same as matlab rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

conversion among BGR, gray and y

Crop borders of images. Args: img_list (list [ndarray] | ndarray): Image list with shape (h, w, c). crop_border (int): Crop borde

Flip testing with X4 self ensemble, i.e., normal, flip H, flip W, flip H and W. Args: model (PyTorch model) inp (Tensor): inp

Warp an image or feature map with optical flow. Args: x (Tensor): Tensor with size (N, C, H, W). flow (Tensor): Tensor with size

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

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

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

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

Args: x (Tensor): The input for the loss module. maps (Tensor): The maps generated by swap module. weight

Args: x (Tensor): the input image of SRNTT. maps (dict[Tensor]): the swapped feature maps on relu3_1, relu2_1

Args: pre_offset: precomputed_offset. Size: [b, 9, h, w, 2]

Args: pre_offset: precomputed_offset. Size: [b, 9, h, w, 2]

Get values according to the filepath from one lmdb named client_key. Args: filepath (str | obj:`Path`): Here, filepath is the lmd

Generate an index list for reading num_frames frames from a sequence of images. Args: crt_idx (int): Current center index. ma

Make layers by stacking the same blocks. Args: basic_block (nn.module): nn.module class for basic block. n_basic_blocks (int): nu

Create a masked version of a given loss function. To use this decorator, the loss function must have the signature like `loss_func(pred, targ

Paired random crop. It crops lists of lq and gt images with corresponding locations. Args: img_gts (list[ndarray] | ndarray): GT ima

Pixel unshuffle. Args: x (Tensor): the input feature. The shape is [b, c, hh, hw]. s (int): downsample ratio. Returns:

Calculate PSNR (Peak Signal-to-Noise Ratio). Ref: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio Args: img1, img2 (ndarray