mmdetection_fashion

https://github.com/doxb/mmdetection_fashion

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (4.2%) to scientific vocabulary

Last synced: 6 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: DoxB
License: apache-2.0
Language: Python
Default Branch: main
Size: 567 MB

Statistics

Stars: 0
Watchers: 1
Forks: 1
Open Issues: 0
Releases: 0

Created over 3 years ago · Last pushed about 3 years ago

Metadata Files

Readme License Citation

KGUopensw_2

OpenMMLab website ^HOT OpenMMLab platform ^{TRY IT OUT}

## 경기대학교 Open Source Software 실습(DD847_2148) 2조 기말과제
🙍‍♂️임정규_DoxB(조장) 🙍‍♂️김성환_OsanAB 🙍‍♂️유준혁_JunHyeokYoo

버전별 추가 사항

ver 1.0.1 - mmdetection 환경 및 MASK-RCNN Config 라이브러리 다운로드
ver 1.0.2 - CPU, GPU, Colab(GPU) demo를 통해 구동 확인
ver 1.0.3 - MASK-RCNN Config 에서 훈련모델 사용할 것 및 Base 에폭 조절 업뎃
ver 1.1.0 - CPU, GPU, Colab(GPU) 훈련 / 검증 소스 구현

datasets link

datasets
해당 레포지토리에 위치시킵니다.

CPU 실행 명령어

훈련: python tools/train.py configs/base/defaultruntimecpu.py
검증: python tools/test.py configs/base/defaultruntimecpu.py workdirs/defaultruntimecpu/latest.pth --show-dir workdirs/result

GPU 실행 명령어

훈련: python tools/train.py configs/base/defaultruntimegpu.py
검증: python tools/test.py configs/base/defaultruntimegpu.py workdirs/defaultruntimegpu/latest.pth --show-dir workdirs/result

Colab_GPU 실행 명령어

훈련: !python tools/train.py configs/base/defaultruntimecolabgpu.py
검증: !python tools/test.py configs/base/defaultruntimecolabgpu.py workdirs/defaultruntimecolabgpu/latest.pth --show-dir work_dirs/result

훈련 환경과 폴더 수정

anaconda와 colab으로 기말과제를 수행하였음

본래 mmdetection내의 있는 파일과 폴더를 대부분 가져왔으나 Docker 폴더를 제외시켰고 mmdetection내의 사용하지 않는 구조는 제외하였음

MASK-RCNN 학습 데이터 조절

주어진 실습 데이터중 훈련을 제대로 하기 위해 Train, Validation, Test 데이터의 비중을 중복되지 않게 8:1:1로 나누어 분배하였음

(총 5926개의 data이기에 Train-4765, Val-577, Test-584로 분배함)

실습데이터는 이러한 비율로 데이터가 나뉘어져 있는 것이 아닌 카테고리 별로 데이터가 나누어져있어 이를 각 카테고리마다 Train-Val-Test를 분리할 필요가 있으니 이를 주피터 노트북을 활용하여 카테고리별로 분류되어있는 이미지를 취합함

마찬가지로 나뉘어져있는 json도 분류하여 Train-Val-Test 별로 취합함

학습결과

pants

jumper

t-shirt

Owner

Login: DoxB
Kind: user

Repositories: 2
Profile: https://github.com/DoxB

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMDetection Contributors"
title: "OpenMMLab Detection Toolbox and Benchmark"
date-released: 2018-08-22
url: "https://github.com/open-mmlab/mmdetection"
license: Apache-2.0

GitHub Events

Total

Last Year

Dependencies

requirements/albu.txt pypi

albumentations >=0.3.2

requirements/build.txt pypi

cython *
numpy *

requirements/docs.txt pypi

docutils ==0.16.0
markdown >=3.4.0
myst-parser *
sphinx ==5.3.0
sphinx-copybutton *
sphinx_markdown_tables >=0.0.17
sphinx_rtd_theme *

requirements/mminstall.txt pypi

mmcv-full >=1.3.17

requirements/optional.txt pypi

cityscapesscripts *
imagecorruptions *
sklearn *

requirements/readthedocs.txt pypi

mmcv *
torch *
torchvision *

requirements/runtime.txt pypi

matplotlib *
numpy *
pycocotools *
scipy *
six *
terminaltables *

requirements/tests.txt pypi

asynctest * test
codecov * test
flake8 * test
interrogate * test
isort ==4.3.21 test
kwarray * test
onnx ==1.7.0 test
onnxruntime >=1.8.0 test
protobuf <=3.20.1 test
pytest * test
ubelt * test
xdoctest >=0.10.0 test
yapf * test

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science