Data loader. Combines a dataset and a sampler, and provides single- or multi-process iterators over the dataset. Arguments: data

Gather-and-Expansion Layer. Args: in_channels (int): Number of input channels. out_channels (int): Number of output channels.

Gather-and-Expansion Layer. Args: in_channels (int): Number of input channels. out_channels (int): Number of output channels.

Compose multiple transforms sequentially. Args: transforms (Sequence[dict | callable]): Sequence of transform object or confi

Compose multiple transforms sequentially. Args: transforms (Sequence[dict | callable]): Sequence of transform object or confi

InvertedResidual block for MobileNetV2. Args: in_channels (int): The input channels of the InvertedResidual block. out_channels (

InvertedResidual block for MobileNetV2. Args: in_channels (int): The input channels of the InvertedResidual block. out_channels (

A simple pipeline to load image.

A simple pipeline to load image.

Pooling Pyramid Module used in PSPNet. Args: pool_scales (tuple[int]): Pooling scales used in Pooling Pyramid Module.

Pooling Pyramid Module used in PSPNet. Args: pool_scales (tuple[int]): Pooling scales used in Pooling Pyramid Module.

Image to Patch Embedding. We use a conv layer to implement PatchEmbed. Args: in_channels (int): The num of input channels. Default:

Image to Patch Embedding. We use a conv layer to implement PatchEmbed. Args: in_channels (int): The num of input channels. Default:

r"""Applies Synchronized Batch Normalization over a 2d or 3d input that is seen as a mini-batch. .. math:: y = \frac{x - mean[x]}{ \

Attention Refinement Module (ARM) to refine the features of each stage. Args: in_channels (int): The number of input channels. ou

Attention Refinement Module (ARM) to refine the features of each stage. Args: in_channels (int): The number of input channels. ou

Data Parallel with a replication callback. An replication callback `__data_parallel_replicate__` of each module will be invoked after being

Non-bottleneck block of ERFNet. Args: channels (int): Number of channels in Non-bottleneck block. drop_rate (float): Probability

Non-bottleneck block of ERFNet. Args: channels (int): Number of channels in Non-bottleneck block. drop_rate (float): Probability

ResLayer to build ResNet style backbone. Args: block (nn.Module): block used to build ResLayer. inplanes (int): inplanes of block

ResLayer to build ResNet style backbone. Args: block (nn.Module): block used to build ResLayer. inplanes (int): inplanes of block

Applies padding to input (if needed) so that input can get fully covered by filter you specified. It support two modes "same" and "corner". The

Applies padding to input (if needed) so that input can get fully covered by filter you specified. It support two modes "same" and "corner". The

Cascade Feature Fusion Unit in ICNet. Args: low_channels (int): The number of input channels for low resolution feature map.

Cascade Feature Fusion Unit in ICNet. Args: low_channels (int): The number of input channels for low resolution feature map.

A wrapper of concatenated dataset. Same as :obj:`torch.utils.data.dataset.ConcatDataset`, but support evaluation and formatting results

A wrapper of concatenated dataset. Same as :obj:`torch.utils.data.dataset.ConcatDataset`, but support evaluation and formatting results

Context Guided Block for CGNet. This class consists of four components: local feature extractor, surrounding feature extractor, joint feature

Context Guided Block for CGNet. This class consists of four components: local feature extractor, surrounding feature extractor, joint feature

Sampler that restricts data loading to a subset of the dataset. It is especially useful in conjunction with :class:`torch.nn.parallel.Distrib

Downsampler block of ERFNet. This module is a little different from basical ConvModule. The features from Conv and MaxPool layers are con

Downsampler block of ERFNet. This module is a little different from basical ConvModule. The features from Conv and MaxPool layers are con

r"Wraps an exception plus traceback to communicate across threads

Downsampling module for CGNet.

Downsampling module for CGNet.

Load annotations for semantic segmentation. Args: reduce_zero_label (bool): Whether reduce all label value by 1. Usually used

Load annotations for semantic segmentation. Args: reduce_zero_label (bool): Whether reduce all label value by 1. Usually used

ResidualConvUnit, pre-activate residual unit. Args: in_channels (int): number of channels in the input feature map. act_cfg (dict

ResidualConvUnit, pre-activate residual unit. Args: in_channels (int): number of channels in the input feature map. act_cfg (dict

Self-Attention Module. Args: in_channels (int): Input channels of key/query feature. channels (int): Output channels of key/query

Make a ANN used SelfAttentionBlock. Args: low_in_channels (int): Input channels of lower level feature, which is the key feat

Self-Attention Module. Args: in_channels (int): Input channels of key/query feature. channels (int): Output channels of key/query

Make a ANN used SelfAttentionBlock. Args: low_in_channels (int): Input channels of lower level feature, which is the key feat

Implements one encoder layer in Vision Transformer. Args: embed_dims (int): The feature dimension. num_heads (int): Parallel atte

Implements one encoder layer in Vision Transformer. Args: embed_dims (int): The feature dimension. num_heads (int): Parallel atte

Upsampler block of ERFNet. Args: in_channels (int): Number of input channels. out_channels (int): Number of output channels.

