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

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

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. A

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. A

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

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

Function: ---------- get affine transform matrix 'tfm' from src_pts to dst_pts Parameters: ---------- @src_pts:

Get inverse affine matrix.

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

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_

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

Function: ---------- Find Similarity Transform Matrix 'cv2_trans' which could be directly used by cv2.warpAffine():

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

Numpy array to tensor. Args: imgs (list[ndarray] | ndarray): Input images. bgr2rgb (bool): Whether to change bgr to rgb.

imresize function same as MATLAB. It now only supports bicubic. The same scale applies for both height and width. Args: im

We now only use wandb to sync tensorboard log.

Insert bn layer after each conv. Args: names (list): The list of layer names. Returns: list: The list of layer names w

We resize both tensors to [A,B,2] without new malloc: [A,2] -> [A,1,2] -> [A,B,2] [B,2] -> [1,B,2] -> [A,B,2] Then we compute the area

Compute the jaccard overlap of two sets of boxes. The jaccard overlap is simply the intersection over union of two boxes. Here we operate on

Mod crop images, used during testing. Args: img (ndarray): Input image. scale (int): Scale factor. Returns: n

Returns a new subclass of tuple with named fields. >>> Point = namedtuple('Point', ['x', 'y']) >>> Point.__doc__ # docst

Calculate NIQE (Natural Image Quality Evaluator) metric. Ref: Making a "Completely Blind" Image Quality Analyzer. This implementation coul

Performs Non-Maximum Suppression (NMS) on inference results Returns: detections with shape: nx6 (x1, y1, x2, y2, conf, cls)

TODO: Validation using updated metric system The metrics are now evaluated after all images have been tested This allows b

Support OrderedDict for yaml. Returns: yaml Loader and Dumper.

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

Generate paired paths from an meta information file. Each line in the meta information file contains the image names and image shape (usua

Generate paths from lmdb. Args: folder (str): Folder path. Returns: list[str]: Returned path list.

Calculate PDF of the bivariate Gaussian distribution. Args: sigma_matrix (ndarray): with the shape (2, 2) grid (ndarray): gen

Convert prior_boxes to (xmin, ymin, xmax, ymax) representation for comparison to point form ground truth data. Args: boxes: (tenso

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

Quantize an array of (-inf, inf) to [0, levels-1]. Args: arr (ndarray): Input array. min_val (scalar): Minimum value to be cl

Quantize flow to [0, 255]. After this step, the size of flow will be much smaller, and can be dumped as jpeg images. Args:

R1 regularization for discriminator. The core idea is to penalize the gradient on real data alone: when the generator distribution p