# BasicSR **Repository Path**: shawnvision7264/BasicSR ## Basic Information - **Project Name**: BasicSR - **Description**: 开源图像和视频复原工具包（超分辨率， 去噪， 去模糊等）. 目前包括: EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR 等模型. 也支持了 StyleGAN2 和 DFDNet. - **Primary Language**: Python - **License**: Not specified - **Default Branch**: master - **Homepage**: http://xinntao.gitee.io/ - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 44 - **Created**: 2021-08-15 - **Last Updated**: 2024-11-25 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # :rocket: BasicSR [![LICENSE](https://img.shields.io/github/license/xinntao/basicsr.svg)](https://github.com/xinntao/BasicSR/blob/master/LICENSE/LICENSE) [![PyPI](https://img.shields.io/pypi/v/basicsr)](https://pypi.org/project/basicsr/) [![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/xinntao/BasicSR.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/xinntao/BasicSR/context:python) [![python lint](https://github.com/xinntao/BasicSR/actions/workflows/pylint.yml/badge.svg)](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/pylint.yml) [![Publish-pip](https://github.com/xinntao/BasicSR/actions/workflows/publish-pip.yml/badge.svg)](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/publish-pip.yml) [![gitee mirror](https://github.com/xinntao/BasicSR/actions/workflows/gitee-mirror.yml/badge.svg)](https://github.com/xinntao/BasicSR/blob/master/.github/workflows/gitee-mirror.yml) [English](README.md) **|** [简体中文](README_CN.md)   [GitHub](https://github.com/xinntao/BasicSR) **|** [Gitee码云](https://gitee.com/xinntao/BasicSR) google colab logo Google Colab: [GitHub Link](colab) **|** [Google Drive Link](https://drive.google.com/drive/folders/1G_qcpvkT5ixmw5XoN6MupkOzcK1km625?usp=sharing)
:m: [模型库](docs/ModelZoo_CN.md) :arrow_double_down: 百度网盘: [预训练模型](https://pan.baidu.com/s/1R6Nc4v3cl79XPAiK0Toe7g) **|** [复现实验](https://pan.baidu.com/s/1UElD6q8sVAgn_cxeBDOlvQ) :arrow_double_down: Google Drive: [Pretrained Models](https://drive.google.com/drive/folders/15DgDtfaLASQ3iAPJEVHQF49g9msexECG?usp=sharing) **|** [Reproduced Experiments](https://drive.google.com/drive/folders/1XN4WXKJ53KQ0Cu0Yv-uCt8DZWq6uufaP?usp=sharing)
:file_folder: [数据](docs/DatasetPreparation_CN.md) :arrow_double_down: [百度网盘](https://pan.baidu.com/s/1AZDcEAFwwc1OC3KCd7EDnQ) (提取码:basr) :arrow_double_down: [Google Drive](https://drive.google.com/drive/folders/1gt5eT293esqY0yr1Anbm36EdnxWW_5oH?usp=sharing)
:chart_with_upwards_trend: [wandb的训练曲线](https://app.wandb.ai/xintao/basicsr)
:computer: [训练和测试的命令](docs/TrainTest_CN.md)
:zap: [HOWTOs](#zap-howtos) --- BasicSR (**Basic** **S**uper **R**estoration) 是一个基于 PyTorch 的开源图像视频复原工具箱, 比如 超分辨率, 去噪, 去模糊, 去 JPEG 压缩噪声等.
([ESRGAN](https://github.com/xinntao/ESRGAN), [EDVR](https://github.com/xinntao/EDVR), [DNI](https://github.com/xinntao/DNI), [SFTGAN](https://github.com/xinntao/SFTGAN)) ([HandyView](https://gitee.com/xinntao/HandyView), [HandyFigure](https://gitee.com/xinntao/HandyFigure), [HandyCrawler](https://gitee.com/xinntao/HandyCrawler), [HandyWriting](https://gitee.com/xinntao/HandyWriting)) ## :sparkles: 新的特性 - July 31, 2021. Add **bi-directional video super-resolution** codes: [**BasicVSR** and IconVSR](https://arxiv.org/abs/2012.02181). - July 20, 2021. Add **dual-blind face restoration** codes: [**HiFaceGAN**](https://github.com/Lotayou/Face-Renovation) codes by [Lotayou](https://lotayou.github.io/). - Nov 29, 2020. 添加 **ESRGAN** and **DFDNet** [colab demo](colab). - Sep 8, 2020. 添加 **盲人脸复原**测试代码: [DFDNet](https://github.com/csxmli2016/DFDNet). - Aug 27, 2020. 添加 **StyleGAN2 训练和测试** 代码: [StyleGAN2](https://github.com/rosinality/stylegan2-pytorch).