Upsampler block of ERFNet. Args: in_channels (int): Number of input channels. out_channels (int): Number of output channels.

Adaptive Context Module used in APCNet. Args: pool_scale (int): Pooling scale used in Adaptive Context Module to extract regi

Adaptive Context Module used in APCNet. Args: pool_scale (int): Pooling scale used in Adaptive Context Module to extract regi

Asymmetric Fusion Non-local Block(AFNB) Args: low_in_channels (int): Input channels of lower level feature, which is the key

Asymmetric Fusion Non-local Block(AFNB) Args: low_in_channels (int): Input channels of lower level feature, which is the key

Asymmetric Pyramid Non-local Block (APNB) Args: in_channels (int): Input channels of key/query feature, which is the key feat

Asymmetric Pyramid Non-local Block (APNB) Args: in_channels (int): Input channels of key/query feature, which is the key feat

Atrous Spatial Pyramid Pooling (ASPP) Module. Args: dilations (tuple[int]): Dilation rate of each layer. in_channels (int): Input

Atrous Spatial Pyramid Pooling (ASPP) Module. Args: dilations (tuple[int]): Dilation rate of each layer. in_channels (int): Input

Bilateral Guided Aggregation Layer to fuse the complementary information from both Detail Branch and Semantic Branch. Args: out_chann

Bilateral Guided Aggregation Layer to fuse the complementary information from both Detail Branch and Semantic Branch. Args: out_chann

Lookahead optimization strategy for any optimizer. This implemention is based on: https://arxiv.org/abs/1907.08610 "Look

Basic convolutional block for UNet. This module consists of several plain convolutional layers. Args: in_channels (int): Number of i

Basic convolutional block for UNet. This module consists of several plain convolutional layers. Args: in_channels (int): Number of i

Wraps another sampler to yield a mini-batch of indices. Args: sampler (Sampler): Base sampler. batch_size (int): Size of mini-bat

Channel Attention Module (CAM)

Channel Attention Module (CAM)

Context Embedding Block for large receptive filed in Semantic Branch. Args: in_channels (int): Number of input channels. Defa

Context Embedding Block for large receptive filed in Semantic Branch. Args: in_channels (int): Number of input channels. Defa

Dataset to concatenate multiple datasets. Purpose: useful to assemble different existing datasets, possibly large-scale datasets as the c

The Conditional Position Encoding (CPE) module. The CPE is the implementation of 'Conditional Positional Encodings for Vision Transformers <h

The Conditional Position Encoding (CPE) module. The CPE is the implementation of 'Conditional Positional Encodings for Vision Transformers <h

Context Path to provide sufficient receptive field. Args: backbone_cfg:(dict): Config of backbone of Context Path. co

Context Path to provide sufficient receptive field. Args: backbone_cfg:(dict): Config of backbone of Context Path. co

Dynamic Convolutional Module used in DMNet. Args: filter_size (int): The filter size of generated convolution kernel used in

Dynamic Convolutional Module used in DMNet. Args: filter_size (int): The filter size of generated convolution kernel used in

Iterates once over the DataLoader's dataset, as specified by the sampler

Atrous Spatial Pyramid Pooling (ASPP) Module with depthwise separable conv.

Atrous Spatial Pyramid Pooling (ASPP) Module with depthwise separable conv.

Detail Branch with wide channels and shallow layers to capture low-level details and generate high-resolution feature representation. Args:

Detail Branch with wide channels and shallow layers to capture low-level details and generate high-resolution feature representation. Args:

Disentangled Non-Local Blocks. Args: temperature (float): Temperature to adjust attention. Default: 0.05

Disentangled Non-Local Blocks. Args: temperature (float): Temperature to adjust attention. Default: 0.05

Expectation Maximization Attention Module used in EMANet. Args: channels (int): Channels of the whole module. num_bases (int): Nu

Expectation Maximization Attention Module used in EMANet. Args: channels (int): Channels of the whole module. num_bases (int): Nu

An implementation of Efficient Multi-head Attention of Segformer. This module is modified from MultiheadAttention which is a module from mmcv

An implementation of Efficient Multi-head Attention of Segformer. This module is modified from MultiheadAttention which is a module from mmcv

Encoding Module used in EncNet. Args: in_channels (int): Input channels. num_codes (int): Number of code words. conv_cfg

Encoding Module used in EncNet. Args: in_channels (int): Input channels. num_codes (int): Number of code words. conv_cfg

Encoding Layer: a learnable residual encoder. Input is of shape (batch_size, channels, height, width). Output is of shape (batch_size, num_c

Encoding Layer: a learnable residual encoder. Input is of shape (batch_size, channels, height, width). Output is of shape (batch_size, num_c