forked from boostcampaitech6/level2-3-cv-finalproject-cv-08
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[FEAT] Readme Code Merge (boostcampaitech6#9)
* Feat : First Commit * Update readme.md * Update readme.md * Feat : modify readme * Update readme.md * Update readme.md * Update README.md * Update readme.md * Update readme.md --------- Co-authored-by: jouhy <[email protected]> Co-authored-by: Im._.SH <[email protected]> Co-authored-by: 김태양_T6044 <[email protected]>
- Loading branch information
4 people
authored
Mar 28, 2024
1 parent
4d02e3a
commit 12fabe7
Showing
2 changed files
with
143 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1 +1,34 @@ | ||
| # voice2face-modeling- | ||
| # Voice2Face-Modeling | ||
| <img src="https://img.shields.io/badge/PyTorch-EE4C2C?style=for-the-badge&logo=PyTorch&logoColor=white"> <img src="https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=Python&logoColor=white"> <img src="https://img.shields.io/badge/opencv-5C3EE8?style=for-the-badge&logo=opencv&logoColor=white"> <img src="https://img.shields.io/badge/github-181717?style=for-the-badge&logo=github&logoColor=white"> <img src="https://img.shields.io/badge/git-F05032?style=for-the-badge&logo=git&logoColor=white"> <img src="https://img.shields.io/badge/Docker-2496ED?style=for-the-badge&logo=Docker&logoColor=white"> <img src="https://img.shields.io/badge/NCP-03C75A?style=for-the-badge&logo=Naver&logoColor=white"> <img src="https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=Linux&logoColor=white"> | ||
| # File Tree | ||
|
|
||
| modeling | ||
| ├─ pytorch_template | ||
| │ ├─ config | ||
| │ ├─ models | ||
| │ ├─ modules | ||
| │ ├─ predict.py | ||
| │ └─ train.py | ||
| ├─ sf2f | ||
| │ ├─ infer.py | ||
| │ ├─ inference_fuser.py | ||
| │ ├─ test.py | ||
| │ ├─ train.py | ||
| ├─ SimSwap | ||
| │ └─ inference_swap.py | ||
| └─ wcgan-gp | ||
| ├─ inference.py | ||
| └─ train.py | ||
|
|
||
| # Getting Started | ||
|
|
||
|
|
||
|
|
||
| ## References | ||
| [Speech Fusion to Face](https://arxiv.org/pdf/2006.05888.pdf) | ||
|
|
||
| [Conditional GAN](https://arxiv.org/pdf/1411.1784.pdf) | ||
|
|
||
| [Sim Swap](https://github.com/neuralchen/SimSwap) | ||
|
|
||
| [Pytorch Template](https://github.com/victoresque/pytorch-template) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,109 @@ | ||
|
|
||
|
|
||
| # 🔊목소리로 가상 얼굴 생성 서비스 [너의목소리가보여] | ||
| <img src="https://img.shields.io/badge/PyTorch-EE4C2C?style=for-the-badge&logo=PyTorch&logoColor=white"> <img src="https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=Python&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/opencv-5C3EE8?style=for-the-badge&logo=opencv&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/mysql-4479A1?style=for-the-badge&logo=mysql&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/github-181717?style=for-the-badge&logo=github&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/git-F05032?style=for-the-badge&logo=git&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/Docker-2496ED?style=for-the-badge&logo=Docker&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/Flask-000000?style=for-the-badge&logo=Flask&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/Prometheus-E6522C?style=for-the-badge&logo=Prometheus&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/Grafana-F46800?style=for-the-badge&logo=Grafana&