Get label assignment (from teacher). Args: cls_scores (list[Tensor]): Box scores for each scale level. Has shape

Only keep loading image and annotations related configuration. Args: pipeline (list[dict]): Data pipeline configs. Returns:

Extract local maximum pixel with given kernel. Args: heat (Tensor): Target heatmap. kernel (int): Kernel size of max pooling. Def

Get palette from various inputs. Args: palette (list[tuple] | str | tuple | :obj:`Color`): palette inputs. num_classes (int): the

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 hierarchy for classes. Args: hierarchy_file (sty): File path to the hierarchy for classes. Returns: ndar

Get multi-image mask results. Args: mlvl_mask_preds (list[Tensor]): Multi-level mask prediction. Each element in

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

Get top k positions from heatmap. Args: scores (Tensor): Target heatmap with shape [batch, num_classes, height, width].

Inverse function of sigmoid. Args: x (Tensor): The tensor to do the inverse. eps (float): EPS avoid numerical

Importance-based Sample Reweighting (ISR_P), positive part. Args: cls_score (Tensor): Predicted classification scores. bbox_pred

Map from level to values based on max_value.

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

Flatten [N, C, H, W] shape tensor to [N, L, C] shape tensor. Args: x (Tensor): The input tensor of shape [N, C, H, W] before conversion.

nn.Module: normalization layer after the first convolution layer

Convert masks from the form of polygons to bitmaps. Args: polygons (list[ndarray]): masks in polygon representation height (int):

Randomly negate value based on random_negative_prob.

See :func:`BaseInstanceMasks.rescale`.

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 without augmentation.

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 head forward function used in both training and testing.

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:

Asynchronized test for box head without augmentation.

Asynchronized test for mask head without augmentation.

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

Test for mask head with test time augmentation.

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):