load the given checkpoint. Args: config_path (str): the OpenMMLab config for the model we want to

Compute reweight_factor for regression and classification loss.

Collect the information of the running environments.

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

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

Crop predicted masks by zeroing out everything not in the predicted bbox. Args: masks (Tensor): shape [H, W, N].

see :func:`BaseInstanceMasks.crop_and_resize`

Transform outputs for a single batch item into raw bbox predictions. Args: tl_heat (Tensor): Top-left corner heatmap for current

Draw labels on the axes. Args: ax (matplotlib.Axes): The input axes. labels (ndarray): The labels with the shape of (n, ).

Evaluation in COCO protocol. Args: results (list[list | tuple]): Testing results of the dataset. metric (str | list[s

Instance segmentation and object detection evaluation in COCO protocol. Args: results (list[list | tuple | dict]): Testin

Directly extract features from the backbone and neck.

Placeholder of forward function. Returns: dict[str, Tensor]: A dictionary, including features and predicted score

Forward features from the upstream network. Args: feats (tuple[Tensor]): Features from the upstream network, each is