A progress bar which can print the progress. Modified from: https://github.com/hellock/cvbase/blob/master/cvbase/progress.py

VGG network for feature extraction. In this implementation, we allow users to choose whether use normalization in the input feature and the t

A general file client to access files in different backend. The client loads a file or text in a specified backend from its path and return i

Sampler that restricts data loading to a subset of the dataset. Modified from torch.utils.data.distributed.DistributedSampler Support enlargi

Message logger for printing. Args: opt (dict): Config. It contains the following keys: name (str): Exp name. logg

None dict. It will return none if key is not in the dict.

Base model.

Abstract class of storage backends. All backends need to implement two apis: `get()` and `get_text()`. `get()` reads the file as a byte strea

Ceph storage backend.

Charbonnier loss (one variant of Robust L1Loss, a differentiable variant of L1Loss). Described in "Deep Laplacian Pyramid Networks for Fast a

Dataset for the training of Contrastive Correspondence Network. There are three modes: 1. 'lmdb': Use lmdb files. If opt['io_backend'

Dataset for the validation of Contrastive Correspondence Network. There are three modes: 1. 'lmdb': Use lmdb files. If opt['io_backen

Cosine annealing with restarts learning rate scheme. An example of config: period = [10, 10, 10, 10] restarts = [10, 20, 30] restart

Use other features to generate offsets and masks. Intialized the offset with precomputed non-local offset.

Use other features to generate offsets and masks

Use other features to generate offsets and masks. Intialized the offset with precomputed non-local offset.

Define GAN loss. Args: gan_type (str): Support 'vanilla', 'lsgan', 'wgan', 'hinge'. real_label_val (float): The value for real la

Gradient penalty loss for wgan-gp. Args: loss_weight (float): Loss weight. Default: 1.0.

Raw hard disks storage backend.

L1 (mean absolute error, MAE) loss. Args: loss_weight (float): Loss weight for L1 loss. Default: 1.0. reduction (str): Specifies

Lmdb storage backend. Args: db_paths (str | list[str]): Lmdb database paths. client_keys (str | list[str]): Lmdb client keys. Def

MSE (L2) loss. Args: loss_weight (float): Loss weight for MSE loss. Default: 1.0. reduction (str): Specifies the reduction to app

Perceptual loss with commonly used style loss. Args: layers_weights (dict): The weight for each layer of vgg feature. Here is

Memcached storage backend. Attributes: server_list_cfg (str): Config file for memcached server list. client_cfg (str): Config fil

MultiStep with restarts learning rate scheme. Args: optimizer (torch.nn.optimizer): Torch optimizer. milestones (list): Iteratio

Perceptual loss with commonly used style loss. Args: layers_weights (dict): The weight for each layer of vgg feature. Here is

Perceptual loss with multiple inputs images. Args: x (Tensor): Input tensor with shape (B, N, C, H, W), where N indicates num

Reference based CUFED dataset for super-resolution. There are three modes: 1. 'lmdb': Use lmdb files. If opt['io_backend'] == lmdb.

Residual block without BN. It has a style of: ---Conv-ReLU-Conv-+- |________________| Args: nf (int): Number of fea

Residual block with BN. It has a style of: ---Conv-BN-ReLU-Conv-BN-+- |______________________| Args: nf (int): Numb

Single image SR model.

Define Texture Loss. Args: use_weights (bool): If True, the weights computed in swapping will be used to scale the features.

Upsample module. Args: scale (int): Scale factor. Supported scales: 2^n and 3. nf (int): Channel number of intermediate features.