Args: x: (B, H, W, C) Returns: x: (B, C, H, W)

Build dataloader. Args: dataset (torch.utils.data.Dataset): Dataset. dataset_opt (dict): Dataset options. It contains the followi

Build dataset from options. Args: dataset_opt (dict): Configuration for dataset. It must contain: name (str): Dataset name.

Build dataset from options. Args: dataset_opt (dict): Configuration for dataset. It must contain: name (str): Dataset name.

copy model from net_a to net_b

r'''Compute correlation of image with FILT using window, followed by downsampling. Args: image: A tensor. Shape :math:`(N, C, H, W

r""" Function same as 'fspecial' in MATLAB, only support gaussian now. Args: size (int or tuple): size of window sigma (float): si

imfilter same as matlab. Args: input (tensor): (b, c, h, w) tensor to be filtered weight (tensor): (out_ch, in_ch, kh, kw) filter

Args: x (torch.Tensor): scale (float): sizes (tuple(int, int)): kernel (str, default='cubic'): sigma (flo

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

Paired random crop. Support Numpy array and Tensor inputs. It crops lists of lq and gt images with corresponding locations. Args: im

Preprocess the input tensor by normalizing it. Args: x (torch.Tensor): The input tensor. Returns: t

r'''Compute Laplacian Pyramid Args: im: An input tensor. Shape :math:`(N, C, H, W)`.

Reorder images to 'HWC' order. If the input_order is (h, w), return (h, w, 1); If the input_order is (c, h, w), return (h, w, c); If the

Save networks and training state.

Save networks. Args: net (nn.Module | list[nn.Module]): Network(s) to be saved. net_label (str): Network label.

Change to Y channel of YCbCr. Args: img (ndarray): Images with range [0, 255]. Returns: (ndarray): Images with range [0, 255

Converts a string to a list of tokens. If `self.legacy` is set to `False`, a prefix token is added unless the first token is special.

Build pretrained InceptionV3 Parameters ---------- - output_blocks : list of int Indices of blocks to return featu

Convert the type and range of the input image. It converts the input image to np.float32 type and range of [0, 1]. It is mainly used for pre-

Convert the type and range of the input image. It converts the input image to np.float32 type and range of [0, 1]. It is mainly used for pre-

Convert the type and range of the image according to dst_type. It converts the image to desired type and range. If `dst_type` is np.uint8, im

Convert the type and range of the image according to dst_type. It converts the image to desired type and range. If `dst_type` is np.uint8, im

Augment: horizontal flips OR rotate (0, 90, 180, 270 degrees). We use vertical flip and transpose for rotation implementation. All the images

Format the LLM's recommendations in a more visually appealing way Args: answer (str): The raw answer from LLM models (li

Calculate metric from data and options. Args: opt (dict): Configuration. It must contain: type (str): Model type.

copy model from net_a to net_b

r'''Compute correlation of image with FILT, followed by downsampling. Args: image: A tensor. Shape :math:`(N, C, H, W)`. filt: A f

Create model. Args: opt (dict): Configuration. It constains: model_type (str): Model type.

Estimate AGGD (Asymmetric Generalized Gaussian Distribution) parameters. Args: block (Tensor): Image block with shape (b, 1, h, w). Re

Extract model names from the answer string using regex Args: answer (str): The answer string containing model recommendations

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

r""" Compute the inception features for a folder of image files

r"""Return coordinate grid matrices centered at zero point. Args: size: Shape of meshgrid to create

r"""Get mean and variance of input local patch.

r"""Compute gradient map for a given tensor and stack of kernels. Args: x: Tensor with shape (N, C, H, W). kernels: Stack of tenso

r"""Similar to np.fft.ifftshift but applies to PyTorch Tensors

Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None or li

Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None or li

Insert CLS token.

Load network. Args: load_path (str): The path of networks to be loaded. net (nn.Module): Network. strict

Model to device. It also warps models with DistributedDataParallel or DataParallel. Args: net (nn.Module)

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

Preprocesses an RGB image tensor. Args: - x (torch.Tensor): The input RGB image tensor. - test_y_channel (bool): Whether to

Generate paths and mos labels from an meta information file. Each line in the meta information file contains the image names and mos label, s

reduce loss dict. In distributed training, it averages the losses among different GPUs . Args: loss_dict (OrderedDict):