Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Will look for the words added to the trie within `text`. Output is the original string splitted along the boundaries of the words fou

Updates the Trie with new tokens provided as arguments. Args: *args: Variable number of words to be added to the Trie.

Add prefix for dict. Args: inputs (dict): The input dict with str keys. prefix (str): The prefix to add. Returns: d

Transform inputs for decoder. Args: inputs (list[Tensor]): List of multi-level img features. Returns: Tensor

nn.Module: normalization layer after the second convolution layer

Classify each pixel.

nn.Module: the normalization layer named "norm1"

Build loss.

Parse the raw outputs (losses) of the network. Args: losses (dict): Raw output of the network, which usually contain

Multiple with alpha and add beat with clip.

Passes over every char (utf-8 char) on word and recursively adds it to the internal `data` trie representation. The special key `""`

Build segmentor.

Builder for transformer encoder and transformer decoder.

Convert objects of various python types to :obj:`torch.Tensor`. Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`, :class:`S

Converts a token string (or a sequence of tokens) in a single integer id (or a sequence of ids), using the vocabulary. Args:

Get `nn.ModuleDict` to fit the `MMDistributedDataParallel` interface. Args: module (MMDistributedDataParallel | nn.ModuleDict): The input

Apply element-wise weight and reduce loss. Args: loss (Tensor): Element-wise loss. weight (Tensor): Element-wise weights.

Builder for Position Encoding.

Forward function for plugins.

Get the root logger. The logger will be initialized if it has not been initialized. By default a StreamHandler will be added. If `log_file` i

Apply function to a list of arguments. Note: This function applies the ``func`` to multiple inputs and map the multiple outputs o

Build datasets.

Build projection layer for key/query/value/out.

Generate grid Points of a single level. Note: This function is usually called by method ``self.grid_priors``. Args:

Calculate evaluation metrics Args: results (list[ndarray] | list[str]): List of prediction segmentation maps or list of predic

nn.Module: normalization layer after the third convolution layer

Save ndarray to local numpy file. Args: array (ndarray): Ndarray to save. temp_file_name (str): Numpy file name. If 'temp_file_na

Prepare results dict for pipeline.

Sample positive and negative bboxes. This is a simple implementation of bbox sampling given candidates, assigning results and ground

Converts a string into a sequence of tokens, using the tokenizer. Split in words for word-based vocabulary or sub-words for sub-word

Assign boxes to either a ground truth boxes or a negative boxes.

Build Assigner.

Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload

Build Match Cost.

Crop from ``img``

Encode images with backbone and decode into a semantic segmentation map of the same size as input.

Evaluate the dataset. Args: results (list[tuple[torch.Tensor]] | list[str]): per image pre_eval results or predi

Extract features from images.

Forward function for testing, only ``pam_cam`` is used.

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher

Converts all `BatchNorm2d` and `SyncBatchNorm` layers of provided module into `FrozenBatchNorm2d`. If `module` is itself an instance of eithe

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

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

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

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

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

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

lock modules Args: unlocked_groups (int): leave last n layer groups unlocked (default: 0)

make plugins for block. Args: in_channels (int): Input channels of plugin. plugins (list[dict]): List of plugins cfg

Obtain the mean of tensor on different GPUs.

Scatter function. Args: inputs (Tensor): Input Tensor. kwargs (dict): Args for ``mmcv.parallel.scatte