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

CPU prefetcher. Args: loader: Dataloader.

CUDA prefetcher. Ref: https://github.com/NVIDIA/apex/issues/304# It may consums more GPU memory. Args: loader: Dataloader.

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

Prefetch version of dataloader. Ref: https://github.com/IgorSusmelj/pytorch-styleguide/issues/5# TODO: Need to test on single gpu an

A general prefetch generator. Ref: https://stackoverflow.com/questions/7323664/python-generator-pre-fetch Args: generator: Pytho

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

Charbonnier Loss (L1)

Cosine annealing with restarts learning rate scheme. An example of config: periods = [10, 10, 10, 10] restart_weights = [1, 0.5, 0.5, 0.5

Cosine annealing with restarts learning rate scheme. An example of config: periods = [10, 10, 10, 10] restart_weights = [1, 0.5, 0.5, 0.

Paired image dataset for image restoration. Read LQ (Low Quality, e.g. LR (Low Resolution), blurry, noisy, etc) and GT image pairs. Ther

Paired image dataset for image restoration. Read LQ (Low Quality, e.g. LR (Low Resolution), blurry, noisy, etc) and GT image pairs. Ther

Paired image dataset for image restoration. Read LQ (Low Quality, e.g. LR (Low Resolution), blurry, noisy, etc) and GT image pairs. Ther

Paired image dataset for image restoration. Read LQ (Low Quality, e.g. LR (Low Resolution), blurry, noisy, etc) and GT image pairs. Ther

FFHQ dataset for StyleGAN. Args: opt (dict): Config for train datasets. It contains the following keys: dataroot_gt (str): Da

Helper for the face restoration pipeline.

Raw hard disks storage backend.

Base Deblur model for single image deblur.

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

Args: optimizer (torch.nn.optimizer): Torch optimizer. milestones (list): Iterations that will decrease learning rate. g

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

LMDB Maker. Args: lmdb_path (str): Lmdb save path. map_size (int): Map size for lmdb env. Default: 1024 ** 4, 1TB. batch

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

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

MLP as used in Vision Transformer, MLP-Mixer and related networks

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

REDS dataset for training. The keys are generated from a meta info txt file. basicsr/data/meta_info/meta_info_REDS_GT.txt Each line cont

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

Read only lq images in the test phase. Read LQ (Low Quality, e.g. LR (Low Resolution), blurry, noisy, etc). There are two modes: 1. 'met

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

Args: optimizer (torch.nn.optimizer): Torch optimizer. milestones (list): Iterations that will decrease learning rate. g

Video test dataset for recurrent architectures, which takes LR video frames as input and output corresponding HR video frames. Args:

Video test dataset for DUF dataset. Args: opt (dict): Config for train dataset. Most of keys are the same as VideoTestDatase

Video test dataset. Supported datasets: Vid4, REDS4, REDSofficial. More generally, it supports testing dataset with following structures:

Video test dataset for Vimeo90k-Test dataset. It only keeps the center frame for testing. For testing datasets, there is no need to prepare L

Vimeo90K dataset for training. The keys are generated from a meta info txt file. basicsr/data/meta_info/meta_info_Vimeo90K_train_GT.txt