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

Classify each pixel with fc.

Convert the model into training mode while keep normalization layer freezed.

Build datasets.

Build segmentor.

Calculate accuracy according to the prediction and target. Args: pred (torch.Tensor): The model prediction, shape (N, num_class, ...)

Build loss.

Check if is ResNet building block.

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

Make divisible function. This function rounds the channel number to the nearest value that can be divisible by the divisor. It is taken from

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

Calculate evaluation metrics Args: results (list[ndarray]): List of prediction segmentation maps. gt_seg_maps (list[ndarray]): lis

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

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

Evaluate the dataset. Args: results (list): Testing results of the dataset. metric (str | list[str]): Metrics to be e

Get class palette (RGB) of a dataset.

Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to r

Print a log message. Args: msg (str): The message to be logged. logger (logging.Logger | str | None): The logger to be used. Some

Forward function for plugins.

Get class names of a dataset.

Build a module. Args: cfg (dict, list[dict]): The config of modules, is is either a dict or a list of configs. regist

Args: imgs (List[Tensor]): the outer list indicates test-time augmentations and inner Tensor should have a shape

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

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

Multiple with alpha and add beat with clip.

Call evaluate function of dataset.

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

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are "none", "mean" and "sum".

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

Test with single GPU. Args: model (nn.Module): Model to be tested. data_loader (utils.data.Dataloader): Pytorch data loader.

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

Make each stage.

Make transition layer.

Check if norm layer is in correct train state.

Crop from ``img``

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

Placeholder for Forward function for training.

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

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

Initialize the weights in backbone. Args: pretrained (str, optional): Path to pre-trained weights. Defaults to No

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

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

nn.Module: the normalization layer named "norm1"

nn.Module: the normalization layer named "norm2"

nn.Module: normalization layer after the third convolution layer

Randomly sample an img_scale when ``multiscale_mode=='range'``. Args: img_scales (list[tuple]): Images scale range for sampling.

Freeze stages param and norm stats.

Sample from fine grained features. Args: prev_output (list[Tensor]): Prediction of previous decode head. points (Tens

Find the predefined segmentor config directory.

Sample from fine grained features. Args: x (list[Tensor]): Feature pyramid from by neck or backbone. points (Tensor):

Check if the weight(and bias) is all zero.

Check if norm layer is in correct train state.

Collect the information of the running environments.

Contrast distortion.

Crop from ``img``

Extract features from images.

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

Flattens predictions in the batch.

Placeholder of forward function.

Forward function.

Placeholder of forward function.

Intersection over Union Args: pred_label (np.ndarray): 2D predict map label (np.ndarray): label 2D label map n

Randomly get a crop bounding box.

Get ground truth segmentation maps for evaluation.

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

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

Check if is one of the norms.

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)

Calculate Mean Dice (mDice) Args: results (list[ndarray]): List of prediction segmentation maps. gt_seg_maps (list[ndarray]): lis