Run forward function and calculate loss for auxiliary head in training.

Run forward function and calculate loss for auxiliary head in training.

Check branches configuration.

Check branches configuration.

Compute the mean and standard-deviation with sum and square-sum. This method also maintains the moving average on the master device.

Build :obj:`ConcatDataset by.

Build :obj:`ConcatDataset by.

Convert trainId to id for cityscapes.

Convert trainId to id for cityscapes.

Convert segmentation label to onehot. Args: seg_label (Tensor): Segmentation label of shape (N, H, W). num_classes (i

Convert segmentation label to onehot. Args: seg_label (Tensor): Segmentation label of shape (N, H, W). num_classes (i

Run forward function and calculate loss for decode head in inference.

Run forward function and calculate loss for decode head in inference.

Run forward function and calculate loss for decode head in training.

Run forward function and calculate loss for decode head in training.

Create a superset of inputs needed to run test or train batches. Args: input_shape (tuple): input batch dimensions nu

Create a superset of inputs needed to run test or train batches. Args: input_shape (tuple): input batch dimensions nu

Create a superset of inputs needed to run test or train batches. Args: input_shape (tuple): input batch dimensions nu

Create a superset of inputs needed to run test or train batches. Args: input_shape (tuple): input batch dimensions nu

Evaluation in Cityscapes protocol. Args: results (list): Testing results of the dataset. logger (logging.Logger | str

Evaluation in Cityscapes protocol. Args: results (list): Testing results of the dataset. logger (logging.Logger | str

Expand onehot labels to match the size of prediction.

Expand onehot labels to match the size of prediction.

Creates a dictionary of image summaries.

Return a TF-GAN compatible discriminator.

Returns a TF-GAN compatible generator function.

Gets a background stream for copying between CPU and GPU

Initialize ``auxiliary_head``

Initialize ``auxiliary_head``

Initialize ``decode_head``

Initialize ``decode_head``

Check and initialize input transforms. The in_channels, in_index and input_transform must match. Specifically, when input_transform i

Check and initialize input transforms. The in_channels, in_index and input_transform must match. Specifically, when input_transform i

Inject the required update ops with all trainable variables. [Args] model_vars: list of trainable tf.Variables. [list]

Build multiple branch.

Build multiple branch.

Build fuse layer.

Build fuse layer.

Make each layer.

Make each layer.

Build one branch.

Build one branch.

Make stem layer for ResNet.

Make stem layer for ResNet.

Mosaic transform function. Args: results (dict): Result dict. Returns: dict: Updated result dict.

Mosaic transform function. Args: results (dict): Result dict. Returns: dict: Updated result dict.