Calculate the centroid coordinates of the mask. Args: mask (Tensor): The mask to be calculated, shape (h, w). esp (float): Avoid

Collect the information of the running environments.

Collect the information of the running environments.

Contrast distortion.

See :func:`BaseInstanceMasks.crop`.

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

Evaluation for object detection. Args: dataset (Dataset): A PyTorch dataset. results (list): Object detection results

Decode distance prediction to bounding box. Args: points (Tensor): Shape (B, N, 2) or (N, 2). distance (Tensor): Distance from th

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

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

Directly extract features from the backbone and neck.

Extract features from images.

Flattens predictions in the batch (binary case) Remove labels equal to 'ignore_index'.

Flattens predictions in the batch.

flip tensor base on flip_direction. Args: src_tensor (Tensor): input feature map, shape (B, C, H, W). flip_direction (str): The f

Format the results into dir (standard format for ade20k evaluation). Args: results (list): Testing results of the dataset.

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

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

Forward function.

Placeholder of forward function.

Forward for head part which is called after every decoder layer. Args: decoder_out (Tensor): in shape (num_queries, batch_size, c

r"""Generate 2D gaussian radius. This function is modified from the `official github repo <https://github.com/princeton-vl/CornerNet-Lite/blo

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

Base on the previous bboxes and regression values, we compute the regressed bboxes and generate the grids on the bboxes. :param reg:

Generate base anchors of a single level. Args: base_size (int | float): Basic size of an anchor. scales (torch.Tensor

Get squares according to feature map sizes and guided anchors. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes.

Get squares according to feature map sizes and guided anchors. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes.

Get annotation of concatenated dataset by index. Args: idx (int): Index of data. Returns: dict: Annotation i

Get OpenImages annotation by index. Args: idx (int): Index of data. Returns: dict: Annotation info of specif

get_bboxes() is implemented in StageCascadeRPNHead.

Get class names of a dataset.

Get classes name from file. Args: label_file (str): File path of the label description file that maps the classes

Get custom classification channels. Args: num_classes (int): The number of classes. Returns: int: The custom

Get `gt_group_of` of a certain class, which is used in Open Images. Args: annotations (list[dict]): Same as `eval_map()`. class_i

Randomly get a crop bounding box.

Return dataset and sample index when given an indice of ConcatDataset. Args: indice (int): indice of sample in ConcatData

Get ground truth segmentation maps for evaluation.

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

Get image metas from pipeline.

Get points according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map sizes. img_meta

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

Get ``num_points`` most uncertain points during test. Args: mask_pred (Tensor): A tensor of shape (num_rois, num_classes,

Get sampled approxs and inside flags according to feature map sizes. Args: featmap_sizes (list[tuple]): Multi-level feature map s

Compute corresponding GT box and classification targets for proposals. Args: proposals_list (list[list]): Multi level poi

Compute semantic segmentation targets for each image. Args: segm_pred (Tensor): Predicted semantic segmentation map

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

Estimate uncertainty based on pred logits. We estimate uncertainty as L1 distance between 0.0 and the logits prediction in 'mask_pred' for th

Get a tensor of bboxes centered at (0, 0). Returns: Tensor: Tensor of bboxes with shape (num_bboxes, 4) in [xmin, ymi

img: B C H W

Inference image(s) with the detector. Args: model (nn.Module): The loaded detector. imgs (str/ndarray or list[str/ndarray] or tup

Inference image(s) with the segmentor. Args: model (nn.Module): The loaded segmentor. imgs (str/ndarray or list[str/ndarray]): Ei

Initialize a detector from config file. Args: config (str, :obj:`Path`, or :obj:`mmcv.Config`): Config file path, :obj:`Path`

Forks the current default random generator given device.

Calculate intersection and Union. Args: pred_label (ndarray | str): Prediction segmentation map or predict result filename.

Are points located in bboxes. Args: points (Tensor): Points, shape: (m, 2). bboxes (Tensor): Bounding boxes, shape: (n, 4). Retu

Maximization part of EM algorithm(Expectation-Maximization)

Concat multi-level feature maps by image. [feature_level0, feature_level1...] -> [feature_image0, feature_image1...] Convert the shape of eac

Load annotation from annotation file.

Load image level annotations from csv style ann_file. Args: image_level_ann_file (str): CSV style image level annotation

Load proposal from proposal file.

Computes gradient of the Lovasz extension w.r.t sorted errors. See Alg. 1 in paper.

Binary Lovasz hinge loss. Args: logits (torch.Tensor): [P], logits at each prediction (between -infty and +infty). la

Multi-class Lovasz-Softmax loss. Args: probs (torch.Tensor): [P, C], class probabilities at each prediction (between 0 and 1)

This patch applies AgentSD to the forward function of the block.

Pack all blocks in a stage into a ``ResLayer``.

Dictionary mapper. Renames keys according to keymap provided. Args: d (dict): old dict keymap (dict): {'old_key':'new

Convert Mask to ndarray.. Args: mask (:obj:`BitmapMasks` or :obj:`PolygonMasks` or torch.Tensor or np.ndarray): The mask to be co

Compute mask target for positive proposals in multiple images. Args: pos_proposals_list (list[Tensor]): Positive proposals in multiple

Returns: list: Contains all keys in meta_info_fields.

Test model with multiple gpus by progressive mode. This method tests model with multiple gpus and collects the results under two different mo

nn.Module: normalization layer after the first convolution layer

nn.Module: normalization layer after the second convolution layer

nn.Module: normalization layer after the third convolution layer