Get class palette (RGB) of a dataset.

Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the

Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the

Generate grid points of multiple feature levels. Args: featmap_sizes (list[tuple]): List of feature map sizes in

Inference with slide/whole style. Args: img (Tensor): The input image of shape (N, 3, H, W). img_meta (dict): Image i

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

Returns a dictionary of info about the object.

Returns a dictionary of info about the object.

Initialize a segmentor from config file. Args: config (str or :obj:`mmcv.Config`): Config file path or the config object.

Initialize the transformer weights.

Initialize weights.

Initialize weights.

Initialize weights.

Initialize weights.

returns list of pretrained models Returns a tuple (model_name, pretrain_tag) by default or 'name:tag' if as_str == True

Loss Name. This function must be implemented and will return the name of this loss function. This name will be used to combine differ

Loss function for outputs from a single decoder layer. Args: cls_scores (Tensor): Mask score logits from a single decoder layer

Loss function for outputs from a single decoder layer. Args: cls_scores (Tensor): Mask score logits from a single decoder layer

Loss function for outputs from a single decoder layer. Args: cls_scores (Tensor): Mask score logits from a single decoder layer

Compute ``pam_cam``, ``pam``, ``cam`` loss.

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

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

Obtain tight bounding boxes of binary masks. Args: masks (Tensor): Binary mask of shape (n, h, w). Returns: Tensor: Bboxe wi

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

torch.Tensor: concatenated positive and negative boxes

Calculate Mean Dice (mDice) Args: results (list[ndarray] | list[str]): List of prediction segmentation maps or list of predic

Calculate Mean Intersection and Union (mIoU) Args: results (list[ndarray] | list[str]): List of prediction segmentation maps

Calculate Mean Intersection and Union (mIoU) Args: results (list[ndarray] | list[str]): List of prediction segmentation maps

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 convertion.

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

list[int]: The number of priors (points) at a point on the feature grid

int: number of feature levels that the generator will be applied

Returns the number of added tokens when encoding a sequence with special tokens. <Tip> This encodes a dummy input and check

Collect eval result from each iteration. Args: preds (list[torch.Tensor] | torch.Tensor): the segmentation logit

Preprocess an image or batch of images. Args: images (`ImageInput`): Image to preprocess. Expects a sing

PyTorch version of `Focal Loss <https://arxiv.org/abs/1708.02002>`_. Args: pred (torch.Tensor): The prediction with shape (N, C), C is th

Args: rng (None | int | numpy.random.RandomState): seed or state. kwargs (keyword arguments): - num_p

Decorator registering pooler class

Sample pixels that have high loss or with low prediction confidence. Args: seg_logit (torch.Tensor): segmentation logits, shape (

Placeholder for sample function.

Directly returns the positive and negative indices of samples. Args: assign_result (:obj:`AssignResult`): Assigned results