Process unknown mask. Args: unknown (Tensor, optional): Unknown area map generated by trimap of shape (N, 1, ori_

Propagate the latent features throughout the sequence. Args: feats dict(list[tensor]): Features from previous branches. Each

Propagate alpha feature based on guided attention score. Args: gca_score (Tensor): Guided attention score map of shape

Generate a random bbox for the mask on a given image. In our implementation, the max value cannot be obtained since we use `np.random.randint

Generate a 2D Sinc filter. Reference: https://dsp.stackexchange.com/questions/58301/2-d-circularly-symmetric-low-pass-filter # noqa Args:

Read frames from file or video. Args: source (list | mmcv.VideoReader): Source of frames. start_index (int): Start index of frame

Reduce loss as specified. Args: loss (Tensor): Elementwise loss tensor. reduction (str): Options are "none", "mean" and "sum".

Reduce facial landmark heatmaps to 5 heatmaps. DIC realizes facial SR with the help of key points of the face. The number of key points in da

Resize along a specific dimension. Args: img_in (ndarray): The input image. weights (ndarray): The weights used for interpolation

Save visualization results. Args: img (torch.Tensor): Tensor with shape of (n, 3, h, w). filename (str): Path to save

Modify bbox to target size. The original bbox will be enlarged to the target size with the original bbox in the center of the new bbox.

Generate spatial discounting mask constant. Args: mask_width (int): The width of bbox hole. mask_height (int): The he

Apply pdding spatially. Since the PCD module in EDVR requires that the resolution is a multiple of 4, we apply padding to the input L

Apply pdding spatially. Since the SPyNet module in TOFlow requires that the resolution is a multiple of 16, we apply padding to the i

split input tensors for inference. Args: input_tensors (Tensor): Tensor of input frames with shape [1, t, c, h, w

Make sure different ranks share the same seed. All workers must call this function, otherwise it will deadlock. This method is generally used

Wrap models with separate MMDistributedDataParallel. It only wraps the modules with parameters.

Train model entry function. Args: model (nn.Module): The model to be trained. dataset (:obj:`Dataset`): Train dataset. cf

Calculate two-stage loss. Args: stage1_data (dict): Contain stage1 results. stage2_data (dict): Contain stage2 result

Calculate two-stage loss. Args: stage1_data (dict): Contain stage1 results. stage2_data (dict): Contain stage2 result

Extract features of real and fake images. Args: img1, img2 (np.ndarray): Images with range [0, 255] and shape (H,

Calculate FID. Args: X (np.ndarray): Input feature X with shape (n_samples, dims). Y (np.ndarray): Input feature Y wi

Calculate KID. Args: X (np.ndarray): Input feature X with shape (n_samples, dims). Y (np.ndarray): Input feature Y wi

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: data (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation. 'gt'

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation. Requi

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Call function. Args: results (dict): A dict containing the necessary information and data for augmentation.

Standard interface for forward pre hooks.

Get item at each call. Args: idx (int): Index for getting each item.

Get item at each call. Args: idx (int): Index for getting each item.

Get item at each call. Args: idx (int): Index for getting each item.

Get item at each call. Args: idx (int): Index for getting each item.

Get item at each call. Args: idx (int): Index for getting each item.

Get item at each call. Args: idx (int): Index for getting each item.

Get item at each call. Args: idx (int): Index for getting each item.