Data

Tools

Indexes

Applications

Experiments

Open Source Science

autolabelme

https://github.com/panhunger/autolabelme

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 (2.1%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: PanHunger
  • License: other
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 33.3 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed 7 months ago
Metadata Files
Readme License Citation

README.md

AUTO-LABELME

基于Labelme、SAM series、YOLO series等前沿框架与模型，设计了Auto-Labelme软件

特色之处

  • [x] 支持少样本标注，在少量标注数据的基础上，运用SAM算法、预训练Yolo自动生成无标签数据的伪标签，扩充标注数据量
  • [x] 借助Clip和SAM series等模型，对标注结果进行自动微调，提升标注的精准度
  • [x] 兼容各类模型的数据格式，实现一键式导出
  • [x] 零代码操作完成训练与评估的便捷功能
  • [ ] 支持多人协同标注作业
  • [ ] 利用数据库存储标签和图片
  • [ ] 支持联网使用私人网盘的模型和配置

安装方法

安装方法与Labelme相同，另外需要配置SAM2和Ultralystic，请参考对应的开源库

建议使用 Anaconda 创建虚拟环境，命令如下： conda env create -f conda_environment.yml 会创建一个名称为 auto-labelme 的虚拟环境

自动标注

训练界面

目前虽然可以有无代码的可视化训练界面，但是功能不完整，建议还是使用ultralystic的训练方法

Acknowledgement

本项目基于 wkentaro/labelme.

Owner

  • Name: Zhiqun Pan
  • Login: PanHunger
  • Kind: user
  • Location: Shanghai, China
  • Company: University of Shanghai for Science and Technology

Hi, my name is Zhiqun Pan, i a Doctoral student, majoring in Control Science and Engineering at University of Shanghai for Science and Technology.

Citation (CITATION.cff) 

cff-version: 1.0.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Pan"
  given-names: "Zhiqun"
  orcid: "https://orcid.org/0000-0003-3360-9499"
title: "AUTO-Labelme: Automatic Image Polygonal Annotation with Python"
doi: 10.5281/zenodo.5711226
url: "https://github.com/PanHunger/auto-labelme"
license: GPL-3

GitHub Events

Total
  • Push event: 3
  • Public event: 1
Last Year
  • Push event: 3
  • Public event: 1

Dependencies

requirements-dev.txt pypi
  • github2pypi ==1.0.0 development
  • pytest * development
  • pytest-qt * development
  • ruff ==0.1.9 development
  • twine * development
setup.py pypi
  • Pillow >=2.8
  • PyYAML *
  • gdown *
  • imgviz >=1.7.5
  • matplotlib *
  • natsort >=7.1.0
  • numpy *
  • onnxruntime >=1.14.1,
  • osam >=0.2.2
  • qtpy *
  • scikit-image *
  • termcolor *