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/NCP-03C75A?style=for-the-badge&logo=Naver&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/RabbitMQ-FF6600?style=for-the-badge&logo=RabbitMQ&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/Celery-37814A?style=for-the-badge&logo=Celery&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/minio-C72E49?style=for-the-badge&logo=minio&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/amazonrds-527FFF?style=for-the-badge&logo=amazonrds&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/svelte-FF3E00?style=for-the-badge&logo=svelte&logoColor=white"> | ||
| <img src="https://img.shields.io/badge/Linux-FCC624?style=for-the-badge&logo=Linux&logoColor=white"> | ||
|
|
||
| # ✅ Project Overview | ||
| <p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/73b51b54-e7af-4268-a7e5-84458ecc3056" style="max-width: 100%; height: auto;"></p> | ||
|
|
||
| 사용자의 목소리를 입력 받아 얼굴을 생성하고, | ||
| 생성된 얼굴을 다른 영상 속 얼굴에 합성하여 결과물 제공하는 서비스 제작 | ||
| ### ✔️ 기획의도 | ||
|
|
||
| <p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/af1a03ba-1bdd-4b3b-b2f7-502e29f82c58" style="max-width: 100%; height: auto;"></p> | ||
|
|
||
| - 사생활 보호와 사용자 경험을 향상 | ||
| - Multi-modal 기술에 대한 경험 | ||
| - 실제 서비스를 개발하고 개선하는 것 | ||
|
|
||
| <p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/48ba55f8-ea8b-4850-b555-5c5f5335395c" style="max-width: 100%; height: auto;"></p> | ||
|
|
||
| 1. 요즘 얼굴을 드러내지 않고 활동하는 사람이 많아졌다는 점 | ||
| 2. 사생활이나 목소리와 어울리지 않아 이질감을 주는 문제 | ||
|
|
||
| 이를 해결하기 위하여 **성대와 울림통에 의해 목소리가 결정되고, 사람의 목소리에서 추출한 특성으로 여러 생리학적 구조와 특성을 구별할 수 있음** 을 이용합니다. | ||
|
|
||
| 이런 ***목소리와 얼굴 간의 상관 관계*** 를 학습하도록 하였습니다. | ||
|
|
||
| ### ✔️ 기대효과 | ||
| <p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/dc734e1a-4867-4e28-b266-76daf1241c85" style="max-width: 100%; height: auto;"></p> | ||
|
|
||
| ### ✔️ 차별점 | ||
| ⭐ **도파민(중독)** 개발 | ||
| - 최종 프로젝트를 구현하기 위해 `애자일하게 문제를 접근` 하여 **Bottom Up** 방식으로 개발할 부분을 정리하여 단계적으로 서비스를 고도화 해나갈 수 있도록 하였습니다. | ||
| - 모든 프로젝트에 사용했던 코드를 **`모듈화`** 을 통해 재사용 가능하도록 하였으며, 이를 활용하여 서비스 고도화 작업을 이뤄나갔습니다. | ||
| - `실 서비스`까지 프로젝트로 제공하겠다는 마음과, 순간 순간 집중하는 팀원들간의 `단합력`으로 도파민 풀충전 개발을 항상 함께 해나갔습니다. | ||
| ### ➡️ 그 결과 **2일 만에 사용 횟수 🌟 100회** 달성 🌟 | ||
|
|
||
| # ✅ 팀원 소개 | ||
| **우리는 `조화`와 `지속 가능한 성장`을 추구하는 `팀 MakeZenerator` 입니다.** | ||
|
|
||
| **각자의 위치에서 `오너십`을 가지고 `적극적으로 참여`함으로써, 우리는 협업의 힘을 최대화합니다. `치열한 고민`과 `끊임없는 학습`으로, 자신의 역량을 키우고 새로운 아이디어를 탐구합니다.** **우리의 모토는 `함께 성장한다`입니다. 서로를 뒷받침하며 동료들과의 소통을 통해 더 나은 팀을 만들어갑니다.** | ||
|
|
||
| ***열정과 도전 정신으로, 우리는 항상 앞으로 나아가고 있습니다 !*** | ||
|
|
||
| ### 👥 팀원 | ||
| | [신호준] | [김태양]| [김혜지] | [정소윤] | [성주희] | [임서현] | | ||
| |--|--|--|--|--|--| | ||
| |<p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/46462e68-25ee-4b9e-ba55-c1d47be9d965" height="150px" width="150px"></p>|<p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/e300980a-b7e7-4d3d-96d6-680804a1554d" height="150px" width="150px"></p>|<p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/7392ccf4-afc4-4936-8003-621f277ec158" height="150px" width="150px"></p>|<p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/223e0b57-bf61-4035-bf98-0712cb7f3dd0" height="150px" width="150px"></p>|<p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/f90e6806-2048-4321-8bc2-b088e4a6aaf2" height="150px" width="150px"></p>|<p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/21e2dcd9-c982-4695-a640-0770da6694bf" height="150px" width="150px"></p> | ||
