Args: image(Tensor): batch x 3 x height x width Returns: Tensor: batch x height x width x 3

Args: image(tensor): batch x height x width x 3 Returns: y(tensor): batch x height x width cb(te

Args: image(tensor): batch x height x width Returns: Tensor: batch x h*w/64 x h x w

Args: image(tensor): batch x height x width Returns: Tensor: batch x height x width

Args: image(tensor): batch x height x width Returns: Tensor: batch x height x width

Args: image(tensor): batch x height x width Returns: Tensor: batch x height x width

Args: image(tensor): batch x 3 x height x width Returns: dict(tensor): Compressed tensor with batch x h*w/64

Args: image(tensor): batch x height x width Returns: Tensor: batch x height x width

Args: image(tensor): batch x height x width Returns: Tensor: batch x height x width

Args: image(tensor): batch x height x width Returns: Tensor: batch x height x width

Args: patches(tensor) batch x height*width/64, height x width height(int) width(int) Returns:

Args: y(tensor): y channel image cb(tensor): cb channel cr(tensor): cr channel Returns:

Args: image(tensor): batch x height x width x 3 Returns: Tensor: batch x 3 x height x width

Args: compressed(dict(tensor)): batch x h*w/64 x 8 x 8 imgh(int) imgw(int) factor(float)

Args: x (Tensor): Input image, bchw, rgb, [0, 1] quality(float): Quality factor for jpeg compression scheme.

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

Args: x: input features with shape of (num_windows*B, N, C) mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh

x: B, H*W, C

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

Forward function. Args: x (Tensor): Input tensor with shape (n, c, h, w). gt (Tensor): Ground-truth tensor with shape

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

Generate Gaussian kernel used in `duf_downsample`. Args: kernel_size (int): Kernel size. Default: 13. sigma (float): Sigma of the

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

Compute learning rate using chainable form of the scheduler.

Generate a binary mask based on alpha value.