Skip to content

찢기고 구겨진 이미지를 복원하여 추억을 되살려주는 웹 서비스, MTP

Notifications You must be signed in to change notification settings

Meet-the-past/docker

Repository files navigation

Meet The Past(MTP)

주제 소개

Meet The Past

찢겨지고 구겨진 추억의 이미지가 있으신가요? 누군가의 기억과 가까운 모습으로 추억을 되살려드리겠습니다.

사진을 원형에 가까운 모습으로 복구해드리는 서비스를 이용해보세요

소프트웨어 아키텍처

아키텍처

기술스택

⚡ Tech Stack

- Frontend: React, typescript, redux
- Backend : Django, Django-Rest-FrameWork
- Web Server: Nginx
- WSGI: Gunicorn
- Database: postgreSql
- AI : pytorch, dlib, OpenCV
- DB : postgresql
- Deployment: Docker, AWS EC2, AWS S3
- API Test : Postman
- API Documentation : Swagger
- monitoring : prometheus, grafana
Frontend Backend AI DevOps Other
TypeScript
React
Redux
Django
Redis
Rabbitmq
Celery
postgreSql
dlib
pytorch
OpenCV
Colab
Nginx
AWS
S3
Docker
Postman
GitHub
prometheus
grafana
Swagger

4. 실행 방법

Yarn 패키지 설치

git clone --recursive https://github.com/Meet-the-past/docker.git

cd docker/frontend
yarn

AI module 설치 (AI)

cd ../backend
mkdir ai
cd ai

cd Face_Enhancement/models/networks/
git clone https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
cp -rf Synchronized-BatchNorm-PyTorch/sync_batchnorm .
cd ../../../
cd Global/detection_models
git clone https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
cp -rf Synchronized-BatchNorm-PyTorch/sync_batchnorm .
cd ../../
Download the landmark detection pretrained model

cd Face_Detection/
wget http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
bzip2 -d shape_predictor_68_face_landmarks.dat.bz2
cd ../
Download the pretrained model, put the file Face_Enhancement/checkpoints.zip under ./Face_Enhancement, and put the file Global/checkpoints.zip under ./Global. Then unzip them respectively.

cd Face_Enhancement/
wget https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life/releases/download/v1.0/face_checkpoints.zip
unzip face_checkpoints.zip
cd ../
cd Global/
wget https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life/releases/download/v1.0/global_checkpoints.zip
unzip global_checkpoints.zip
cd ../../../../

Docker Start

docker-compose -f docker-compose.prod.yml up -d --build

5. 페이지 및 기능 소개

[회원가입 & 로그인]

로그인-회원가입

[메인 페이지]

메인페이지-online-video-cutter com

[이미지 업로드]

업로드1번-online-video-cutter com

[결과 페이지]

결과페이지-online-video-cutter com

[히스토리 페이지]

히스토리페이지-online-video-cutter com

[반응형 CSS 적용]

예시

6. 팀원

Name 정태원 김건혁 이채현 박성빈 박수연 장아령
Profile
Role Team Leader, Frontend, Backend, Devops Backend,Devops Frontend Backend,Devops Backend,Devops Backend, Devops
gitHub teawon Hyeok @chloe @SeongbinPark @PARK-Su-yeon @aristo0922

7. Reference

https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life

https://medium.com/@dkfud2121/meet-the-past-mtp-9f3df63c4217

Footer

About

찢기고 구겨진 이미지를 복원하여 추억을 되살려주는 웹 서비스, MTP

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •