mdx-net-submission - GitLite

KO | EN

gitlite — search

#javascript #python #ai #llm #go #machine-learning #linux #docker #windows #kubernetes #vue #security #ios #open-source

mdx-net-submission

(★ 134)

No description available.

파일 탐색기

최종 버전 다운로드 (.zip)

- .gitkeep
- __init__.py
- aicrowd_helpers.py
- music_demixing.py
- mixer.ckpt
- mixer_val.ckpt
- bass.onnx
- drums.onnx
- other.onnx
- vocals.onnx
- docker_build.sh
- docker_run.sh
- environ.sh
- parser.py
- verify_or_download_data.py
.gitattributes
.gitignore
aicrowd.json
apt.txt
base_model.py
configs.py
download_demucs.py
environment.yml
eval_musdb18.py
globalsdr_musdb18.py
LICENSE
mdxnet.py
models.py
postBuild
predict.py
README.md
requirements.txt
run.sh
score.py
test.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/kuielab/mdx-net-submission

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd mdx-net-submission

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# MDX-Net Music Source Separation

This repository contains the source code and pretrained models for MDX-Net's submission to the [Sony Demixing Challenge](https://www.aicrowd.com/challenges/music-demixing-challenge-ismir-2021), which ranked second place.

This branch is undergoing refractorization, the code may break for you. Please see [Reproducible Submission](#for-musicians-reproducible-submission) for branches that contain working source code and pretrained models.

## For machine learning scientists

Please see [MDX-Net](https://github.com/kuielab/mdx-net) for the code to train your own models.

## For musicians (Reproducible Submission)

Please see the following branches for instructions to install and use the pretrained models.
- MDX Track A submission: [leaderboard_A](https://github.com/kuielab/mdx-net-submission/tree/leaderboard_A)
	- Uses only [MUSDB18-HQ dataset](https://zenodo.org/record/3338373), lower quality stems extracted
- MDX Track B submission: [leaderboard_B](https://github.com/kuielab/mdx-net-submission/tree/leaderboard_B)
	- Uses extra datasets, higher quality stems extracted

## Installation

```
conda env create -f environment.yml -n mdx-submit
pip install -r requirements.txt
```