Scribd Logo
Upload

Welcome to Scribd!

  • 182 views

    Waifu Args

    Uploaded by

    Vee
    This GitHub repository contains an open source tool for reducing noise and increasing the resolution of anime-style artwork using deep learning models. The README explains how to install dependencies, run the command line tool and web application, train custom models, and convert videos.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Waifu Args

    Uploaded by

    Vee
    182 views7 pages
    This GitHub repository contains an open source tool for reducing noise and increasing the resolution of anime-style artwork using deep learning models. The README explains how to install dependencies, run the command line tool and web application, train custom models, and convert videos.

    Original Description:

    How to use Waifu2x.

    Original Title

    waifu args

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This GitHub repository contains an open source tool for reducing noise and increasing the resolution of anime-style artwork using deep learning models. The README explains how to install dependencies, run the command line tool and web application, train custom models, and convert videos.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    182 views7 pages

    Waifu Args

    Uploaded by

    Vee
    This GitHub repository contains an open source tool for reducing noise and increasing the resolution of anime-style artwork using deep learning models. The README explains how to install dependencies, run the command line tool and web application, train custom models, and convert videos.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 7

    GitHub - nagadomi/waifu2x: Image Super-Resolution for Anime-Style Art

    Personal

    Open source

    Business

    Explore

    6/17/16, 21:42

    Pricing

    Blog

    Support

    This repository

    nagadomi / waifu2x
    Code

    Watch

    Issues 23

    Pull requests 0

    Wiki

    Pulse

    401

    Sign up

    Sign in

    Search

    Star

    Fork

    5,924

    695

    Graphs

    Image Super-Resolution for Anime-Style Art


    331 commits

    Branch: master

    3 branches

    3 releases

    New pull request

    nagadomi committed on GitHub Merge pull request #120 from izzygomez/patch-1

    17 contributors

    Find file

    Clone or download

    Latest commit 96098d7 3 days ago

    appendix

    Add support for Korean language

    a month ago

    assets

    improve german locale

    20 days ago

    cache

    first commit

    data

    Fix .gitignore

    7 months ago

    images

    Update supplementary material

    7 months ago

    lib

    Add more informative message for CUDA error

    a month ago

    models

    Revert anime_style_art_rgb/scale2.0x_model.t7

    3 months ago

    tools

    Remove unused attributes in json

    3 months ago

    webgen

    improve german locale

    .gitattributes

    Add .gitattributes

    7 months ago

    .gitignore

    Update .gitignore

    7 months ago

    LICENSE

    add LICENSE and NOTICE

    NOTICE

    Update NOTICE

    README.md

    (minor) Update README

    convert_data.lua

    Fix undefined variable in convert_data.lua

    7 months ago

    train.lua

    Optionalize downsampling filters

    3 months ago

    train.sh

    Reproducibility for anime_style_art_rgb

    3 months ago

    train_photo.sh

    Update training script

    3 months ago

    train_ukbench.sh

    Change the jpeg config for the photo model

    7 months ago

    waifu2x.lua

    Merge branch 'master' of github.com:nagadomi/waifu2x into dev

    3 months ago

    web.lua

    Add support for Korean language

    a year ago

    20 days ago

    a year ago
    4 months ago
    3 days ago

    a month ago

    README.md

    waifu2x
    Image Super-Resolution for Anime-style art using Deep Convolutional Neural Networks. And it supports photo.
    Demo-Application can be found at http://waifu2x.udp.jp/ .

    https://github.com/nagadomi/waifu2x

    Page 1 of 7

    GitHub - nagadomi/waifu2x: Image Super-Resolution for Anime-Style Art

    6/17/16, 21:42

    Summary
    Click to see the slide show.

    https://github.com/nagadomi/waifu2x

    Page 2 of 7

    GitHub - nagadomi/waifu2x: Image Super-Resolution for Anime-Style Art

    6/17/16, 21:42

    References
    waifu2x is inspired by SRCNN [1]. 2D character picture (HatsuneMiku) is licensed under CC BY-NC by piapro [2].
    [1] Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang, "Image Super-Resolution Using Deep Convolutional
    Networks", http://arxiv.org/abs/1501.00092
    [2] "For Creators", http://piapro.net/en_for_creators.html

    Public AMI
    Region: us-east-1 (N.Virginia)
    AMI ID: ami-568f823c
    AMI NAME: waifu2x-server
    Instance Type: g2.2xlarge
    OS: Ubuntu 14.04
    User: ubuntu
    Created at: 2016-03-22

    See ~/README.md
    Please update the git repo first.

    https://github.com/nagadomi/waifu2x

    Page 3 of 7

    GitHub - nagadomi/waifu2x: Image Super-Resolution for Anime-Style Art

    6/17/16, 21:42

    git pull

    Third Party Software


    Third-Party
    If you are a windows user, I recommend you to use waifu2x-cae(Just download from releases tab) or waifu2x-convercpp.

