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.

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

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,

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

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

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

:meth: evaluate by average precision

evaluate by Caltech-style log-average miss rate ref: str - "CALTECH_-2"/"CALTECH_-4"

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): Det results from test results

TODO: Add expand for polygon

Extract features from images.

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

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

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.

Dummy forward function.

Forward function for exporting to ONNX. Over-write `forward` because: `masks` is directly created with zero (valid position tag) and

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

Args: img (list[Tensor]): List of tensors of shape (1, C, H, W). Typically these should be mean centered and std

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.

Generate proposals from encoded memory. Args: memory (Tensor) : The output of encoder, has shape (bs, num_key, em

Generate base anchors of a single level. Args: base_sizes_per_level (list[tuple[int, int]]): Basic sizes of ancho

Generate buckets w.r.t bucket number and scale factor of proposals. Args: proposals (Tensor): Shape (n, 4) num_buckets (int): Num

Generates per block width from RegNet parameters. Args: initial_width ([int]): Initial width of the backbone width_sl

return x GiB.

A wrapper for computing ATSS targets for points in multiple images. Args: cls_scores (list[Tensor]): Box iou-aware scores for eac

Transform network output for a batch into bbox predictions.

Transform network outputs for a batch into bbox predictions. Args: all_cls_scores_list (list[Tensor]): Classification outputs

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

Get class names of current dataset. Args: classes (Sequence[str] | str | None): If classes is None, use default C

Get det results and gt information of a certain class. Args: det_results (list[list]): Same as `eval_map()`. annotations (list[di

Compute FCOS regression and classification targets for points in multiple images. Args: points (list[Tensor]): Points of

Get gt priorities according to their areas. Smaller gt has higher priority. Args: gt_bboxes (Tensor): Ground truth boxes

Get the mask scores. mask_score = bbox_score * mask_iou

Run the model in onnxruntime env. Args: feat (list[Tensor]): A list of tensors from torch.rand, each is a 4D-tensor. Ret

Get the position embedding of proposal.

Get the reference points used in decoder. Args: spatial_shapes (Tensor): The shape of all feature maps, has shape

Get ``num_points`` most uncertain points with random points during train. Sample points in [0, 1] x [0, 1] coordinate space based on

Resize, binarize, and format the instance mask predictions. Args: mask_pred (Tensor): shape (N, H, W). label_pred (Te

Gets widths/stage_blocks of network at each stage. Args: widths (list[int]): Width in each stage. Returns: t

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

Compute regression targets and each point inside or outside gt_bbox in multiple images. Args: points (list[Tensor]): Poin

Compute regression and classification targets in multiple images. Args: gt_bboxes (list[Tensor]): Ground truth bboxes for each im

Compute target maps for anchors in multiple images. Args: anchor_list (list[list[Tensor]]): Multi level anchors of each

Compute regression and classification targets for anchors in multiple images. Args: anchor_list (list[list[Tensor]]): Mul

Compute instance segmentation targets for each image. Args: mask_pred (Tensor): Predicted prototypes with shape (

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

Compute regression and classification targets for anchors in multiple images. Args: cls_scores_list (list[Tensor])： Class

Get targets for ATSS head. This method is almost the same as `AnchorHead.get_targets()`. Besides returning the targets as the parent

Get targets for GFL head. This method is almost the same as `AnchorHead.get_targets()`. Besides returning the targets as the parent m

Get targets for ATSS head. This method is almost the same as `AnchorHead.get_targets()`. Besides returning the targets as the parent

Compute regression, classification and centerness targets for points in multiple images. Args: points (list[Tensor]): Poi

Generate corner targets. Including corner heatmap, corner offset. Optional: corner embedding, corner guiding shift, centripetal shif

Compute regression and classification targets for a batch image. Outputs from a single decoder layer of a single feature level are used.

Get targets for GFL head. This method is almost the same as `AnchorHead.get_targets()`. Besides returning the targets as the parent m

Get targets for ATSS head. This method is almost the same as `AnchorHead.get_targets()`. Besides returning the targets as the parent

Compute target of mask IoU. Mask IoU target is the IoU of the predicted mask (inside a bbox) and the gt mask of corresponding gt mask

Get the valid radios of feature maps of all level.