Cubic function. Args: x (ndarray): The distance from the center position. Returns: ndarray: The weight corresponding to a pa

wgan loss. Args: input (Tensor): Input tensor. target (bool): Target label. Returns: Tensor: wga

The behavior after each train iteration. Args: runner (``mmcv.runner.BaseRunner``): The runner.

The behavior after each train iteration. Args: runner (``mmcv.runner.BaseRunner``): The runner.

The behavior after each train iteration. Args: runner (object): The runner.

Build conv1 of the block. Args: in_channels (int): The input channels of the ConvModule. out_channels (int): The outp

Build conv2 of the block. Args: in_channels (int): The input channels of the ConvModule. out_channels (int): The outp

Check whether the input is a mirror-extended sequence. If mirror-extended, the i-th (i=0, ..., t-1) frame is equal to the (t-1-i)-

Check whether the input is a mirror-extended sequence. If mirror-extended, the i-th (i=0, ..., t-1) frame is equal to the (t-1-i)-

Connectivity error for evaluating alpha matte prediction. Args: alpha (ndarray): Ground-truth alpha matte with shape (height, width).

Marks functions as deprecated. Throw a warning when a deprecated function is called, and add a note in the docstring. Modified from https://g

Evaluate with different metrics. Args: results (list[tuple]): The output of forward_test() of the model. Return:

Evaluating with saving generated images. (needs no metrics) Args: results (list[tuple]): The output of forward_test() of the mode

Evaluate with different metrics. Args: results (list[tuple]): The output of forward_test() of the model. Return:

Evaluating with different metrics. Args: results (list[tuple]): The output of forward_test() of the model. Return:

Evaluate with different metrics. Args: results (list[tuple]): The output of forward_test() of the model. Return:

Evaluate with different metrics. Args: results (list[tuple]): The output of forward_test() of the model. Return:

Postprocess the predicted. This class is adopted from https://github.com/MarcoForte/FBA_Matting. Args: alpha (Tensor): Tensor wi

Forward function. Args: inputs (tuple): Input data. kwargs (dict): Args for ``mmcv.parallel.scatter_g

Forward function to calculate accuracy. Args: pred (torch.Tensor): Prediction of models. target (torch.Tensor): Target

Get Inception feature maps. Args: inp (torch.Tensor): Input tensor of shape Bx3xHxW. Values are expected to be in

Get InceptionA feature maps. Args: x (torch.Tensor): Input tensor of shape BxCxHxW. Returns: torch.Tensor: Fe

Get InceptionC feature maps. Args: x (torch.Tensor): Input tensor of shape BxCxHxW. Returns: torch.Tensor: Fe

Get first InceptionE feature maps. Args: x (torch.Tensor): Input tensor of shape BxCxHxW. Returns: torch.Tens

Get second InceptionE feature maps. Args: x (torch.Tensor): Input tensor of shape BxCxHxW. Returns: torch.Ten

Forward function for base model. Args: imgs (Tensor): Input image(s). labels (Tensor): Ground-truth label(s).

Forward function. Args: x (Tensor): Input tensor. Returns: Tensor: Forward results.

Forward function. Args: x (Tensor): Input tensor. Returns: Tensor: Forward results.

Forward function. Args: x (tuple[torch.Tensor]): Contains global image and the local image patch. Return

Forward function. Args: x (Tensor): Input tensor with shape (n, c, h, w). Returns: Tensor: Forward results.

Forward function. Args: img (Tensor): Input tensor with shape (n, c, h, w). Returns: Tensor: Forward results

Forward Function. Args: x (torch.Tensor): Input tensor with shape of (n, c, h, w). Returns: torch.Tensor: Ou

Forward function. Args: x (tuple[torch.Tensor]): Contains global image and the local image patch. Return

Forward function. Args: x (Tensor): Input tensor with shape (n, c, h, w). Returns: Tensor: Forward results.

Forward function. Args: x (Tensor): Input tensor with shape (n, c, h, w). Returns: Tensor: Forward results.

Forward function. Args: x (Tensor): Input tensor with shape (n, c, h, w). Returns: Tensor: Forward results.

Forward Function. Args: x (torch.Tensor): Input tensor with shape of (n, c, h, w). mask (torch.Tensor): Input tensor

Forward function. Args: x (Tensor): The input feature map of refiner. raw_alpha (Tensor): The raw predicted alpha mat

Forward function. Args: x (Tensor): The input of MLP. Returns: Tensor: The output of MLP.