    Dependencies
    Hardware
    NVIDIA GPU

    Platform
    Torch7
    NVIDIA CUDA

    LuaRocks packages (excludes torch7's default packages)


    lua-csnappy
    md5
    uuid
    turbo

    Installation
    Setting Up the Command Line Tool Environment
    (on Ubuntu 14.04)

    Install CUDA
    See: NVIDIA CUDA Getting Started Guide for Linux
    Download CUDA
    sudo dpkg -i cuda-repo-ubuntu1404_7.5-18_amd64.deb
    sudo apt-get update
    sudo apt-get install cuda

    Install Package
    sudo apt-get install libsnappy-dev
    sudo apt-get install libgraphicsmagick1-dev

    Install Torch7
    See: Getting started with Torch

    https://github.com/nagadomi/waifu2x

    Page 4 of 7

    GitHub - nagadomi/waifu2x: Image Super-Resolution for Anime-Style Art

    6/17/16, 21:42

    And install luarocks packages.


    luarocks install graphicsmagick # upgrade
    luarocks install lua-csnappy
    luarocks install md5
    luarocks install uuid
    PREFIX=$HOME/torch/install luarocks install turbo # if you need to use web application

    Getting waifu2x
    git clone --depth 1 https://github.com/nagadomi/waifu2x.git

    Validation
    Testing the waifu2x command line tool.
    th waifu2x.lua

    Web Application
    th web.lua

    View at: http://localhost:8812/

    Command line tools


    Noise Reduction
    th waifu2x.lua -m noise -noise_level 1 -i input_image.png -o output_image.png

    th waifu2x.lua -m noise -noise_level 2 -i input_image.png -o output_image.png


    th waifu2x.lua -m noise -noise_level 3 -i input_image.png -o output_image.png

    2x Upscaling
    th waifu2x.lua -m scale -i input_image.png -o output_image.png

    Noise Reduction + 2x Upscaling


    th waifu2x.lua -m noise_scale -noise_level 1 -i input_image.png -o output_image.png

    th waifu2x.lua -m noise_scale -noise_level 2 -i input_image.png -o output_image.png


    th waifu2x.lua -m noise_scale -noise_level 3 -i input_image.png -o output_image.png

    Batch conversion

    https://github.com/nagadomi/waifu2x

    Page 5 of 7

    GitHub - nagadomi/waifu2x: Image Super-Resolution for Anime-Style Art

    6/17/16, 21:42

    find /path/to/imagedir -name "*.png" -o -name "*.jpg" > image_list.txt


    th waifu2x.lua -m scale -l ./image_list.txt -o /path/to/outputdir/prefix_%d.png

    See also th waifu2x.lua -h .

    Using photo model


    Please add -model_dir models/photo to command line option, if you want to use photo model. For example,
    th waifu2x.lua -model_dir models/photo -m scale -i input_image.png -o output_image.png

    Video Encoding
    * avconv is alias of ffmpeg on Ubuntu 14.04.
    Extracting images and audio from a video. (range: 00:09:00 ~ 00:12:00)
    mkdir frames
    avconv -i data/raw.avi -ss 00:09:00 -t 00:03:00 -r 24 -f image2 frames/%06d.png
    avconv -i data/raw.avi -ss 00:09:00 -t 00:03:00 audio.mp3

    Generating a image list.


    find ./frames -name "*.png" |sort > data/frame.txt

    waifu2x (for example, noise reduction)


    mkdir new_frames
    th waifu2x.lua -m noise -noise_level 1 -resume 1 -l data/frame.txt -o new_frames/%d.png

    Generating a video from waifu2xed images and audio.


    avconv -f image2 -framerate 24 -i new_frames/%d.png -i audio.mp3 -r 24 -vcodec libx264 -crf 16 video.mp4

    Train Your Own Model


    Notes: If you have cuDNN library, you can use cudnn kernel with -backend cudnn option. And you can convert trained
    cudnn model to cunn model with tools/cudnn2cunn.lua .

    Data Preparation
    Genrating a file list.
    find /path/to/image/dir -name "*.png" > data/image_list.txt

    You should use noise free images. In my case, waifu2x is trained with 6000 high-resolution-noise-free-PNG images.
    Converting training data.
    th convert_data.lua

    https://github.com/nagadomi/waifu2x

    Page 6 of 7

    GitHub - nagadomi/waifu2x: Image Super-Resolution for Anime-Style Art

    6/17/16, 21:42

    Train a Noise Reduction(level1) model


    mkdir models/my_model
    th train.lua -model_dir models/my_model -method noise -noise_level 1 -test images/miku_noisy.png
    th cleanup_model.lua -model models/my_model/noise1_model.t7 -oformat ascii
    # usage
    th waifu2x.lua -model_dir models/my_model -m noise -noise_level 1 -i images/miku_noisy.png -o output.png

    You can check the performance of model with models/my_model/noise1_best.png .

    Train a Noise Reduction(level2) model


    th train.lua -model_dir models/my_model -method noise -noise_level 2 -test images/miku_noisy.png
    th cleanup_model.lua -model models/my_model/noise2_model.t7 -oformat ascii
    # usage
    th waifu2x.lua -model_dir models/my_model -m noise -noise_level 2 -i images/miku_noisy.png -o output.png

    You can check the performance of model with models/my_model/noise2_best.png .

    Train a 2x UpScaling model


    th train.lua -model_dir models/my_model -method scale -scale 2 -test images/miku_small.png
    th cleanup_model.lua -model models/my_model/scale2.0x_model.t7 -oformat ascii
    # usage
    th waifu2x.lua -model_dir models/my_model -m scale -scale 2 -i images/miku_small.png -o output.png

    You can check the performance of model with models/my_model/scale2.0x_best.png .

    2016 GitHub, Inc.

    Terms

    Privacy

    Security

    https://github.com/nagadomi/waifu2x

    Contact

    Help

    Status

    API

    Training

    Shop

    Blog

    About

    Page 7 of 7

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy