Make each stage.

Make each stage.

Make transition layer.

Make transition layer.

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

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

Build backbone.

Build backbone.

Build loss.

Build loss.

Maps value x from range [a, b] to range [c, d]

Maps value x from range [a, b] to range [c, d]

Collect the information of the running environments.

Crop from ``img``

Crop from ``img``

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

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

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

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

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

Get class weight for loss function. Args: class_weight (list[float] | str | None): If class_weight is a str, take it as a fil

Get class weight for loss function. Args: class_weight (list[float] | str | None): If class_weight is a str, take it as a fil

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

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

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

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

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

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

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 conversion.

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 conversion.

Test with single GPU by progressive mode. Args: model (nn.Module): Model to be tested. data_loader (utils.data.Dataloader): Pytor

Freeze stages param and norm stats.

Freeze stages param and norm stats.

Freeze stages param and norm stats.

Freeze stages param and norm stats.

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

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

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

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

Calculate global coordinate of mosaic image and local coordinate of cropped sub-image. Args: loc (str): Index for the sub

Calculate global coordinate of mosaic image and local coordinate of cropped sub-image. Args: loc (str): Index for the sub

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

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

sum over the first and last dimention

Collect the information of the running environments.

Contrast distortion.

Contrast distortion.

Execute an replication callback `__data_parallel_replicate__` on each module created by original replication. The callback will be invoked w