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

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

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

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

Forward function. Args: imgs (Tensor): Input tensor with shape (n, 2, c, h, w). padding_flag (bool): Padding or not.

Texture transformer. Q = LTE(lq_up) K = LTE(ref_downup) V = LTE(ref), from V_level_n to V_level_1 Relevance embeddin

Defines the computation performed at every call. Args: merged (Tensor): Image to predict alpha matte. trimap (Tensor)

Forward function. Args: masked_img (torch.Tensor): Image with hole as input. mask (torch.Tensor): Mask as input.

Forward function. Args: inputs (Tensor): Tensor of input frames. target (Tensor): Tensor of target frame. Default: No

Forward function. Args: lq (Tensor): Input lq images. gt (Tensor): Ground-truth image. Default: None. tes

Forward function. Args: lq (Tensor): Input lq images. gt (Tensor): Ground-truth image. Default: None. tes

Forward function. Args: lq (Tensor): Input lq images. gt (Tensor): Ground-truth image. Default: None. tes

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). last_hidden (Tensor | None): The feedback o

Forward function. Args: x (Tensor): Input tensor with shape (n, 3, h, w). Returns: Tuple[Tensor]: Forward re

Forward function for partial conv2d. Args: input (torch.Tensor): Tensor with shape of (n, c, h, w). mask (torch.Tenso

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

Forward function of GCAModule. Args: img_feat (Tensor): Image feature map of shape (N, ori_c, ori_h, ori_w).

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

Forward Function. Args: x (torch.Tensor): Input tensor with shape of :math:`(n, *, c)`. Same as ``torch.nn.Linear

Forward function for ASPP module. Args: x (Tensor): Input tensor with shape (N, C, H, W). Returns: Tensor: O

Forward Function. Args: x (torch.Tensor): Tensor with shape (n, c, h, w). context (torch.Tensor): Tensor with shape (

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

Forward function. Add skip connections without final ReLU. Args: x (Tensor): Input tensor with shape (n, c, h, w). Retur

Apply spatial and temporal ensemble. Args: imgs (torch.Tensor): The images to be processed by the model. Its size

Forward function for partial conv2d. Args: input (torch.Tensor): Tensor with shape of (n, c, h, w). mask (torch.Tenso

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

Forward function. Args: x (Tensor): Input tensor with shape (N, C, H, W). Returns: Tensor: Output tensor.

Args: pred_alpha (Tensor): of shape (N, 1, H, W). Predicted alpha matte. fg (Tensor): of shape (N, 3, H, W). Tensor o

Args: pred_alpha (Tensor): of shape (N, 1, H, W). Predicted alpha matte. fg (Tensor): of shape (N, 3, H, W). Tensor o

Args: pred_alpha (Tensor): of shape (N, 1, H, W). Predicted alpha matte. fg (Tensor): of shape (N, 3, H, W). Tensor o

Args: input (Tensor): The input for the loss module, i.e., the network prediction. target_is_real (bo

Forward function. Args: discriminator (nn.Module): Network for the discriminator. real_data (Tensor): Real input data

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

Forward Function. Args: pred (Tensor): of shape (N, C, H, W). Predicted tensor. target (Tensor): of shape (N, C, H, W

Forward Function. Args: pred (Tensor): of shape (N, C, H, W). Predicted tensor. target (Tensor): of shape (N, C, H, W

Forward function. Args: pred (torch.Tensor): Tensor with shape of (n, c, h, w). mask (torch.Tensor, optional): Tensor

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

Forward function. Args: pred (Tensor): Predicted tensor. gt (Tensor): GT tensor. Returns: Tensor

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). gt (Tensor): Ground-truth tensor with shape

Forward function. Args: maps (Tuple[Tensor]): Input tensors. soft_attention (Tensor): Soft-attention tensor.

Args: pred (Tensor): of shape (N, C, H, W). Predicted tensor. target (Tensor): of shape (N, C, H, W). Ground truth te

Forward dummy function for getting flops. Args: x (torch.Tensor): Input tensor with shape of (n, c, h, w). Returns:

Used for computing network FLOPs. Args: img (Tensor): Input frames. Returns: Tensor: Output frame(s).

