Giter VIP home page Giter VIP logo

izhx / tc-youkuvsre Goto Github PK

View Code? Open in Web Editor NEW
42.0 2.0 7.0 7.79 MB

天池2019阿里巴巴优酷视频增强和超分辨率挑战赛自用代码,EDVR、WDSR、ESRGAN三个模型。

License: MIT License

Python 90.71% Shell 0.09% C++ 1.73% Cuda 6.31% C 0.64% MATLAB 0.52%
deep-learning super-resolution video-super-resolution single-image-super-resolution tianchi pytorch computer-vision python

tc-youkuvsre's Introduction

YoukuSR

“努力,要努力,我要变成万人迷!”

天池2019阿里巴巴优酷视频增强和超分辨率挑战赛自用代码,EDVR、WDSR、ESRGAN三个模型。有参考价值的东西,可能只有utils/y4m_tools.py

简介

第一次参加天池,还要期末考试压力好大嘤嘤嘤~

初赛GG了,比赛结束后发现与前排的思路一致,只是没卡没时间哇,2-stage、ensemble、flip都没做,只提交了baseline,不过此次参赛学习到了很多知识。

数据处理是自己手写的,读取y4m文件流,分帧转化为yuv444的;写了几个Dataset,分别给VSR和SISR用,VSR时做了场景分割(室友写的机器学习算法,暂时没专门学习场景检测的文献)以及帧序列padding的处理(在xintao大佬的策略上稍作修改),WDSR修改了一点点代码尝试单通道SR。输出生成y4m和输入差不多。

EDVR、WDSR的model architecture来自EDVRwdsr_ntire2018,自己写了训练代码。ESRGAN代码全部来自BasicSR,不得不说大佬所有东西都手写,代码很健壮,造轮子精神可嘉。

自己配置了Netflix的vmaf并且封装了函数,在utils/vmaf_tools.py中。

文件结构

├── README.md               // readme
├── dataset                 // 数据集
├── data                    // 数据代码
├── utils                   // 通用工具
├── model                   // 模型代码
├── models                  // 模型代码
├── optim                   // 优化器
├── options                 // 配置项
├── vmaf                    // vmaf
├── scripts                 // 
└── ...                     // 

编码规范

环境依赖等

Python 3.6.x ...

pytorch使用tensorboard.

tc-youkuvsre's People

Contributors

gaozhangyang avatar irisrainbowneko avatar izhx avatar midebuxing avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.