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

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

Classify each pixel with fc.

Classify each pixel with fc.

Builds the residual blocks used in the generator. Args: x: The 4D input tensor. labels: The labels of the class we seek to sample fro

Builds graph for a spectrally normalized 1 by 1 convolution. This is used in the context of non-local networks to reduce channel count for st

Convert a version string into a tuple of integers. This method is usually used for comparing two versions. For pre-release versions: alpha <

Build datasets.

Multiple with alpha and add beat with clip.

Convert a version string into a tuple of integers. This method is usually used for comparing two versions. For pre-release versions: alpha <

Build segmentor.

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

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

Build datasets.

Build segmentor.

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

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

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

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

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

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

Forward function for plugins.

Forward function for plugins.

Check the forward and backward for the customized batch normalization.

add new dementions at the front and the tail

Builds the residual blocks used in the discriminator. Args: x: The 4D input vector. out_channels: Number of features in the output la

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

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

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

Multiple with alpha and add beat with clip.

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

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

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

nn.Module: the normalization layer named "norm1"

nn.Module: the normalization layer named "norm2"

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

Tensorflow assign function for list of tensors.

Downsamples the input volume by means of average pooling. Args: x: The 4D input tensor. Returns: An downsampled version of the in

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

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

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

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

Creates a TPU Estimator.

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 conversion.

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 conversion.

nn.Module: the normalization layer named "norm1"

nn.Module: the normalization layer named "norm2"

Prepare results dict for pipeline.

Prepare results dict for pipeline.

Setup multi-processing environment variables.

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

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

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