Used for computing network FLOPs. Args: imgs (Tensor): Input images. Returns: Tensor: Restored image.

Used for computing network FLOPs. Args: img (Tensor): Input image. Returns: Tensor: Output image.

Used for computing network FLOPs. Args: img (Tensor): Dummy input used to compute FLOPs. Returns: Tensor: Du

Used for computing network FLOPs. Args: img (Tensor): Dummy input used to compute FLOPs. Returns: Tensor: Du

Defines the computation performed at every test call. Args: merged (Tensor): Image to predict alpha matte. trimap (Te

Defines the computation performed at every test call. Args: merged (Tensor): Image to predict alpha matte. trimap (Te

Defines the computation performed at every test call. Args: merged (Tensor): Image to predict alpha matte. trimap (Te

Forward function for testing. Args: masked_img (torch.Tensor): Tensor with shape of (n, 3, h, w). mask (torch.Tensor)

Forward function for testing. Args: masked_img (torch.Tensor): Tensor with shape of (n, 3, h, w). mask (torch.Tensor)

Forward function for testing. Args: masked_img (torch.Tensor): Tensor with shape of (n, 3, h, w). mask (torch.Tensor)

Testing forward function. Args: inputs (Tensor): The input Tensor with shape (n, 2, c, h, w). target (Tensor): The ta

Testing forward function. Args: lq (Tensor): LQ Tensor with shape (n, c, h, w). gt (Tensor): GT Tensor with shape (n,

Testing forward function. Args: lq (Tensor): LQ Tensor with shape (n, c, h, w). gt (Tensor): GT Tensor with shape (n,

Testing forward function. Args: lq (Tensor): LQ image. gt (Tensor): GT image. coord (Tensor): Coord tenso

Testing forward function. Args: lq (Tensor): LQ Tensor with shape (n, t, c, h, w). gt (Tensor): GT Tensor with shape

Testing forward function. Args: lq (Tensor): LQ Tensor with shape (n, c, h, w). gt (Tensor): GT Tensor with shape (n,

Testing forward function. Args: lq (Tensor): LQ Tensor with shape (n, t, c, h, w). gt (Tensor): GT Tensor with sh

Testing forward function. Args: lq (Tensor): LQ Tensor with shape (n, t, c, h, w). gt (Tensor): GT Tensor with sh

Testing forward function. Args: lq (Tensor): LQ Tensor with shape (n, c, h, w). gt (Tensor): GT Tensor with shape (n,

Forward function for training GCA model. Args: merged (Tensor): with shape (N, C, H, W) encoding input images. Ty

Forward function for training IndexNet model. Args: merged (Tensor): Input images tensor with shape (N, C, H, W).

Defines the computation performed at every training call. Args: merged (Tensor): of shape (N, C, H, W) encoding input images.

Training forward function. Args: inputs (Tensor): Tensor of inputs frames with shape (n, 2, c, h, w).

Training forward function. Args: lq (Tensor): LQ Tensor with shape (n, c, h, w). gt (Tensor): GT Tensor with shap

Training forward function. Args: lq (Tensor): LQ Tensor with shape (n, c, h, w). gt (Tensor): GT Tensor with shap

Training forward function. Args: lq (Tensor): LQ Tensor with shape (n, c, h, w). gt (Tensor): GT Tensor with shape (n

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

Inference image with the model. Args: model (nn.Module): The loaded model. img (str): File path of input image. img_unpai

Calculates the learning rate. Args: runner (object): The passed runner. base_lr (float): Base learning rate.

Gradient error for evaluating alpha matte prediction. Args: alpha (ndarray): Ground-truth alpha matte. trimap (ndarray): Input tr

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

Initialization function. Args: m (nn.Module): Module to be initialized.

Initialize random seed. If the seed is not set, the seed will be automatically randomized, and then broadcast to all processes to prevent som

Abstract method for initializing weight. All subclass should overwrite it.

Init weights for models. Args: pretrained (str, optional): Path for pretrained weights. If given None, pretrained

Init weights for models. Args: pretrained (str, optional): Path for pretrained weights. If given None, pretrained

Init weights for models. Args: pretrained (str, optional): Path for pretrained weights. If given None, pretrained