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

Flip bboxes horizontally. Args: bboxes (numpy.ndarray): Bounding boxes, shape (..., 4*k) img_shape (tuple[int]): Imag

Export bbox branch to onnx which supports batch inference. Args: x (tuple[Tensor]): Feature maps of all scale level.

Export bbox branch to onnx which supports batch inference. Args: x (tuple[Tensor]): Feature maps of all scale level.

Encode ground truth boxes to tblr coordinate. It first convert the gt coordinate to tblr format, (top, bottom, left, right), relative to pri

Compute the area of an array of bboxes. Args: bboxes (Tensor): The coordinates ox bboxes. Shape: (m, 4) Returns: Tensor: Are

Evaluate the model only at the start of training by epoch.

Calculate the binary CrossEntropy loss. Args: pred (torch.Tensor): The prediction with shape (N, 1) or (N, ). When the shape

Args: mask_preds (Tensor): Mask prediction in shape (num_query, *). gt_masks (Tensor): Ground truth in shape (num_gt,

Convert masks from the form of bitmaps to polygons. Args: bitmap (ndarray): masks in bitmap representation. Return: list[nda

BIoULoss. This is an implementation of paper `Improving Object Localization with Fitness NMS and Bounded IoU Loss. <https://arxiv.org/abs

Apply bucketing estimation (cls preds) and fine regression (offset preds) to generate det bboxes. Args: proposals (Tensor): Boxes to

Args: dn_args (dict): Returns:

Build RoI operator to extract feature from each level feature map. Args: layer_cfg (dict): Dictionary to construct and config RoI

Build shared head.

Compute point specific representation regions. See Grid R-CNN Plus (https://arxiv.org/abs/1906.05688) for details.

Calculate the confusion matrix. Args: dataset (Dataset): Test or val dataset. results (list[ndarray]): A list of detection result

Calculate positive recall with score threshold. Args: cls_scores (list[Tensor]): Classification scores at all fpn levels.

Compute centerness targets. Args: pos_bbox_targets (Tensor): BBox targets of positive bboxes in shape (num_pos, 4

Get bboxes according to center points. Only used in :class:`MaxIoUAssigner`.

r"""`Implementation of paper `Enhancing Geometric Factors into Model Learning and Inference for Object Detection and Instance Segmentation <ht

Convert keys in checkpoints. There can be some breaking changes during the development of mmdetection, and this tool is used for upgrading ch

Convert keys in detectron pretrained ResNet models to pytorch style.

Convert keys in pycls pretrained RegNet models to mmdet style.

Create gif frame image through matplotlib. Args: image_dir (str): Root directory of result images nrows (int): Number of rows dis

Create gif through imageio. Args: frames (list[ndarray]): Image frames gif_name (str): Saved gif name duration (int): Dis

Calculate the CrossEntropy loss. Args: pred (torch.Tensor): The prediction with shape (N, C), C is the number of classes.

Decode distance prediction to bounding box. Args: points (Tensor): Shape (B, N, 2) or (N, 2). pred_bboxes (Tensor): D

Apply transformation `pred_bboxes` to `boxes`. Args: boxes (torch.Tensor): Basic boxes, e.g. anchors. pred_bboxes (to

Transform outputs into detections raw bbox prediction. Args: center_heatmap_pred (Tensor): center predict heatmap,

Sampling the feature x according to offset. Args: feat (Tensor): Feature offset (Tensor): Spatial offset for feature

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

Convert ground truth bboxes from relative position to absolute position. Only used in evaluating time.

Calculate dice loss, there are two forms of dice loss is supported: - the one proposed in `V-Net: Fully Convolutional Neural Netw

r"""`Implementation of Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression, https://arxiv.org/abs/1911.08287`_. Code is

r"""Distribution Focal Loss (DFL) is from `Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection

Draw bounding boxes on the axes. Args: ax (matplotlib.Axes): The input axes. bboxes (ndarray): The input bounding boxes with the

Draw masks on the image and their edges on the axes. Args: ax (matplotlib.Axes): The input axes. img (ndarray): The image with th

Args: size (tuple): expected shape of dummy masks, (N, H, W) Return: list[list[ndarray]]: dummy mask

Encode bounding box to distances. Args: points (Tensor): Shape (N, 2), The format is [x, y]. gt_bboxes (Tensor): Shap

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

Evaluate and show results. Args: dataset (Dataset): A PyTorch dataset. results (list): Object detection or panoptic s

Evaluate PQ according to the panoptic results json file.

TODO: Add expand for polygon

Extract features from images.

Directly extract teacher features from the backbone+neck.

Fast NMS in `YOLACT <https://arxiv.org/abs/1904.02689>`_. Fast NMS allows already-removed detections to suppress other detections so that eve

Format the results to txt (standard format for Cityscapes evaluation). Args: results (list): Testing results of the datas

Format the model predictions according to the interface with dataset. Args: results (:obj:`InstanceData`): Processed

Forward feature from the upstream network to get prototypes and linearly combine the prototypes, using masks coefficients, into instan

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

Forward function. Args: feats (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor.

Args: x (Tensor): Has shape (B, C, H, W). In most case, C is 3. Returns: tuple: Contains merged results and

Calls either :func:`forward_train` or :func:`forward_test` depending on whether ``return_loss`` is ``True``. Note this setting will c

Forward function. Args: mlvl_feats (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor with

Forward function. Args: mlvl_feats (tuple[Tensor]): Features from the upstream network, each is a 4D-tensor with

Args: imgs (List[Tensor]): the outer list indicates test-time augmentations and inner Tensor should have a shape

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

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

Forward function for training mode. Args: x (list[Tensor]): Features from backbone. img_metas (list[dict]): Meta info

Compute location targets for guided anchoring. Each feature map is divided into positive, negative and ignore regions. - positive reg

Compute guided anchoring targets. Args: approx_list (list[list]): Multi level approxs of each image. inside_flag_list

Generate 2D gaussian kernel. Args: radius (int): Radius of gaussian kernel. sigma (int): Sigma of gaussian function. Default: 1.

`Focal Loss <https://arxiv.org/abs/1708.02002>`_ for targets in gaussian distribution. Args: pred (torch.Tensor): The prediction.

Generate base anchors. Returns: list(torch.Tensor): Base anchors of a feature grid in multiple \ feature levels.

Generate base anchors. Returns: list(torch.Tensor): Base anchors of a feature grid in multiple \ feature levels.