hidden_states: (B, L, D) Returns: same shape as hidden_states

r"""Pass the input through the encoder layer. Args: hidden_states: the sequence to the encoder layer (required). resi

hidden_states: (B, L, D) Returns: same shape as hidden_states

Calculate the artifact map of LDL (Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution. In CVPR 2

Learning Rate Schedule # Arguments epoch (int): The number of epochs # Returns lr (float32): learnin

Learning Rate Schedule # Arguments epoch (int): The number of epochs # Returns lr (float32): learnin

Make coordinates at grid centers.

Make coordinates at grid centers.

Peak signal-to-noise ratio averaged over samples and channels.

Peak signal-to-noise ratio averaged over samples and channels.

RMSE for (N, C, H, W) image; torch.float32 [0.,1.].

type = ["split", "cross"]

Convert torch Tensors into image numpy arrays. After clamping to [min, max], values will be normalized to [0, 1]. Args: tensor (Tens

Convert torch Tensors into image numpy arrays. After clamping to [min, max], values will be normalized to [0, 1]. Args: tensor (Tens

2 pixel shift compare with original matlab version

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