| |<p align='center'>[<img src="https://img.shields.io/badge/github-181717?style=for-the-badge&logo=github&logoColor=white">](https://github.com/internationalwe)</p>|<p align='center'>[<img src="https://img.shields.io/badge/github-181717?style=for-the-badge&logo=github&logoColor=white">](https://github.com/taeyang916)</p>|<p align='center'>[<img src="https://img.shields.io/badge/github-181717?style=for-the-badge&logo=github&logoColor=white">](https://github.com/carboxaminoo)</p>|<p align='center'>[<img src="https://img.shields.io/badge/github-181717?style=for-the-badge&logo=github&logoColor=white">](https://github.com/soyoonjeong)</p>|<p align='center'>[<img src="https://img.shields.io/badge/github-181717?style=for-the-badge&logo=github&logoColor=white">](https://github.com/jouhy)</p>|<p align='center'>[<img src="https://img.shields.io/badge/github-181717?style=for-the-badge&logo=github&logoColor=white">](https://github.com/dlatjgus0612)</p>| | ||
|
|
||
| ### 👥 역할 | ||
| <p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/f2bb09f6-53d8-46f9-9728-d271778bdd1d" style="max-width: 100%; height: auto;"></p> | ||
|
|
||
| # ✅ 타임라인 | ||
| 팀 구성, 방향성을 설정하고 프로젝트를 설계하였습니다. 이후 `서비스 파이프라인`을 설계, `sprint 주기`에 맞춰 회의를 진행하고, `기능명세서`를 작성하여 `task`를 진행하였습니다. | ||
|
|
||
| 원활한 서비스 완성을 위해 `Version`을 나누었고, | ||
| 서비스를 실습해보기 위해 간단한 v0.1, | ||
| 이후 데이터 파이프라인을 구축하고, 시스템 아키텍처와 서비스 전반을 고도화하여 현재의 **`v1.0 최종 프로젝트 배포`** 가 완료된 상태입니다. | ||
|
|
||
| ✔️ 타임라인 표 | ||
| <p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/fcde2215-042c-48ea-983b-0e570fffa8d4" style="max-width: 100%; height: auto;"></p> | ||
|
|
||
| # ✅ 시스템 아키텍처 & 파이프라인 | ||
|
|
||
| ✔️ 아키텍처 사진 | ||
| <p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/1722531e-4ebe-4f57-bf0d-08b6dc80c0ea" style="max-width: 100%; height: auto;"></p> | ||
|
|
||
| ✔️ 파이프라인 사진 | ||
| <p align="center"><img src="https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/assets/46400961/538e368d-83ef-43a6-8aca-87826dee824e" style="max-width: 100%; height: auto;"></p> | ||
|
|
||
| # ✅ Getting Started | ||
| > 아래 Readme를 통해 직접 프로젝트에 구현된 코드를 살펴볼 수 있습니다. | ||
| ### 💫 Model | ||
| - [Model](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/modeling) / [README.md](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/modeling/README.md) | ||
|
|
||
| ### 📊 Data | ||
| - [Data Pipeline](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/data) / [README.md](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/data/README.md) | ||
|
|
||
| ### 🖼️ Frontend | ||
| - [Frontend](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/frontend) / [README.md](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/frontend/README.md) | ||
|
|
||
| ### 💻 Backend | ||
| - [Backend](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/backend) / [README.md](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/backend/README.md) | ||
|
|
||
| ### 🌐 MLOps | ||
| - [MLOps](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/mlops) / [README.md](https://github.com/boostcampaitech6/level2-3-cv-finalproject-cv-08/tree/main/mlops/README.md) | ||
|
|
||
| ## Links | ||
| ### [YOUTUBE 발표자료](https://youtu.be/VJL6UQUTKrY?si=ZEs1L4BqvAnHlwvh) | ||
| updated. 2024.04.02 | ||
| ### [NOTION LINK](https://truealex.notion.site/CV-08-d7987f38c09f470aababdedd822e96ca?pvs=4) | ||
| updated. 2024.03.31 |