The registry that provides name -> object mapping, to support third-party users' custom modules. To create a registry (e.g. a backbone r

r""" SwinIR A PyTorch impl of : `SwinIR: Image Restoration Using Swin Transformer`, based on Swin Transformer. Args: img_size (in

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

r""" Image to Patch Embedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

r""" Image to Patch Unembedding Args: img_size (int): Image size. Default: 224. patch_size (int): Patch token size. Default: 4.

A basic Swin Transformer layer for one stage. Args: dim (int): Number of input channels. input_resolution (tuple[int]): Input re

Merge patches into image

Splitting image into patches

Dequantize CbCr channel

CPU prefetcher. Args: loader: Dataloader.

JPEG Quantization for CbCr channels Args: rounding(function): rounding function to use

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

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

Chroma subsampling on CbCr channels

Upsample chroma layers

Full JPEG compression algorithm Args: rounding(function): rounding function to use

Discrete Cosine Transformation

Full JPEG decompression algorithm Args: rounding(function): rounding function to use

This JPEG algorithm result is slightly different from cv2. DiffJPEG supports batch processing. Args: differentiable(bool): If True, u

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

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

钩子类,用于捕获前向和后向信息

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

Converts RGB image to YCbCr

Residual Swin Transformer Block (RSTB). Args: dim (int): Number of input channels. input_resolution (tuple[int]): Input resolutio

r""" Swin Transformer Block. Args: dim (int): Number of input channels. input_resolution (tuple[int]): Input resulotion.

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

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

r""" Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window. A

Converts YCbCr image to RGB JPEG

Dequantize Y channel

JPEG Quantization for Y channel Args: rounding(function): rounding function to use

Inverse discrete Cosine Transformation

Adaptive Mask Generator generate adaptive mask based on semantics

Base model.