更多
## :zap: HOWTOs 我们提供了简单的流程来快速上手 训练/测试/推理 模型. 这些命令并不能涵盖所有用法, 更多的细节参见下面的部分. | GAN | | | | | | | :--- | :---: | :---: | :--- | :---: | :---: | | StyleGAN2 | [训练](docs/HOWTOs_CN.md#如何训练-StyleGAN2) | [测试](docs/HOWTOs_CN.md#如何测试-StyleGAN2) | | | | | **Face Restoration** | | | | | | | DFDNet | - | [测试](docs/HOWTOs_CN.md#如何测试-DFDNet) | | | | | **Super Resolution** | | | | | | | ESRGAN | *TODO* | *TODO* | SRGAN | *TODO* | *TODO*| | EDSR | *TODO* | *TODO* | SRResNet | *TODO* | *TODO*| | RCAN | *TODO* | *TODO* | | | | | EDVR | *TODO* | *TODO* | DUF | - | *TODO* | | BasicVSR | *TODO* | *TODO* | TOF | - | *TODO* | | **Deblurring** | | | | | | | DeblurGANv2 | - | *TODO* | | | | | **Denoise** | | | | | | | RIDNet | - | *TODO* | CBDNet | - | *TODO*| ## :wrench: 依赖和安装 For detailed instructions refer to [INSTALL.md](INSTALL.md). ## :hourglass_flowing_sand: TODO 清单 参见 [project boards](https://github.com/xinntao/BasicSR/projects). ## :turtle: 数据准备 - 数据准备步骤, 参见 **[DatasetPreparation_CN.md](docs/DatasetPreparation_CN.md)**. - 目前支持的数据集 (`torch.utils.data.Dataset`类), 参见 [Datasets_CN.md](docs/Datasets_CN.md). ## :computer: 训练和测试 - **训练和测试的命令**, 参见 **[TrainTest_CN.md](docs/TrainTest_CN.md)**. - **Options/Configs**配置文件的说明, 参见 [Config_CN.md](docs/Config_CN.md). - **Logging**日志系统的说明, 参见 [Logging_CN.md](docs/Logging_CN.md). ## :european_castle: 模型库和基准 - 目前支持的模型描述, 参见 [Models_CN.md](docs/Models_CN.md). - **预训练模型和log样例**, 参见 **[ModelZoo_CN.md](docs/ModelZoo_CN.md)**. - 我们也在 [wandb](https://app.wandb.ai/xintao/basicsr) 上提供了**训练曲线**等:

## :memo: 代码库的设计和约定 参见 [DesignConvention_CN.md](docs/DesignConvention_CN.md).
下图概括了整体的框架. 每个模块更多的描述参见:
**[Datasets_CN.md](docs/Datasets_CN.md)** | **[Models_CN.md](docs/Models_CN.md)** | **[Config_CN.md](Config_CN.md)** | **[Logging_CN.md](docs/Logging_CN.md)** ![overall_structure](./assets/overall_structure.png) ## :scroll: 许可 本项目使用 Apache 2.0 license.
更多关于**许可**和**致谢**, 请参见 [LICENSE](LICENSE/README.md). ## :earth_asia: 引用 如果 BasicSR 对你有所帮助, 可以考虑引用BasicSR.
下面是一个 BibTex 引用条目, 它需要 `url` LaTeX package. ``` latex @misc{wang2020basicsr, author = {Xintao Wang and Ke Yu and Kelvin C.K. Chan and Chao Dong and Chen Change Loy}, title = {{BasicSR}: Open Source Image and Video Restoration Toolbox}, howpublished = {\url{https://github.com/xinntao/BasicSR}}, year = {2020} } ``` > Xintao Wang, Ke Yu, Kelvin C.K. Chan, Chao Dong and Chen Change Loy. BasicSR: Open Source Image and Video Restoration Toolbox. https://github.com/xinntao/BasicSR, 2020. ## :e-mail: 联系 若有任何问题, 请电邮 `xintao.wang@outlook.com`.