str: the string of the module

Set attribute, i.e. self.name = value This reloading prevent the teacher model from being registered as a nn.Module. The teacher modu

Add the fc branch which consists of a sequential of conv layers.

Add default meta keys. We set default meta keys including `pad_shape`, `scale_factor` and `img_norm_cfg` to avoid the case where no `

Add the fc branch which consists of a sequential of fc layers.

Adjust the brightness of image.

Apply Color transformation to image.

Adjust the image contrast.

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

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

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

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

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

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

bbox post-processing method. The boxes would be rescaled to the original image scale and do the nms operation. Usually `with_nms` is

bbox post-processing method. Do the nms operation for bboxes in same level. Args: mlvl_scores (list[Tensor]): Box scores

Args: cls_pred (Tensor): The prediction with shape (num_query, 1, *) or (num_query, *). gt_labels (Te

Build transformer encoding layers.

Build patch embedding layer.

Initialize predictor layers of a single level head.

Check branches configuration.

Compute the value of gamma according to paper. gamma is the parameter of bernoulli distribution, which controls the number of features

Build :obj:`ConcatDataset by.

Get matrix of the corresponding relationship between the parent class and the child class. Args: hierarchy_map (dict): In

Convert trainId to id for cityscapes.

Convert segmentation label to onehot. Args: seg_label (Tensor): Segmentation label of shape (N, H, W). num_classes (i

CopyPaste transform function. Args: dst_results (dict): Result dict of the destination image. src_results (dict): Res

Function to randomly crop images, bounding boxes, masks, semantic segmentation maps. Args: results (dict): Result dict fr

Run forward function and calculate loss for decode head in inference.

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

delete plugins for block if exist. Args: plugin_names (list[str]): List of plugins name to delete.

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

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

Convert detection results to COCO json style.

Evaluation in Cityscapes protocol. Args: results (list): Testing results of the dataset. txtfile_prefix (str | None):

Evaluation in Cityscapes protocol. Args: results (list): Testing results of the dataset. logger (logging.Logger | str

Expand onehot labels to match the size of prediction.

Expand onehot labels to match the size of prediction.

Filter out bboxes too small after Mosaic.

Compute candidate boxes which include following 5 things: bbox1 before augment, bbox2 after augment, min_bbox_size (pixels), min_area

Filter images too small.

Filter bboxes and corresponding masks too small after shear augmentation.

Filter bboxes and corresponding masks too small after rotate augmentation.

Filter bboxes and masks too small or translated out of image.

Args: cls_pred (Tensor): Predicted classification logits, shape (num_query, num_class). gt_labels (Te

Forward function for classification and regression parts.

Forward function for feature maps before classifying each pixel with ``self.cls_seg`` fc. Args: inputs (list[Tensor]): Li

Forward function for feature maps before classifying each pixel with ``self.cls_seg`` fc. Args: inputs (list[Tensor]): Li

Forward function for feature maps before classifying each pixel with ``self.cls_seg`` fc. Args: inputs (list[Tensor]): Li

Forward function for shared part.

Get new sequence via geometric sequence interpolation. Args: src_size (int): Pos_embedding size in pre-trained model.

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

Transform outputs of a single image into bbox results. Args: center_heatmap_pred (Tensor): Center heatmap for current level with

Similar to func:``AnchorHead._get_bboxes_single``, but additionally processes coeff_preds_list and uses fast NMS instead of traditional

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

Transform outputs from the last decoder layer into bbox predictions for each image. Args: cls_score (Tensor): Box score l

Get different colors for each masks. Get different colors for each masks by adding a bias color to the base category color. Args:

Randomly generates the absolute crop size based on `crop_type` and `image_size`. Args: image_size (tuple): (h, w).

Get model evaluation results.

Get guided anchors and loc masks for a single level. Args: square (tensor): Squares of a single level. shape_pred (te

Convert gt bboxes to center offset and log width height.

Get points of a single scale level. This function will be deprecated soon.

Get repeat factor for each images in the dataset. Args: dataset (:obj:`CustomDataset`): The dataset repeat_thr (float

Get processed mask related results of single image. Args: kernel_preds (Tensor): Dynamic kernel prediction of all points

Get processed mask related results of single image. Args: cls_scores (Tensor): Classification score of all points

Get processed mask related results of single image. Args: cls_scores (Tensor): Classification score of all points