Print keys with different name or different size when loading models. 1. Print keys with different names. 2. If strict=False, print t

Set learning rate for warm-up. Args: lr_groups_l (list): List for lr_groups, each for an optimizer.

Calculate SSIM (structural similarity) for one channel images. It is called by func:`calculate_ssim`. Args: img (ndarray): Images wi

Calculate SSIM (structural similarity) (PyTorch version). It is called by func:`calculate_ssim_pt`. Args: img (Tensor): Images with

Adaptive instance normalization. Adjust the reference features to have the similar color and illuminations as those in the degradate features

USM sharpening. borrowed from real-ESRGAN Input image: I; Blurry image: B. 1. K = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > thresho

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

Kai Zhang (github: https://github.com/cszn)

Create a 1D, 2D, or 3D average pooling module.

bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

Generate a bivariate isotropic or anisotropic Gaussian kernel. In the isotropic mode, only `sig_x` is used. `sig_y` and `theta` is ignored.

Generate a bivariate generalized Gaussian kernel. ``Paper: Parameter Estimation For Multivariate Generalized Gaussian Distributions`` In the

Generate a plateau-like anisotropic kernel. 1 / (1+x^(beta)) Reference: https://stats.stackexchange.com/questions/203629/is-there-a-plateau-

x: image, NxcxHxW k: kernel, Nx1xhxw

PSNR metric. im1, im2: h x w x , [0, 255], uint8

Calculate PSNR (Peak Signal-to-Noise Ratio). Reference: https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio Args: img (ndarray)

SSIM the same outputs as MATLAB's im1, im2: h x w x , [0, 255], uint8

Calculate SSIM (structural similarity). ``Paper: Image quality assessment: From error visibility to structural similarity`` The results are

Check whether the input is a mirror-extended sequence. If mirror-extended, the i-th (i=0, ..., t-1) frame is equal to the (t-1-i)-th frame.

Check resume states and pretrain_network paths. Args: opt (dict): Options. resume_iter (int): Resume iteration.

jitter color: randomly jitter the RGB values, in numpy formats

jitter color: randomly jitter the brightness, contrast, saturation, and hue, in torch Tensor formats

Compute features. Args: block (ndarray): 2D Image block. Returns: list: Features with length of 18.

Compute optical flow using SPyNet for feature alignment. Note that if the input is an mirror-extended sequence, 'flows_forward' is no

Conv block used in MSDilationBlock.

Performs data augmentation of the input image Input: image: a cv2 (OpenCV) image mode: int. Choice of transformation to apply

Dequantize an array. Args: arr (ndarray): Input array. min_val (scalar): Minimum value to be clipped. max_val (scalar): M

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). From: https://github.com/rwightman/pytorch-image-models/

Build pretrained Inception model for FID computation. The Inception model for FID computation uses a different set of weights and has a sligh

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

Get facial component (left_eye, right_eye, mouth) coordinates from a pre-loaded pth file

Degradation pipeline, modified from Real-ESRGAN: https://github.com/xinntao/Real-ESRGAN

Degradation pipeline, modified from Real-ESRGAN: https://github.com/xinntao/Real-ESRGAN

Get local weights for generating the artifact map of LDL. It is only called by the `get_refined_artifact_map` function. Args: residu

Get the position from a period list. It will return the index of the right-closest number in the period list. For example, the cumulative_per

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

Get target label. Args: input (Tensor): Input tensor. target_is_real (bool): Whether the target is real or fake.

This matches the implementation in Denoising Diffusion Probabilistic Models: From Fairseq. Build sinusoidal embeddings. This matches

Calculate image gradient. Input: im: h x w x c numpy array

Calculate image gradient. Input: im: h x w x c numpy array